184 citations · 931 across the 54 of their papers we have counts for
43 papers · 1 filter
PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback
Souradip Chakraborty, Amrit Singh Bedi, Alec Koppel +4
We present a novel unified bilevel optimization-based framework, \textsf{PARL}, formulated to address the recently highlighted critical issue of policy alignment in reinforcement l…
TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
Ruijie Zheng, Xiyao Wang, Yanchao Sun +5
Despite recent progress in reinforcement learning (RL) from raw pixel data, sample inefficiency continues to present a substantial obstacle. Prior works have attempted to address t…
GFairHint: Improving Individual Fairness for Graph Neural Networks via Fairness Hint
Paiheng Xu, Yuhang Zhou, Bang An +2
Given the growing concerns about fairness in machine learning and the impressive performance of Graph Neural Networks (GNNs) on graph data learning, algorithmic fairness in GNNs ha…
Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function
Ruijie Zheng, Xiyao Wang, Huazhe Xu +1
Probabilistic dynamics model ensemble is widely used in existing model-based reinforcement learning methods as it outperforms a single dynamics model in both asymptotic performance…
Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness
Yuancheng Xu, Yanchao Sun, Micah Goldblum +2
The robustness of a deep classifier can be characterized by its margins: the decision boundary's distances to natural data points. However, it is unclear whether existing robust tr…
SMART: Self-supervised Multi-task pretrAining with contRol Transformers
Yanchao Sun, Shuang Ma, Ratnesh Madaan +3
Self-supervised pretraining has been extensively studied in language and vision domains, where a unified model can be easily adapted to various downstream tasks by pretraining repr…
STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning
Souradip Chakraborty, Amrit Singh Bedi, Alec Koppel +3
Directed Exploration is a crucial challenge in reinforcement learning (RL), especially when rewards are sparse. Information-directed sampling (IDS), which optimizes the information…
Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
Yongyuan Liang, Yanchao Sun, Ruijie Zheng +1
Recent studies reveal that a well-trained deep reinforcement learning (RL) policy can be particularly vulnerable to adversarial perturbations on input observations. Therefore, it i…
Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems
Yanchao Sun, Ruijie Zheng, Parisa Hassanzadeh +4
Communication is important in many multi-agent reinforcement learning (MARL) problems for agents to share information and make good decisions. However, when deploying trained commu…
Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy
Xiyao Wang, Wichayaporn Wongkamjan, Furong Huang
Model-based reinforcement learning (RL) often achieves higher sample efficiency in practice than model-free RL by learning a dynamics model to generate samples for policy learning.…
Transferring Fairness under Distribution Shifts via Fair Consistency Regularization
Bang An, Zora Che, Mucong Ding +1
The increasing reliance on ML models in high-stakes tasks has raised a major concern on fairness violations. Although there has been a surge of work that improves algorithmic fairn…
FedBC: Calibrating Global and Local Models via Federated Learning Beyond Consensus
Amrit Singh Bedi, Chen Fan, Alec Koppel +4
In this work, we quantitatively calibrate the performance of global and local models in federated learning through a multi-criterion optimization-based framework, which we cast as…
Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning
Souradip Chakraborty, Amrit Singh Bedi, Alec Koppel +4
Model-based approaches to reinforcement learning (MBRL) exhibit favorable performance in practice, but their theoretical guarantees in large spaces are mostly restricted to the set…
End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking
Arpit Bansal, Avi Schwarzschild, Eitan Borgnia +4
Machine learning systems perform well on pattern matching tasks, but their ability to perform algorithmic or logical reasoning is not well understood. One important reasoning capab…
Transfer RL across Observation Feature Spaces via Model-Based Regularization
Yanchao Sun, Ruijie Zheng, Xiyao Wang +2
In many reinforcement learning (RL) applications, the observation space is specified by human developers and restricted by physical realizations, and may thus be subject to dramati…
Understanding the Generalization Benefit of Model Invariance from a Data Perspective
Sicheng Zhu, Bang An, Furong Huang
Machine learning models that are developed with invariance to certain types of data transformations have demonstrated superior generalization performance in practice. However, the…
VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization
Mucong Ding, Kezhi Kong, Jingling Li +4
Most state-of-the-art Graph Neural Networks (GNNs) can be defined as a form of graph convolution which can be realized by message passing between direct neighbors or beyond. To sca…
Comfetch: Federated Learning of Large Networks on Constrained Clients via Sketching
Tahseen Rabbani, Brandon Feng, Marco Bornstein +5
Federated learning (FL) is a popular paradigm for private and collaborative model training on the edge. In centralized FL, the parameters of a global architecture (such as a deep n…
Practical and Fast Momentum-Based Power Methods
Tahseen Rabbani, Apollo Jain, Arjun Rajkumar +1
The power method is a classical algorithm with broad applications in machine learning tasks, including streaming PCA, spectral clustering, and low-rank matrix approximation. The di…
Certified Defense via Latent Space Randomized Smoothing with Orthogonal Encoders
Huimin Zeng, Jiahao Su, Furong Huang
Randomized Smoothing (RS), being one of few provable defenses, has been showing great effectiveness and scalability in terms of defending against -norm adversarial perturba…
Scaling-up Diverse Orthogonal Convolutional Networks with a Paraunitary Framework
Jiahao Su, Wonmin Byeon, Furong Huang
Enforcing orthogonality in neural networks is an antidote for gradient vanishing/exploding problems, sensitivity by adversarial perturbation, and bounding generalization errors. Ho…
Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL
Yanchao Sun, Ruijie Zheng, Yongyuan Liang +1
Evaluating the worst-case performance of a reinforcement learning (RL) agent under the strongest/optimal adversarial perturbations on state observations (within some constraints) i…
Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks
Avi Schwarzschild, Eitan Borgnia, Arjun Gupta +4
Deep neural networks are powerful machines for visual pattern recognition, but reasoning tasks that are easy for humans may still be difficult for neural models. Humans possess the…
DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations
Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova +6
Data poisoning and backdoor attacks manipulate training data to induce security breaches in a victim model. These attacks can be provably deflected using differentially private (DP…