|
Publications
* alphabetical order or equal contributions
Preprints
Sample Efficient Deep Reinforcement Learning via Local Planning
Dong Yin*, Sridhar Thiagarajan*, Nevena Lazic*, Nived Rajaraman, Botao Hao, Csaba Szepesvari
Journal and Conference Papers
Wide Neural Networks Forget Less Catastrophically
Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Huiyi Hu, Razvan Pascanu, Dilan Gorur, Mehrdad Farajtabar
International Conference on Machine Learning (ICML), 2022.
Efficient Local Planning with Linear Function Approximation
Dong Yin, Botao Hao, Yasin Abbasi-Yadkori, Nevena Lazic, Csaba Szepesvari
International Conference on Algorithmic Learning Theory (ALT), 2022.
Confident Least Square Value Iteration with Local Access to a Simulator
Botao Hao, Nevena Lazic, Dong Yin, Yasin Abbasi-Yadkori, Csaba Szepesvari
International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
An Instance-Dependent Simulation Framework for Learning with Label Noise
Keren Gu, Xander Masotto, Vandana Bachani, Balaji Lakshminarayanan, Jack Nikodem, Dong Yin
Machine Learning Journal, June 2022.
An Efficient Framework for Clustered Federated Learning
Avishek Ghosh*, Jichan Chung*, Dong Yin*, Kannan Ramchandran
IEEE Transactions on Information Theory, December 2022.
Conference version at Neural Information Processing Systems (NeurIPS), 2020.
Preliminary version at ICML Workshop on Federated Learning for User Privacy and Data Confidentiality, 2020.
Improved Regret Bound and Experience Replay in Regularized Policy Iteration
Nevena Lazic, Dong Yin, Yasin Abbasi-Yadkori, Csaba Szepesvari
International Conference on Machine Learning (ICML), 2021 (long talk).
A Maximum-Entropy Approach to Off-Policy Evaluation in Average-Reward MDPs
Nevena Lazic, Dong Yin, Mehrdad Farajtabar, Nir Levine, Dilan Gorur, Chris Harris, Dale Schuurmans
Annual Conference on Neural Information Processing Systems (NeurIPS), 2020.
Stochastic Gradient and Langevin Processes
Xiang Cheng, Dong Yin, Peter Bartlett, Michael Jordan
International Conference on Machine Learning (ICML), 2020.
A Fourier Perspective on Model Robustness in Computer Vision
Dong Yin, Raphael Gontijo Lopes, Jonathon Shlens, Ekin D. Cubuk, Justin Gilmer
Annual Conference on Neural Information Processing Systems (NeurIPS), 2019.
Shorter version at ICML Workshop on Uncertainty and Robustness in Deep Learning, 2019.
Rademacher Complexity for Adversarially Robust Generalization
Dong Yin, Kannan Ramchandran, Peter Bartlett
International Conference on Machine Learning (ICML), 2019.
Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning
Dong Yin, Yudong Chen, Kannan Ramchandran, Peter Bartlett
International Conference on Machine Learning (ICML), 2019 (long talk).
Shorter version at ICML Nonconvex Optimization Workshop, 2018.
Online Learning for Non-Stationary A/B Tests
Andres Munoz Medina*, Sergei Vassilvitskii*, Dong Yin*
ACM International Conference on Information and Knowledge Management (CIKM), 2018.
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Dong Yin, Yudong Chen, Kannan Ramchandran, Peter Bartlett
International Conference on Machine Learning (ICML), 2018 (long talk).
Gradient Diversity: a Key Ingredient for Scalable Distributed Learning
Dong Yin, Ashwin Pananjady, Max Lam, Dimitris Papailiopoulos, Kannan Ramchandran, Peter Bartlett
International Conference on Artificial Intelligence and Statistics (AISTATS), 2018.
Shorter version at NIPS Optimization Workshop, 2017 (oral presentation).
Workshop Papers
Architecture Matters in Continual Learning
Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Timothy Nguyen, Razvan Pascanu, Dilan Gorur, Mehrdad Farajtabar
Technical report.
Importance of Representation Learning for Off-Policy Fitted Q-Evaluation
Xian Wu, Nevena Lazic, Dong Yin, Cosmin Paduraru
NeurIPS Offline Reinforcement Learning Workshop, 2021.
Revisiting Memory Replay For Large Scale Continual Learning
Yogesh Balaji, Mehrdad Farajtabar, Dong Yin, Alex Mott, Ang Li
Workshop on Continual Learning in Computer Vision, 2021. arXiv
Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint
Dong Yin, Mehrdad Farajtabar, Ang Li, Nir Levine, Alex Mott
Preliminary version with a different title presented at ICML Workshop on Continual Learning, 2020 (spotlight).
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation
Raphael Gontijo Lopes, Dong Yin, Ben Poole, Justin Gilmer, Ekin D. Cubuk
ICML Workshop on Uncertainty and Robustness in Deep Learning, 2019.
Robust Federated Learning in a Heterogeneous Environment
Avishek Ghosh, Justin Hong, Dong Yin, Kannan Ramchandran
ICML Workshop on Security and Privacy of Machine Learning, 2019.
Earlier Papers
Sub-linear Time Support Recovery for Compressed Sensing using Sparse-Graph Codes
Xiao Li, Dong Yin, Sameer Pawar, Ramtin Pedarsani, Kannan Ramchandran
IEEE Transactions on Information Theory, October 2019.
Learning Mixtures of Sparse Linear Regressions Using Sparse Graph Codes
Dong Yin, Ramtin Pedarsani, Yudong Chen, Kannan Ramchandran
IEEE Transactions on Information Theory, March 2019.
Shorter version at IEEE Allerton Conference on Communication, Control, and Computing, 2017.
PhaseCode: Fast and Efficient Compressive Phase Retrieval based on Sparse-Graph Codes
Ramtin Pedarsani, Dong Yin, Kangwook Lee, Kannan Ramchandran
IEEE Transactions on Information Theory, April 2017.
Distributed Sequence Memory of Multidimensional Inputs in Recurrent Networks
Adam S. Charles, Dong Yin, Christopher J. Rozell
Journal of Machine Learning Research (JMLR), Janurary 2017.
Compressed Sensing Using Sparse-Graph Codes for the Continuous-Alphabet Setting
Dong Yin, Ramtin Pedarsani, Xiao Li, Kannan Ramchandran
IEEE Allerton Conference on Communication, Control, and Computing, 2016.
Fast and Robust Compressive Phase Retrieval with Sparse-graph Codes
Dong Yin, Kangwook Lee, Ramtin Pedarsani, Kannan Ramchandran
IEEE International Symposium on Information Theory (ISIT), 2015.
Can Random Linear Networks Store Multiple Long Input Streams?
Adam S. Charles, Dong Yin, Christopher J. Rozell
IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2014.
Sparse Constraint Affine Projection Algorithm with Parallel Implementation and Application in Compressive Sensing
Dong Yin, Hing Cheung So, Yuantao Gu
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014.
|