activity
20242026
collaborators

9 papers

math.OC2026

Improved Convergence Rate for Stochastic Multi-Gradient Descent: A Proof Discovered with AI

Lisha Chen

For smooth nonconvex stochastic multi-objective problems, stochastic multi-gradient descent (SMG) computes an approximate steepest common descent direction of the objectives from s…

cs.LG2026

Regularity-Aware Stochastic MGDA with Adaptive Conflict-Avoidant Update Direction Control

Chentong Huang, Lisha Chen

Multi-objective learning (MOL) aims to optimize multiple objectives simultaneously. The multi-gradient descent algorithm (MGDA) is a workhorse that iteratively updates along a comm…

cs.LG2026

SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front

Liuyuan Jiang, Chentong Huang, Lisha Chen

Scalarization is widely used in multi-objective optimization owing to its simplicity and scalability. In many applications, the goal is to generate solutions that represent diverse…

math.OC2025

Efficient Penalty-Based Bilevel Methods: Improved Analysis, Novel Updates, and Flatness Condition

Liuyuan Jiang, Quan Xiao, Lisha Chen +1

Penalty-based methods have become popular for solving bilevel optimization (BLO) problems, thanks to their effective first-order nature. However, they often require inner-loop iter…

cs.CL2025

BiRQ: Bi-Level Self-Labeling Random Quantization for Self-Supervised Speech Recognition

Liuyuan Jiang, Xiaodong Cui, Brian Kingsbury +2

Speech is a rich signal, and labeled audio-text pairs are costly, making self-supervised learning essential for scalable representation learning. A core challenge in speech SSL is…

eess.AS2025

Objective Soups: Multilingual Multi-Task Modeling for Speech Processing

A F M Saif, Lisha Chen, Xiaodong Cui +3

Training a single model for multilingual, multi-task speech processing (MSP) is severely hampered by conflicting objectives between tasks like speech recognition and translation. W…