610 citations · 1.2k across the 24 of their papers we have counts for
18 papers · 1 filter
Sample Efficient Deep Reinforcement Learning via Local Planning
Dong Yin, Sridhar Thiagarajan, Nevena Lazic +3
The focus of this work is sample-efficient deep reinforcement learning (RL) with a simulator. One useful property of simulators is that it is typically easy to reset the environmen…
Architecture Matters in Continual Learning
Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin +4
A large body of research in continual learning is devoted to overcoming the catastrophic forgetting of neural networks by designing new algorithms that are robust to the distributi…
Wide Neural Networks Forget Less Catastrophically
Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin +4
A primary focus area in continual learning research is alleviating the "catastrophic forgetting" problem in neural networks by designing new algorithms that are more robust to the…
Efficient Local Planning with Linear Function Approximation
Dong Yin, Botao Hao, Yasin Abbasi-Yadkori +2
We study query and computationally efficient planning algorithms with linear function approximation and a simulator. We assume that the agent only has local access to the simulator…
An Instance-Dependent Simulation Framework for Learning with Label Noise
Keren Gu, Xander Masotto, Vandana Bachani +3
We propose a simulation framework for generating instance-dependent noisy labels via a pseudo-labeling paradigm. We show that the distribution of the synthetic noisy labels generat…
Improved Regret Bound and Experience Replay in Regularized Policy Iteration
Nevena Lazic, Dong Yin, Yasin Abbasi-Yadkori +1
In this work, we study algorithms for learning in infinite-horizon undiscounted Markov decision processes (MDPs) with function approximation. We first show that the regret analysis…
The Effectiveness of Memory Replay in Large Scale Continual Learning
Yogesh Balaji, Mehrdad Farajtabar, Dong Yin +2
We study continual learning in the large scale setting where tasks in the input sequence are not limited to classification, and the outputs can be of high dimension. Among multiple…
A maximum-entropy approach to off-policy evaluation in average-reward MDPs
Nevena Lazic, Dong Yin, Mehrdad Farajtabar +4
This work focuses on off-policy evaluation (OPE) with function approximation in infinite-horizon undiscounted Markov decision processes (MDPs). For MDPs that are ergodic and linear…
Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint
Dong Yin, Mehrdad Farajtabar, Ang Li +2
Neural networks have achieved remarkable success in many cognitive tasks. However, when they are trained sequentially on multiple tasks without access to old data, their performanc…
Stochastic Gradient and Langevin Processes
Xiang Cheng, Dong Yin, Peter L. Bartlett +1
We prove quantitative convergence rates at which discrete Langevin-like processes converge to the invariant distribution of a related stochastic differential equation. We study the…
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation
Raphael Gontijo Lopes, Dong Yin, Ben Poole +2
Deploying machine learning systems in the real world requires both high accuracy on clean data and robustness to naturally occurring corruptions. While architectural advances have…
A Fourier Perspective on Model Robustness in Computer Vision
Dong Yin, Raphael Gontijo Lopes, Jonathon Shlens +2
Achieving robustness to distributional shift is a longstanding and challenging goal of computer vision. Data augmentation is a commonly used approach for improving robustness, howe…
Robust Federated Learning in a Heterogeneous Environment
Avishek Ghosh, Justin Hong, Dong Yin +1
We study a recently proposed large-scale distributed learning paradigm, namely Federated Learning, where the worker machines are end users' own devices. Statistical and computation…
Rademacher Complexity for Adversarially Robust Generalization
Dong Yin, Kannan Ramchandran, Peter Bartlett
Many machine learning models are vulnerable to adversarial attacks; for example, adding adversarial perturbations that are imperceptible to humans can often make machine learning m…
Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning
Dong Yin, Yudong Chen, Kannan Ramchandran +1
We study robust distributed learning that involves minimizing a non-convex loss function with saddle points. We consider the Byzantine setting where some worker machines have abnor…
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Dong Yin, Yudong Chen, Kannan Ramchandran +1
In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or…
Online Learning for Non-Stationary A/B Tests
Andrés Muñoz Medina, Sergei Vassilvitskii, Dong Yin
The rollout of new versions of a feature in modern applications is a manual multi-stage process, as the feature is released to ever larger groups of users, while its performance is…
Gradient Diversity: a Key Ingredient for Scalable Distributed Learning
Dong Yin, Ashwin Pananjady, Max Lam +3
It has been experimentally observed that distributed implementations of mini-batch stochastic gradient descent (SGD) algorithms exhibit speedup saturation and decaying generalizati…