Potential Reading List
About this potential to read list :
-
To educate my students in class, new members of my team with basic tutorials, and to help existing members understand advanced topics. This website includes a (growing) list of tutorials and papers we survey for such a purpose (Since 2017).
-
At the beginning of each semester, I collect a messy list of potential readings and put them here. Then my students will choose papers they want to review (mostly from this list) and we make a plan for that semester’s reading session schedule.
-
In summary, this is a messy list, only for planning and filtering purposes.
- Topic I: Foundations, Analysis and Theory
- Topic II: DNN with Varying Structures
- Topic III: Reliable and Benchmarking and Applications
- Topic IV: Optimization
- Topic V: Generative
- Topic VI: Reinforcement
- Topic VII: Graphs
- Topic VIII: 2019 Learning Strategies
Potential Deep-Learning-Papers provided to my Course Students to reproduce in 2019-Fall course
Potential Deep-Learning-Papers-Reading-for-Graphs we read in 2019-Spring
- GNN code repos: https://paperswithcode.com/task/graph-embedding
- Similar course: https://www.math.uwaterloo.ca/~bico/co759/2018/index.html
Basics:
- GraphSAGE / GatedGNN /
- ChebNet, Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- Relational inductive biases, deep learning, and graph networks, et al, Oriol Vinyals, Yujia Li, Razvan Pascanu, 2018
- Graph Neural Networks: A Review of Methods and Applications https://arxiv.org/pdf/1812.08434.pdf
- Modeling relational data with graph convolutional networks, 2017, Michael Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, Max Welling
- An Experimental Study of Neural Networks for Variable Graphs, workshop 2018 ICLR
- How Powerful are Graph Neural Networks? / Keyulu Xu, Weihua Hu, Jure Leskovec, Stefanie Jegelka, 2018
- A Comprehensive Survey on Graph Neural Networks 2018, https://arxiv.org/pdf/1901.00596.pdf
- Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning Qimai Li, Zhichao Han, Xiao-Ming Wu,
- K Xu, W Hu, J Leskovec, S Jegelka - arXiv preprint arXiv:1810.00826, 2018 Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., and Monfardini, G. The graph neural network model. IEEE Transactions on Neural Networks, 20(1):61–80, 2009.
- Convolutional neural networks over tree structures for programming language processing. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016.
- Semi-Supervised Classification with Graph Convolutional Networks Authors: Thomas N. Kipf, Max Welling
- Graph Attention Networks, Authors: Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio
- Learning Convolutional Neural Networks for Graphs, http://proceedings.mlr.press/v48/niepert16.pdf
- Inductive representation learning on large graphs, NIPS16
- Higher-order clustering in networks, H Yin, AR Benson, J Leskovec, Physical Review E 97 (5), 052306 PDF
Basic graph represenation learning:
- RECS: Robust Graph Embedding Using Connection Subgraphs
- LASAGNE: Locality And Structure Aware Graph Node Embedding
- Adversarially Regularized Graph Autoencoder for Graph Embedding
- All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks
- LanczosNet: Multi-Scale Deep Graph Convolutional Networks
- Graph Neural Networks with convolutional ARMA filters
- Geniepath: Graph neural networks with adaptive receptive paths Z Liu, C Chen, L Li, J Zhou, X Li, L Song, Y Qi arXiv preprint arXiv:1802.00910
- Link Prediction Based on Graph Neural Networks arXiv:1802.09691
- Deep Graph Infomax, P Veličković, W Fedus, WL Hamilton, P Liò, Y Bengio… - arXiv preprint arXiv 2018
- ICML18, Anonymous Walk Embeddings, Authors: Sergey Ivanov, Evgeny Burnaev
- Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks Authors: Federico Monti, Michael Bronstein, Xavier Bresson
- Diffusion-convolutional neural networks, NeuroIPS16
- Convolutional networks on graphs for learning molecular fingerprints, NeuroIPS15
- Geometric deep learning: going beyond euclidean data, 2017
- Dynamic graph cnn for learning on point clouds, 2018
GNN extend/beyond:
- GM-PLL: Graph Matching based Partial Label Learning
- Graph Matching Networks for Learning the Similarity of Graph Structured Objects, 2019
- A Functional Representation for Graph Matching
- Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
- Sample Efficient Semantic Segmentation using Rotation Equivariant Convolutional Networks J Linmans, J Winkens, BS Veeling, TS Cohen, M Welling arXiv preprint arXiv:1807.00583
- 2018, Rotation Equivariant CNNs for Digital Pathology BS Veeling, J Linmans, J Winkens, T Cohen, M Welling arXiv preprint arXiv:1806.03962
- Emerging Convolutions for Generative Normalizing Flows E Hoogeboom, R Berg, M Welling, arXiv preprint arXiv:1901.11137
- 3d steerable cnns: Learning rotationally equivariant features in volumetric data M Weiler, M Geiger, M Welling, W Boomsma, T Cohen Advances in Neural Information Processing Systems, 10402-10413
- Convolutional networks for spherical signals T Cohen, M Geiger, J Köhler, M Welling arXiv preprint arXiv:1709.04893
- Graph Convolutional Matrix Completion R van den Berg, TN Kipf, M Welling stat 1050, 7
- Relaxed Quantization for Discretized Neural Networks
- Probabilistic Binary Neural Networks, JWT Peters, M Welling arXiv preprint arXiv:1809.03368
- Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning, C Qu, S Mannor, H Xu, Y Qi, L Song, J Xiong, arXiv preprint arXiv:1901.09326
- Double Neural Counterfactual Regret Minimization H Li, K Hu, Z Ge, T Jiang, Y Qi, L Song arXiv preprint arXiv:1812.10607 2018
- Neural Model-Based Reinforcement Learning for Recommendation X Chen, S Li, H Li, S Jiang, Y Qi, L Song arXiv preprint arXiv:1812.10613
- Deep hyperspherical learning W Liu, YM Zhang, X Li, Z Yu, B Dai, T Zhao, L Song Advances in Neural Information Processing Systems, 3950-3960
- Graph Edit Distance Computation via Graph Neural Networks Yunsheng Bai, Hao Ding, Song Bian, Ting Chen, Yizhou Sun, Wei Wang
- Hierarchical Graph Representation Learning with Differentiable Pooling Authors: Rex Ying, Jiaxuan You, Christopher Morris, Xiang Ren, William L. Hamilton, Jure Leskovec
- FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling Authors: Jie Chen, Tengfei Ma, Cao Xiao, Abstract: The graph convolutional networks (GCN) recently proposed by Kipf and Welling are an effective graph model for semi-supervised learning. Such a model, however, is transductive in nature because parameters are learned through convolutions with both training and test data
- Representation Learning on Graphs with Jumping Knowledge Networks Authors: Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, Stefanie Jegelka Abstract: Recent deep learning approaches for representation learning on graphs follow a neighborhood aggregation procedure. We analyze some important properties of these models, and propose a strategy to overcome those. In particular, the range of “neighboring”
- Gauge Equivariant Convolutional Networks and the Icosahedral CNN TS Cohen, M Weiler, B Kicanaoglu, M Welling - arXiv preprint arXiv:1902.04615, 2019 The idea of equivariance to symmetry transformations provides one of the first
- Learning Invariant Representations Of Planar Curves Authors: Gautam Pai, Aaron Wetzler, Ron Kimmel
Generate:
- Learning Bayesian Networks is NP-Complete by DM Chickering - 1996 - Cited by 1069
- Neural scene representation and rendering, science 2018
- Relational Deep Reinforcement Learning, 2018
- Generating sentences from a continuous space, 2015
- Encoding Robust Representation for Graph Generation
- Syntax-Directed Variational Autoencoder for Molecule Generation H Dai, Y Tian, B Dai, S Skiena, L Song, International Conference on Machine Learning
- Graphical Generative Adversarial Networks C Li, M Welling, J Zhu, B Zhang arXiv preprint arXiv:1804.03429
- 2019, Recurrent Inference Machines for Reconstructing Heterogeneous MRI Data K Lønning, P Putzky, JJ Sonke, L Reneman, MWA Caan, M Welling
- Deep Reinforcement Learning for NLP, ACL18
- DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation R Assouel, M Ahmed, MH Segler, A Saffari, Y Bengio - arXiv preprint arXiv …, 2018
- Edge-exchangeable graphs and sparsity, NIPS16, Authors: Diana Cai, Trevor Campbell, Tamara Broderick Abstract: Many popular network models rely on the assumption of (vertex) exchangeability, in which the distribution of the graph is invariant to relabelings of the vertices. However, the Aldous-Hoover theorem guarantees that these graphs are dense or empty with probability one, whereas many real-world graphs are sparse. We present an alternative notion of exchangeability for random graphs, which we call edge exchangeability,
- Junction Tree Variational Autoencoder for Molecular Graph Generation Authors: Wengong Jin, Regina Barzilay, Tommi Jaakkola
- Towards Variational Generation of Small Graphs Authors: Martin Simonovsky, Nikos Komodakis
- GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML2018 Authors: Jiaxuan You, Rex Ying, Xiang Ren, William Hamilton, Jure Leskovec
- Pixels to Graphs by Associative Embedding Authors: Alejandro Newell, Jia Deng Abstract: Graphs are a useful abstraction of image content. Not only can graphs represent details about individual objects in a scene but they can capture the interactions between pairs of objects. We present a method for training a convolutional neural network such that it takes in an input image and produces a full graph definition.
- Syntax-Directed Variational Autoencoder for Structured Data Authors: Hanjun Dai, Yingtao Tian, Bo Dai, Steven Skiena, Le Song
- NetGAN: Generating Graphs via Random Walks, ICML2018 Authors: Aleksandar Bojchevski, Oleksandr Shchur, Daniel Zügner, Stephan Günnemann
- Graphons, mergeons, and so on! Authors: Justin Eldridge, Mikhail Belkin, Yusu Wang Abstract: In this work we develop a theory of hierarchical clustering for graphs. Our modelling assumption is that graphs are sampled from a graphon, which is a powerful and general model for generating graphs and analyzing large networks.
- Convolutional Imputation of Matrix Networks Authors: Qingyun Sun, Mengyuan Yan, David Donoho, boyd
with GM:
- Neural Graph Machines: Learning Neural Networks Using Graphs
- Graph HyperNetworks for Neural Architecture Search
- MRF Optimization by Graph Approximation
- Credit Assignment Techniques in Stochastic Computation Graphs
- Graph Refinement based Tree Extraction using Mean-Field Networks and Graph Neural Networks, R Selvan, T Kipf, M Welling, JH Pedersen, J Petersen, M de Bruijne arXiv preprint arXiv:1811.08674
- SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient
- Combinatorial Bayesian Optimization using Graph Representations C Oh, JM Tomczak, E Gavves, M Welling arXiv preprint arXiv:1902.00448
- Learning Steady-States of Iterative Algorithms over Graphs H Dai, Z Kozareva, B Dai, A Smola, L Song International Conference on Machine Learning, 1114-1122
- A Hilbert space embedding for distributions. In Proceedings of the International Conference on Algorithmic Learning Theory, volume 4754, pp. 13–31. Springer, 2007.
- Hilbert space embeddings of conditional distributions. In Proceedings of the International Conference on Machine Learning, 2009.
- Nonparametric tree graphical models. In 13th Workshop on Artificial Intelligence and Statistics, volume 9 of JMLR workshop and conference proceedings, pp. 765–772, 2010
- Kernel belief propagation. In Proc. Intl. Con- ference on Artificial Intelligence and Statistics, volume 10 of JMLR workshop and conference proceedings, 2011.
- Injective Hilbert space embeddings of probability measures. In Proceedings of Annual Conference. Computational Learning Theory, pp. 111–122, 2008.
- Jebara, T., Kondor, R., and Howard, A. Probability product kernels. J. Mach. Learn. Res., 5:819–844, 2004.
- Kernel-based just-in-time learning for passing expectation propagation messages. In Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, UAI 2015, July 12-16, 2015, Amsterdam, The Netherlands, pp. 405–414, 2015
- Deeply learning the messages in message passing inference. In Advances in Neural Information Processing Systems, 2015.
- Minka, T. The EP energy function and minimization schemes. See www. stat. cmu. edu/minka/papers/learning. html, August, 2001.
- Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing Authors: Davide Bacciu, Federico Errica, Alessio Micheli Abstract: We introduce the Contextual Graph Markov Model, an approach combining ideas from generative models and neural networks for the processing of graph data.
- Inference in probabilistic graphical models by Graph Neural Networks Authors: KiJung Yoon, Renjie Liao, Yuwen Xiong, Lisa Zhang, Ethan Fetaya, Raquel Urtasun, Richard Zemel, Xaq Pitkow Abstract: A useful computation when acting in a complex environment is to infer the marginal probabilities or most probable states of task-relevant variables.
Applications and more:
- End-to-end differentiable physics for learning and control
- Learning to represent programs with graphs
- KG^ 2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings Y Zhang, H Dai, K Toraman, L Song arXiv preprint arXiv:1805.12393
- video2net: Extracting dynamic interaction networks from multi-person discussion videos / https://www.cs.stanford.edu/~srijan/pubs/paper-video2net.pdf
- Theory and Application of Network Biology Towards Precision Medicine
- Attention, Learn to Solve Routing Problems! W Kool, H van Hoof, M Welling
- Extraction of Airways using Graph Neural Networks R Selvan, T Kipf, M Welling, JH Pedersen, J Petersen, M de Bruijne arXiv preprint arXiv:1804.04436
- Deep Learning with Permutation-invariant Operator for Multi-instance Histopathology Classification, JM Tomczak, M Ilse, M Welling, arXiv preprint arXiv:1712.00310
- Sequence2Vec: a novel embedding approach for modeling transcription factor binding affinity landscape H Dai, R Umarov, H Kuwahara, Y Li, L Song, X Gao Bioinformatics 33 (22), 3575-3583
- Learning combinatorial optimization algorithms over graphs H Dai, EB Khalil, Y Zhang, B Dilkina, L Song arXiv preprint arXiv:1704.01665
- Neural network-based graph embedding for cross-platform binary code similarity detection, X Xu, C Liu, Q Feng, H Yin, L Song, D Song Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications …
- Convolutional neural network based on SMILES representation of compounds for detecting chemical motif M Hirohara, Y Saito, Y Koda, K Sato, Y Sakakibara - BMC Bioinformatics, 2018
- Heterogeneous Graph Neural Networks for Malicious Account Detection Z Liu, C Chen, X Yang, J Zhou, X Li, L Song -
- Diffusion-Based Approximate Value Functions Authors: Martin Klissarov, Doina Precup
- Mean Field Multi-Agent Reinforcement Learning Authors: Yaodong Yang, Rui Luo, Minne Li, Ming Zhou, Weinan Zhang, Jun Wang Abstract: Existing multi-agent reinforcement learning methods are limited typically to a small number of agents. When the agent number increases largely, the learning becomes intractable due to the curse of the dimensionality and the exponential growth of agent interactions
- Protein–ligand scoring with convolutional neural networks
- Visualizing convolutional neural network protein-ligand scoring
- KDEEP: Protein–Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks, 2018
- D3R Grand Challenge 2: blind prediction of protein–ligand poses, affinity rankings, and relative binding free energies
- Structured sequence modeling with graph convolutional recurrent networks,” arXiv preprint arXiv:1612.07659, 2016.
- Structural-rnn: Deep learning on spatio-temporal graphs,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 5308–5317.
- Prioritizing network communities
- Community detection and stochastic block models: recent developments
- Android Malware Detection using Large-scale Network Representation Learning + Deep Android Malware Detection Pdf + PDF
Robustness and scalable
- Does Your Model Know the Digit 6 Is Not a Cat? A Less Biased Evaluation of” Outlier” Detectors
- Faithful and Customizable Explanations of Black Box Models H Lakkaraju, E Kamar, R Caruana, J Leskovec - 2019
- Adversarial Examples as an Input-Fault Tolerance Problem
- Adversarial Attack on Graph Structured Data https://arxiv.org/abs/1806.02371
- Adversarial Attacks on Neural Networks for Graph Data, https://dl.acm.org/citation.cfm?id=3220078 (edited)
- Android Malware Detection using Large-scale Network Representation Learning, https://arxiv.org/abs/1806.04847
- “Deep Program Reidentification: A Graph Neural Network Solution” https://arxiv.org/abs/1812.04064
- Heterogeneous Graph Neural Networks for Malicious Account Detection Z Liu, C Chen, X Yang, J Zhou, X Li, L Song Proceedings of the 27th ACM International Conference on Information and …
- L-Shapley and C-Shapley: Efficient model interpretation for structured data J Chen, L Song, MJ Wainwright, MI Jordan arXiv preprint arXiv:1808.02610
- Stochastic Training of Graph Convolutional Networks with Variance Reduction Authors: Jianfei Chen, Jun Zhu, Le Song
- A causal framework for explaining the predictions of black-box sequence-to-sequence models, EMNLP17
- Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs, Daniel Neil, Joss Briody, Alix Lacoste, Aaron Sim, Paidi Creed, Amir Saffari
- Interpretable Convolutional Neural Networks Quanshi Zhang, Ying Nian Wu, Song-Chun Zhu
- Towards Efficient Large-Scale Graph Neural Network Computing Lingxiao Ma, Zhi Yang, Youshan Miao, Jilong Xue, Ming Wu, Lidong Zhou, Yafei Dai
- Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
- DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices
- Squeezing deep learning into mobile and embedded devices, ND Lane, S Bhattacharya, A Mathur, P Georgiev, C Forlivesi, F Kawsar
