29 citations · 75 across the 35 of their papers we have counts for
12 papers · 1 filter
Polyhedral Instability Governs Regret in Online Learning
Yuetai Li, Fengqing Jiang, Yichen Feng +6
Many online decision problems over combinatorial actions are addressed via convex relaxations, leading to online convex optimization with piecewise linear objectives and induced po…
The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks
Fengqing Jiang, Yuetai Li, Yichen Feng +6
Hypergraphs provide a natural framework to model higher-order interactions in scientific, social, and biological systems. Hypergraph neural networks (HGNNs) aim to learn from such…
TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
Zhangchen Xu, Yuetai Li, Fengqing Jiang +4
Reinforcement Learning (RL) has become a powerful tool for enhancing the reasoning abilities of large language models (LLMs) by optimizing their policies with reward signals. Yet,…
SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
Fengqing Jiang, Fengbo Ma, Zhangchen Xu +8
Large language models (LLMs) exhibit advancing capabilities in complex tasks, such as reasoning and graduate-level question answering, yet their resilience against misuse, particul…
A Method for Fast Autonomy Transfer in Reinforcement Learning
Dinuka Sahabandu, Bhaskar Ramasubramanian, Michail Alexiou +3
This paper introduces a novel reinforcement learning (RL) strategy designed to facilitate rapid autonomy transfer by utilizing pre-trained critic value functions from multiple envi…
Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization
Arezoo Rajabi, Reeya Pimple, Aiswarya Janardhanan +3
Transfer learning (TL) has been demonstrated to improve DNN model performance when faced with a scarcity of training samples. However, the suitability of TL as a solution to reduce…
LDL: A Defense for Label-Based Membership Inference Attacks
Arezoo Rajabi, Dinuka Sahabandu, Luyao Niu +2
The data used to train deep neural network (DNN) models in applications such as healthcare and finance typically contain sensitive information. A DNN model may suffer from overfitt…
Game of Trojans: A Submodular Byzantine Approach
Dinuka Sahabandu, Arezoo Rajabi, Luyao Niu +3
Machine learning models in the wild have been shown to be vulnerable to Trojan attacks during training. Although many detection mechanisms have been proposed, strong adaptive attac…
Privacy-Preserving Reinforcement Learning Beyond Expectation
Arezoo Rajabi, Bhaskar Ramasubramanian, Abdullah Al Maruf +1
Cyber and cyber-physical systems equipped with machine learning algorithms such as autonomous cars share environments with humans. In such a setting, it is important to align syste…
Reinforcement Learning Beyond Expectation
Bhaskar Ramasubramanian, Luyao Niu, Andrew Clark +1
The inputs and preferences of human users are important considerations in situations where these users interact with autonomous cyber or cyber-physical systems. In these scenarios,…
Shaping Advice in Deep Multi-Agent Reinforcement Learning
Baicen Xiao, Bhaskar Ramasubramanian, Radha Poovendran
Multi-agent reinforcement learning involves multiple agents interacting with each other and a shared environment to complete tasks. When rewards provided by the environment are spa…
Potential-Based Advice for Stochastic Policy Learning
Baicen Xiao, Bhaskar Ramasubramanian, Andrew Clark +3
This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show…