collaborators

12 papers

cs.LG2026

What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression

Wendao Wu, Fangqing Zhang, Haihan Zhang +1

Teacher-Student Knowledge Transfer (KT) is ubiquitous in modern machine learning, ranging from classical model compression via Knowledge Distillation (KD) to the emergent phenomeno…

cs.LG2026

SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning

Lirui Luo, Guoxi Zhang, Hongming Xu +2

In deep reinforcement learning (DRL), an agent is trained from a stream of experience. In a continual learning setting, such agents can suffer from plasticity loss: their ability t…

cs.LG2026

Near-optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear Representation

Shihong Ding, Fangyu Du, Cong Fang

Multi-task learning (MTL) has emerged as a pivotal paradigm in machine learning by leveraging shared structures across multiple related tasks. Despite its empirical success, the de…

cs.LG2026

Mild Over-Parameterization Benefits Asymmetric Tensor PCA

Shihong Ding, Weicheng Lin, Cong Fang

Asymmetric Tensor PCA (ATPCA) is a prototypical model for studying the trade-offs between sample complexity, computation, and memory. Existing algorithms for this problem typically…

cs.LG2026

Accelerating Single-Pass SGD for Generalized Linear Prediction

Qian Chen, Shihong Ding, Cong Fang

We study generalized linear prediction under a streaming setting, where each iteration uses only one fresh data point for a gradient-level update. While momentum is well-establishe…

cs.CV2026

MVR: Multi-view Video Reward Shaping for Reinforcement Learning

Lirui Luo, Guoxi Zhang, Hongming Xu +3

Reward design is of great importance for solving complex tasks with reinforcement learning. Recent studies have explored using image-text similarity produced by vision-language mod…