- Towards Efficient Large-Scale Graph Neural Network Computing, Lingxiao Ma†∗, Zhi Yang†∗, Youshan Miao‡, Jilong Xue‡, Ming Wu‡, Lidong Zhou‡, Yafei Dai, https://arxiv.org/pdf/1810.08403.pdf
- Cavs: An Efficient Runtime System for Dynamic Neural Networks 1,2Shizhen Xu†, 1,3Hao Zhang†, 1,3Graham Neubig, 3Wei Dai, 1Jin Kyu Kim, 2Zhijie Deng, 3Qirong Ho, 2Guangwen Yang, 3Eric P. Xing
- A Comparison of Distributed Machine Learning Platforms (2017)
- GeePS: scalable deep learning on distributed GPUs with a GPU-specialized parameter server (2016)
- AMPNet: Asynchronous Model-Parallel Training for Dynamic Neural Networks (2017)
- GraphLab / GraphX / Pregel
- Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis
- Towards Efficient Large-Scale Graph Neural Network Computing (2018)
- The High-Dimensional Geometry of Binary Neural Networks Authors: Alexander G. Anderson, Cory P. Berg
- Learning Discrete Weights Using the Local Reparameterization Trick
- Sparsely-Connected Neural Networks: Towards Efficient VLSI Implementation of Deep Neural Networks
- Espresso: Efficient Forward Propagation for Binary Deep Neural Networks
- GkmExplain https://github.com/kundajelab/gkmexplain
Deep-Learning-Papers-Reading-Roadmap we read in Fall-2017
-
state-of-the-art-result-for-machine-learning-problems URL
Foundations
- DeepLearningSummerSchool17 + videolectures
- Andrew Ng - Nuts and Bolts of Applying Deep Learning : https://www.youtube.com/watch?v=F1ka6a13S9I :
- Ganguli - Theoretical Neuroscience and Deep Learning DLSS16 http://videolectures.net/deeplearning2016_ganguli_theoretical_neuroscience/
- Ganguli - Theoretical Neuroscience and Deep Learning.pdf DLSS17 https://drive.google.com/file/d/0B6NHiPcsmak1dkZMbzc2YWRuaGM/view
- Sharp Minima Can Generalize For Deep Nets, Laurent Dinh (Univ. Montreal), Razvan Pascanu, Samy Bengio (Google Brain), Yoshua Bengio (Univ. Montreal)
- Automated Curriculum Learning for Neural Networks, Alex Graves, Marc G. Bellemare, Jacob Menick, Koray Kavukcuoglu, Remi Munos
- Learning to learn without gradient descent by gradient descent, Yutian Chen, Matthew Hoffman, Sergio Gomez, Misha Denil, Timothy Lillicrap, Matthew Botvinick , Nando de Freitas
- Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study, Samuel Ritter, David Barrett, Adam Santoro, Matt Botvinick
- Geometry of Neural Network Loss Surfaces via Random Matrix Theory, Jeffrey Pennington, Yasaman Bahri
- On the Expressive Power of Deep Neural Networks, Maithra Raghu, Ben Poole, Surya Ganguli, Jon Kleinberg, Jascha Sohl-Dickstein
- Neuroscience-Inspired Artificial Intelligence, http://www.cell.com/neuron/fulltext/S0896-6273(17)30509-3
- Understanding deep learning requires rethinking generalization, ICLR17
- On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima, ICLR17
- Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes, ICLR17
- Capacity and Trainability in Recurrent Neural Networks, ICLR17
- Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations, ICLR17
- Frustratingly Short Attention Spans in Neural Language Modeling, ICLR17
- Topology and Geometry of Half-Rectified Network Optimization, ICLR17
- Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning, ICLR17
- Adversarial Feature Learning, ICLR17
- Do Deep Convolutional Nets Really Need to be Deep and Convolutional?, ICLR17
- Why Deep Neural Networks for Function Approximation?, ICLR17
- Bengio - Recurrent Neural Networks - DLSS 2017.pdf: https://drive.google.com/file/d/0ByUKRdiCDK7-LXZkM3hVSzFGTkE/view
- On the Expressive Power of Deep Neural Networks, Maithra Raghu, Ben Poole, Jon Kleinberg, Surya Ganguli, Jascha Sohl-Dickstein ; PMLR 70:2847-2854
- Equivariance Through Parameter-Sharing, Siamak Ravanbakhsh, Jeff Schneider, Barnabás Póczos ; PMLR 70:2892-2901
- Large-Scale Evolution of Image Classifiers, Esteban Real, Sherry Moore, Andrew Selle, Saurabh Saxena, Yutaka Leon Suematsu, Jie Tan, Quoc V. Le, Alexey Kurakin ; PMLR 70:2902-2911
- Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks, Itay Safran, Ohad Shamir ; PMLR 70:2979-2987
- A Closer Look at Memorization in Deep Networks, ICML17
- Dynamic Word Embeddings, ICML17
- Combining Low-Density Separators with CNNs, Yu-Xiong Wang*, Carnegie Mellon University; Martial Hebert, Carnegie Mellon University, NIPS16
- CNNpack: Packing Convolutional Neural Networks in the Frequency Domain, NIPS16
- Residual Networks are Exponential Ensembles of Relatively Shallow Networks, NIPS16
- Dense Associative Memory for Pattern Recognition, NIPS16
- Learning Kernels with Random Features, Aman Sinha*, Stanford University; John Duchi,
- Simple and Efficient Weighted Minwise Hashing, NIPS16
- Reward Augmented Maximum Likelihood for Neural Structured Prediction
- Unimodal Probability Distributions for Deep Ordinal Classification, ICML17
- End-to-End Learning for Structured Prediction Energy Networks, ICML17
- Orthogonal Random Features, NIPS16
- Learning Structured Sparsity in Deep Neural Networks, NIPS16
- Learning the Number of Neurons in Deep Networks, NIPS16
- Quantized Random Projections and Non-Linear Estimation of Cosine Similarity, NIPS16
- An equivalence between high dimensional Bayes optimal inference and M-estimation, NIPS16
- High Dimensional Structured Superposition Models, NIPS16
- Learning Deep Embeddings with Histogram Loss, NIPS16
- Learning values across many orders of magnitude, NIPS16
- Learning Deep Parsimonious Representations, NIPS16
