Session: Robust Machine Learning
Chair: Zhengyuan Zhou
Cluster: Optimization For Data Science
Talk 1: Robust Reinforcement Learning from Corrupted Human Feedback
Speaker: Zixuan Zhang
Abstract: Reinforcement learning from human feedback (RLHF) provides a principled framework for aligning AI systems with human preference data. For various reasons, e.g., personal bias, context ambiguity, lack of training, etc, human annotators may give incorrect or inconsistent preference labels. To tackle this challenge, we propose a robust RLHF approach $R^3M$, which models the potentially corrupted preference label as sparse outliers. Accordingly, we formulate the robust reward learning as an l1-regularized maximum likelihood estimation problem. Computationally, we develop an efficient alternating optimization algorithm, which only incurs negligible computational overhead compared with the standard RLHF approach. Theoretically, we prove that under proper regularity conditions, $R^3M$ can consistently learn the underlying reward and identify outliers, provided that the number of outlier labels scales sublinearly with the preference sample size. Furthermore, we remark that $R^3M$ is versatile and can be extended to various preference optimization methods, including direct preference optimization (DPO). Our experiments on robotic control and natural language generation with large language models (LLMs) show that $R^3M$ improves robustness of the reward against several types of perturbations to the preference data.
Talk 2: Robust Online Control with Model Misspecification
Speaker: Xinyi Chen
Abstract: We study online control of an unknown nonlinear dynamical system that is approximated by a time-invariant linear system with model misspecification. Our study focuses on robustness, a measure of how much deviation from the assumed linear approximation can be tolerated by a controller while maintaining finite ℓ2-gain. A basic methodology to analyze robustness is via the small gain theorem. However, as an implication of recent lower bounds on adaptive control, this method can only yield robustness that is exponentially small in the dimension of the system and its parametric uncertainty. The work of Cusumano and Poolla shows that much better robustness can be obtained, but the control algorithm is inefficient, taking exponential time in the worst case. In this paper we investigate whether there exists an efficient algorithm with provable robustness beyond the small gain theorem. We demonstrate that for a fully actuated system, this is indeed attainable. We give an efficient controller that can tolerate robustness that is polynomial in the dimension and independent of the parametric uncertainty; furthermore, the controller obtains an ℓ2-gain whose dimension dependence is near optimal.
Talk 3: Approximations to worst-case data dropping: unmasking failure modes
Speaker: Jenny Huang
Abstract: A data analyst might worry about generalization if dropping a very small fraction of data points from a study could change its substantive conclusions. Finding the worst-case data subset to drop poses a combinatorial optimization problem. To overcome this intractability, recent works propose using additive approximations, which treat the contribution of a collection of data points as the sum of their individual contributions, and greedy approximations, which iteratively select the point with the highest impact to drop and re-run the data analysis without that point [Broderick et al., 2020, Kuschnig et al., 2021]. We identify that, even in a setting as simple as OLS linear regression, many of these approximations can break down in realistic data arrangements. Several of our examples reflect masking, where one outlier may hide or conceal the effect of another outlier. Based on the failures we identify, we provide recommendations for users and suggest directions for future improvements.