- Efficient High-Order Interaction-Aware Feature Selection Based on Conditional Mutual Information, NIPS16
- A Bayesian method for reducing bias in neural representational similarity analysis, NIPS16
- Richards - Deep_Learning_in_the_Brain.pd https://drive.google.com/file/d/0B2A1tnmq5zQdcFNkWU1vdDJiT00/view and https://drive.google.com/file/d/0B2A1tnmq5zQdQWU0Skd6TVVQYUE/view?usp=drive_web
DNN with Varying Structures
- SCAN: Learning Abstract Hierarchical Compositional Visual Concepts, https://arxiv.org/pdf/1707.03389.pdf
- Krueger - Bayesian Hypernetworks.pdf https://drive.google.com/file/d/0B6NHiPcsmak1RUlucW1RN29oS3M/view?usp=drive_web
- Leblond and Alayrac - SeaRNN.pdf https://drive.google.com/file/d/0B6NHiPcsmak1SDVEaWc0OWtaV0k/view?usp=drive_web
- Sharir - Overlapping Architectures.pdf https://drive.google.com/file/d/0B6NHiPcsmak1ZzVkci1EdVN2YkU/view?usp=drive_web
- Ullrich - Bayesian Compression.pd https://drive.google.com/file/d/0B6NHiPcsmak1WlRUeHFpSW5OZGc/view?usp=drive_web
- Understanding Synthetic Gradients and Decoupled Neural Interfaces, Wojtek Czarnecki, Grzegorz Świrszcz, Max Jaderberg, Simon Osindero, Oriol Vinyals, Koray Kavukcuoglu, ICML17
- Video Pixel Networks, Nal Kalchbrenner, Aaron van den Oord, Karen Simonyan, Ivo Danihelka, Oriol Vinyals, Alex Graves, Koray Kavukcuoglu
- AdaNet: Adaptive Structural Learning of Artificial Neural Networks, Corinna Cortes, Xavi Gonzalvo, Vitaly Kuznetsov, Mehryar Mohri, Scott Yang
- Learning to Generate Long-term Future via Hierarchical Prediction, Ruben Villegas, Jimei Yang, Yuliang Zou, Sungryull Sohn, Xunyu Lin, Honglak Lee
- Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning, Junhyuk Oh, Satinder Singh, Honglak Lee, Pushmeet Kohli
- Latent LSTM Allocation: Joint Clustering and Non-Linear Dynamic Modeling of Sequence Data, Manzil Zaheer, Amr Ahmed, Alex Smola
- Large-Scale Evolution of Image Classifiers, Esteban Real, Sherry Moore, Andrew Selle, Saurabh Saxena, Yutaka Leon Suematsu, Jie Tan, Quoc Le, Alexey Kurakin
- Sequence Modeling via Segmentations, Chong Wang (Microsoft Research) · Yining Wang (CMU) · Po-Sen Huang (Microsoft Research) · Abdelrahman Mohammad (Microsoft) · Dengyong Zhou (Microsoft Research) · Li Deng (Citadel)
- ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices
- Adaptive Neural Networks for Fast Test-Time Prediction
- Making Neural Programming Architectures Generalize via Recursion, ICLR17
- Optimization as a Model for Few-Shot Learning, ICLR17
- Learning End-to-End Goal-Oriented Dialog, ICLR17
- Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer, ICLR17
- Nonparametric Neural Networks, ICLR17
- An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax, ICLR17
- Improving Neural Language Models with a Continuous Cache, ICLR17
- Variational Recurrent Adversarial Deep Domain Adaptation, ICLR17
- Soft Weight-Sharing for Neural Network Compression, ICLR17
- Tracking the World State with Recurrent Entity Networks, (Lecun), ICLR17
- Deep Biaffine Attention for Neural Dependency Parsing, ICLR17
- Learning to Remember Rare Events, ICLR17
- Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks, ICLR17
- Deep Learning with Dynamic Computation Graphs, ICLR17
- Query-Reduction Networks for Question Answering, ICLR17
- Bidirectional Attention Flow for Machine Comprehension, ICLR17
- Dynamic Coattention Networks For Question Answering, ICLR17
- Structured Attention Networks, ICLR17
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer, (Dean), ICLR17
- Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain, ICLR17
- Mollifying Networks, Bengio, ICLR17
- Automatic Rule Extraction from Long Short Term Memory Networks, ICLR17
- Loss-aware Binarization of Deep Networks, ICLR17
- Deep Multi-task Representation Learning: A Tensor Factorisation Approach, ICLR17
- Towards Deep Interpretability (MUS-ROVER II): Learning Hierarchical Representations of Tonal Music, ICLR17
- Reasoning with Memory Augmented Neural Networks for Language Comprehension, ICLR17
- Semi-Supervised Classification with Graph Convolutional Networks, ICLR17
- Hierarchical Multiscale Recurrent Neural Networks, ICLR17
- AdaNet: Adaptive Structural Learning of Artificial Neural Networks, ICML17
- Language Modeling with Gated Convolutional Networks, ICML17
- Image-to-Markup Generation with Coarse-to-Fine Attention, ICML17
- Input Switched Affine Networks: An RNN Architecture Designed for Interpretability, ICML17
- Differentiable Programs with Neural Libraries, ICML17
- Convolutional Sequence to Sequence Learning, ICML17
- State-Frequency Memory Recurrent Neural Networks, ICML17
- SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization, Juyong Kim, Yookoon Park, Gunhee Kim, Sung Ju Hwang ; PMLR 70:1866-1874
- Deriving Neural Architectures from Sequence and Graph Kernels Tao Lei, Wengong Jin, Regina Barzilay, Tommi Jaakkola ; PMLR 70:2024-2033
- Delta Networks for Optimized Recurrent Network Computation, Daniel Neil, Jun Haeng Lee, Tobi Delbruck, Shih-Chii Liu ; PMLR 70:2584-2593
- Recurrent Highway Networks, Julian Georg Zilly, Rupesh Kumar Srivastava, Jan Koutnı́k, Jürgen Schmidhuber ; PMLR 70:4189-4198
- Ask Me Anything: Dynamic Memory Networks for Natural Language Processing, ICML17
- OptNet: Differentiable Optimization as a Layer in Neural Networks, ICML17
- Swapout: Learning an ensemble of deep architectures, Saurabh Singh*, UIUC; Derek Hoiem, UIUC; David Forsyth, UIUC, NIPS16
- Natural-Parameter Networks: A Class of Probabilistic Neural Networks, Hao Wang*, HKUST; Xingjian Shi, ; Dit-Yan Yeung, NIPS16
- Learning What and Where to Draw, NIPS16
- Hierarchical Question-Image Co-Attention for Visual Question Answering, NIPS16
- Proximal Deep Structured Models, NIPS16
- Direct Feedback Alignment Provides Learning In Deep Neural Networks, NIPS16
- Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes, NIPS16
- Matching Networks for One Shot Learning, NIPS16
- Can Active Memory Replace Attention? Łukasz Kaiser*, ; Samy Bengio, NIPS16
- Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences, NIPS16
- Binarized Neural Networks, NIPS16
- Interaction Networks for Learning about Objects, Relations and Physics, NIPS16
- Optimal Architectures in a Solvable Model of Deep Networks, NIPS16
Reliable and Benchmarking and Applications
- Conditional Image Generation with Pixel CNN Decoders, NIPS16
- Dhruv - Visual Dialog - RLSS 2017 https://drive.google.com/file/d/0BzUSSMdMszk6RndSbkEzcnRFMGs/view and https://drive.google.com/file/d/0BzUSSMdMszk6cDVBMlRqLUs3TFk/view
- Input Switched Affine Networks: An RNN Architecture Designed for Interpretability, Jakob Foerster, Justin Gilmer, Jan Chorowski, Jascha Sohl-Dickstein, David Sussillo
- Axiomatic Attribution for Deep Networks, Ankur Taly, Qiqi Yan,,Mukund Sundararajan
- Differentiable Programs with Neural Libraries, Alex L Gaunt, Marc Brockschmidt, Nate Kushman, Daniel Tarlow
- Neural Optimizer Search with Reinforcement Learning, Irwan Bello, Barret Zoph, Vijay Vasudevan, Quoc Le
- Measuring Sample Quality with Kernels, Jackson Gorham (STANFORD) · Lester Mackey (Microsoft Research)
- Learning Continuous Semantic Representations of Symbolic Expressions, ICML17
- Recovery Guarantees for One-hidden-layer Neural Networks, ICML17
- On the State of the Art of Evaluation in Neural Language Models, https://arxiv.org/abs/1707.05589
- End-to-end Optimized Image Compression, ICLR17
- Multi-Agent Cooperation and the Emergence of (Natural) Language, ICLR17
- Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data, ICLR17
- Deep Learning with Differential Privacy,
- Privacy-Preserving Deep Learning, CCS15
- Learning to Query, Reason, and Answer Questions On Ambiguous Texts, ICLR17
- Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy, ICLR17
- Data Noising as Smoothing in Neural Network Language Models (Ng), ICLR17
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks, ICLR17
- Visualizing Deep Neural Network Decisions: Prediction Difference Analysis, ICLR17
- On Detecting Adversarial Perturbations, ICLR17
- Delving into Transferable Adversarial Examples and Black-box Attacks, ICLR17
- Parseval Networks: Improving Robustness to Adversarial Examples, ICML17
- iSurvive: An Interpretable, Event-time Prediction Model for mHealth, ICML17
- Being Robust (in High Dimensions) Can Be Practical, ICML17
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks, ICML17
- On Calibration of Modern Neural Networks, ICML17
- Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs, ICML17
- Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation, ICML17
- Analogical Inference for Multi-relational Embeddings, Hanxiao Liu, Yuexin Wu, Yiming Yang ; PMLR 70:2168-2178
- Deep Transfer Learning with Joint Adaptation Networks, Mingsheng Long, Han Zhu, Jianmin Wang, Michael I. Jordan ; PMLR 70:2208-2217
- Sequence to Better Sequence: Continuous Revision of Combinatorial Structures, Jonas Mueller, David Gifford, Tommi Jaakkola ; PMLR 70:2536-2544
- Meta Networks, Tsendsuren Munkhdalai, Hong Yu ; PMLR 70:2554-2563
- Geometry of Neural Network Loss Surfaces via Random Matrix Theory, Jeffrey Pennington, Yasaman Bahri ; PMLR 70:2798-2806
- Asymmetric Tri-training for Unsupervised Domain Adaptation, Kuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada ; PMLR 70:2988-2997
- Developing Bug-Free Machine Learning Systems With Formal Mathematics, Daniel Selsam, Percy Liang, David L. Dill ; PMLR 70:3047-3056
- Learning Important Features Through Propagating Activation Differences, Avanti Shrikumar, Peyton Greenside, Anshul Kundaje ; PMLR 70:3145-3153
- High-Dimensional Structured Quantile Regression, ICML17
- Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs, Rakshit Trivedi, Hanjun Dai, Yichen Wang, Le Song ; PMLR 70:3462-3471
- Learning to Generate Long-term Future via Hierarchical Prediction, Ruben Villegas, Jimei Yang, Yuliang Zou, Sungryull Sohn, Xunyu Lin, Honglak Lee ; PMLR 70:3560-3569
- Sequence Modeling via Segmentations, Chong Wang, Yining Wang, Po-Sen Huang, Abdelrahman Mohamed, Dengyong Zhou, Li Deng ; PMLR 70:3674-3683
- A Unified View of Multi-Label Performance Measures, Xi-Zhu Wu, Zhi-Hua Zhou ; PMLR 70:3780-3788
- Convexified Convolutional Neural Networks, Yuchen Zhang, Percy Liang, Martin J. Wainwright ; PMLR 70:4044-4053
- Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin, ICML17
- Learning Transferrable Representations for Unsupervised Domain Adaptation, NIPS16
- Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity, NIPS16
- Unsupervised Domain Adaptation with Residual Transfer Networks, Mingsheng Long*, Tsinghua University; Han Zhu, Tsinghua University; Jianmin Wang, Tsinghua University; Michael Jordan, NIPS16
- Interpretable Distribution Features with Maximum Testing Power, Wittawat Jitkrittum*, Gatsby Unit, UCL; Zoltan Szabo, ; Kacper Chwialkowski, Gatsby Unit, UCL; Arthur Gretton, NIPS16
- Domain Separation Networks, NIPS16
- Multimodal Residual Learning for Visual QA, NIPS16
- Learning feed-forward one-shot learners, NIPS16
- Adversarial Multiclass Classification: A Risk Minimization Perspective, NIPS16
- Generating Images with Perceptual Similarity Metrics based on Deep Networks, NIPS16
- Dialog-based Language Learning, Jason Weston*, NIPS16
- The Robustness of Estimator Composition, NIPS16
- Large Margin Discriminant Dimensionality Reduction in Prediction Space, NIPS16
- Robustness of classifiers: from adversarial to random noise, NIPS16
- Examples are not Enough, Learn to Criticize! Model Criticism for Interpretable Machine Learning, NIPS16
- Blind Attacks on Machine Learners, Alex Beatson*, Princeton University; Zhaoran Wang, Princeton University; Han Liu, NIPS16
- Composing graphical models with neural networks for structured representations and fast inference, NIPS16
- Spatiotemporal Residual Networks for Video Action Recognition, NIPS16
- Learning Important Features Through Propagating Activation Differences, ICML17
Optimization
- Johnson - Automatic Differentiation.p https://drive.google.com/file/d/0B6NHiPcsmak1ckYxR2hmRGdzdFk/view
- Osborne - Probabilistic numerics for deep learning - DLSS 2017.pdf https://drive.google.com/file/d/0B2A1tnmq5zQdWHBYOFctNi1KdVU/view
- Learned Optimizers that Scale and Generalize, Olga Wichrowska, Niru Maheswaranathan, Matthew Hoffman, Sergio Gomez, Misha Denil, Nando de Freitas, Jascha Sohl-Dickstein
- Learning to learn by gradient descent by gradient descent
- Asynchronous Stochastic Gradient Descent with Delay Compensation,
- How to Escape Saddle Points Efficiently, Chi Jin (UC Berkeley) · Rong Ge (Duke University) · Praneeth Netrapalli (Microsoft Research) · Sham M. Kakade (University of Washington) · Michael Jordan (UC Berkeley)
- Natasha: Faster Non-Convex Stochastic Optimization Via Strongly Non-Convex Parameter
- Batched High-dimensional Bayesian Optimization via Structural Kernel Learning
- Towards Principled Methods for Training Generative Adversarial Networks, ICLR17
- Optimization as a Model for Few-Shot Learning, ICLR17
- Amortised MAP Inference for Image Super-resolution, ICLR17
- Neural Architecture Search with Reinforcement Learning, ICLR17
- Distributed Second-Order Optimization using Kronecker-Factored Approximations, ICLR17
- Mode Regularized Generative Adversarial Networks, ICLR17
- Highway and Residual Networks learn Unrolled Iterative Estimation, ICLR17
- Snapshot Ensembles: Train 1, Get M for Free, ICLR17
- Learning to Optimize, ICLR17
- Recurrent Batch Normalization, ICLR17
- Adversarially Learned Inference, ICLR17
- Reasoning with Memory Augmented Neural Networks for Language Comprehension, ICLR17
- Deep ADMM-Net for Compressive Sensing MRI, NIPS16
- Sharp Minima Can Generalize For Deep Nets, ICML17
- Forward and Reverse Gradient-Based Hyperparameter Optimization, ICML17
- Automated Curriculum Learning for Neural Networks, ICML17
- How to Escape Saddle Points Efficiently, ICML17
- Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs, ICML17
- An overview of gradient optimization algorithms, (https://arxiv.org/abs/1609.04747)
- Learning Deep Architectures via Generalized Whitened Neural Networks, Ping Luo ; PMLR 70:2238-2246
- The Loss Surface of Deep and Wide Neural Networks, Quynh Nguyen, Matthias Hein ; PMLR 70:2603-2612
- Relative Fisher Information and Natural Gradient for Learning Large Modular Models, Ke Sun, Frank Nielsen ; PMLR 70:3289-3298
- meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting, Xu Sun, Xuancheng Ren, Shuming Ma, Houfeng Wang ; PMLR 70:3299-3308
- Axiomatic Attribution for Deep Networks, Mukund Sundararajan, Ankur Taly, Qiqi Yan ; PMLR 70:3319-3328
- Follow the Moving Leader in Deep Learning, Shuai Zheng, James T. Kwok ; PMLR 70:4110-4119
- Oracle Complexity of Second-Order Methods for Finite-Sum Problems, ICML17
- The Shattered Gradients Problem: If resnets are the answer, then what is the question?, ICML17
- Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks, ICML17
- End-to-End Differentiable Adversarial Imitation Learning, ICML17
- Neural Optimizer Search with Reinforcement Learning, ICML17
- Adaptive Neural Networks for Efficient Inference, ICML17
- Practical Gauss-Newton Optimisation for Deep Learning, ICML17
- Deep Tensor Convolution on Multicores, ICML17
- The Generalized Reparameterization Gradient, Francisco Ruiz*, Columbia University; Michalis K. Titsias, ; David Blei, NIPS16
- Attend, Infer, Repeat: Fast Scene Understanding with Generative Models, NIPS16
- Memory-Efficient Backpropagation Through Time, NIPS16
- Professor Forcing: A New Algorithm for Training Recurrent Networks, NIPS16
- Understanding the Effective Receptive Field in Deep Convolutional Neural Networks, NIPS16
Generative
- GAN tutorial by Ian Goodfellow (NIPS 2016): https://arxiv.org/abs/1701.00160 https://www.youtube.com/watch?v=AJVyzd0rqdc
- Goodfellow - Generative Models I - DLSS 2017 https://drive.google.com/file/d/0ByUKRdiCDK7-bTgxTGoxYjQ4NW8/view
- Courville - Generative Models II - DLSS 2017. https://drive.google.com/file/d/0B_wzP_JlVFcKQ21udGpTSkh0aVk/view
- Makhzani and Frey - PixelGAN Autoencoders.pdf https://drive.google.com/file/d/0B6NHiPcsmak1SFdRN2lmS3FnekE/view
- Welling - Graphical Models and Deep Learning.pd https://drive.google.com/file/d/0B6NHiPcsmak1NHJHdzEySzNNQ0U/view
- Parallel Multiscale Autoregressive Density Estimation, Scott Reed, Aäron van den Oord, Nal Kalchbrenner, Ziyu Wang, Dan Belov, Nando de Freitas
- Count-Based Exploration with Neural Density Models, Georg Ostrovski, Marc Bellemare, Aaron van den Oord, Remi Munos
- Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo, Maithra Raghu, Ben Poole, Surya Ganguli, Jon Kleinberg, Jascha Sohl-Dickstein
- Johnson - Graphical Models and Deep Learning https://drive.google.com/file/d/0B6NHiPcsmak1RmZ3bmtFWUd5bjA/view?usp=drive_web
- Variational Boosting: Iteratively Refining Posterior Approximations, Andrew Miller, Nicholas J Foti, Ryan Adams
- Stochastic Generative Hashing, Bo Dai, Ruiqi Guo, Sanjiv Kumar, Niao He, Le Song, ICML17
- Robust Structured Estimation with Single-Index Models, ICML17
- Learning to Act by Predicting the Future, ICLR17
- Improving Generative Adversarial Networks with Denoising Feature Matching, ICLR17
- Boosted Generative Models, ICLR17
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables, ICLR17
- Robust Probabilistic Modeling with Bayesian Data Reweighting, ICML17
- Deep Generative Models for Relational Data with Side Information, ICML17
- Learning to Discover Cross-Domain Relations with Generative Adversarial Networks Taeksoo Kim, Moonsu Cha, Hyunsoo Kim, Jung Kwon Lee, Jiwon Kim ; PMLR 70:1857-1865
- Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks, Lars Mescheder, Sebastian Nowozin, Andreas Geiger ; PMLR 70:2391-2400
- McGan: Mean and Covariance Feature Matching GAN, Youssef Mroueh, Tom Sercu, Vaibhava Goel ; PMLR 70:2527-2535
- Parallel Multiscale Autoregressive Density Estimation, Scott Reed, Aäron Oord, Nal Kalchbrenner, Sergio Gómez Colmenarejo, Ziyu Wang, Yutian Chen, Dan Belov, Nando Freitas ; PMLR 70:2912-2921
- Adversarial Feature Matching for Text Generation, Yizhe Zhang, Zhe Gan, Kai Fan, Zhi Chen, Ricardo Henao, Dinghan Shen, Lawrence Carin ; PMLR 70:4006-4015
- Learning Hierarchical Features from Deep Generative Models, Shengjia Zhao, Jiaming Song, Stefano Ermon ; PMLR 70:4091-4099
- Wasserstein Generative Adversarial Networks, ICML17
- Generalization and Equilibrium in Generative Adversarial Nets (GANs), ICML17
- Exponential Family Embeddings, NIPS16
- Wasserstein GAN, ICML17
Reinforcement
- Hasselt - Deep Reinforcement Learning - RLSS 2017.pdf https://drive.google.com/file/d/0BzUSSMdMszk6UE5TbWdZekFXSE0/view?usp=drive_web
- Pineau - RL Basic Concepts - RLSS 2017.pdf https://drive.google.com/file/d/0BzUSSMdMszk6bjl3eU5CVmU0cWs/view http://videolectures.net/deeplearning2016_pineau_reinforcement_learning/ and http://videolectures.net/deeplearning2016_pineau_advanced_topics/
- Roux - RL in the Industry - RLSS 2017.pdf https://drive.google.com/file/d/0BzUSSMdMszk6bEprTUpCaHRrQ28/view
- Singh - Steps Towards Continual Learning.pdf https://drive.google.com/file/d/0BzUSSMdMszk6YVhFUUNLZnZLSWs/view?usp=drive_web
- Sutton - Temporal-Difference Learning- RLSS 2017.pd https://drive.google.com/file/d/0BzUSSMdMszk6VE9kMkY2SzQzSW8/view?usp=drive_web
- Szepesvari - Theory of RL - RLSS 2017.pdf https://drive.google.com/file/d/0BzUSSMdMszk6U194Ym5jSnZQbGM/view?usp=drive_web
- Thomas - Safe Reinforcement Learning - RLSS 2017.pdf https://drive.google.com/file/d/0BzUSSMdMszk6TDRMRGRaM0dBcHM/view?usp=drive_web
- Minimax Regret Bounds for Reinforcement Learning, Mohammad Gheshlaghi Azar, Ian Osband, Remi Munos
- Why is Posterior Sampling Better than Optimism for Reinforcement Learning? Ian Osband, Benjamin Van Roy
- DARLA: Improving Zero-Shot Transfer in Reinforcement Learning, Irina Higgins, Arka Pal, Andrei Rusu, Loic Matthey, Chris Burgess, Alexander Pritzel, Matt Botvinick, Charles Blundell, Alexander Lerchner
- A Distributional Perspective on Reinforcement Learning, Marc G. Bellemare, Will Dabney, Remi Munos
- A Laplacian Framework for Option Discovery in Reinforcement Learning, Marlos Machado (Univ. Alberta), Marc G. Bellemare, Michael Bowling
- The Predictron: End-to-End Learning and Planning, David Silver, Hado van Hasselt, Matteo Hessel, Tom Schaul, Arthur Guez, Tim Harley, Gabriel Dulac-Arnold, David Reichert, Neil Rabinowitz, Andre Barreto, Thomas Degris
- FeUdal Networks for Hierarchical Reinforcement Learning, Sasha Vezhnevets, Simon Osindero, Tom Schaul, Nicolas Hees, Max Jaderberg, David Silver, Koray Kavukcuoglu
- Neural Episodic Control, Alex Pritzel, Benigno Uria, Sriram Srinivasan, Adria Puigdomenech, Oriol Vinyals, Demis Hassabis, Daan Wierstra, Charles Blundell
- Robust Adversarial Reinforcement Learning, Lerrel Pinto, James Davidson, Rahul Sukthankar, Abhinav Gupta
- Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs, Michael Gygli, Mohammad Norouzi, Anelia Angelova
- Distral: Robust Multitask Reinforcement Learning, https://arxiv.org/pdf/1707.04175.pdf
- Reinforcement Learning with Unsupervised Auxiliary Tasks, ICLR17
- Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic, ICLR17
- DARLA: Improving Zero-Shot Transfer in Reinforcement Learning, ICML17
- Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning, Junhyuk Oh, Satinder Singh, Honglak Lee, Pushmeet Kohli ; PMLR 70:2661-2670
- Count-Based Exploration with Neural Density Models, Georg Ostrovski, Marc G. Bellemare, Aäron Oord, Rémi Munos ; PMLR 70:2721-2730
- Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction, Wen Sun, Arun Venkatraman, Geoffrey J. Gordon, Byron Boots, J. Andrew Bagnell ; PMLR 70:3309-3318
More:
- ICLR 2017 Papers
- ICML 2017 Papers
- NIPS 2017 papers
- Yann Lecun
- Y. Bengio
- G. Hinton
- Juergen Schmidhuber