5 papers
Why Ghost Outputs Teach: A Kernel-Based Understanding of Subliminal Learning
Zhe Li, Bicheng Ying, Chaosheng Dong +1
Subliminal Learning (SL) is a recently identified phenomenon in which a student model acquires downstream task capabilities by matching seemingly unrelated auxiliary outputs from a…
Behavioral Feature Boosting via Substitute Relationships for E-commerce Search
Chaosheng Dong, Michinari Momma, Yijia Wang +2
On E-commerce platforms, new products often suffer from the cold-start problem: limited interaction data reduces their search visibility and hurts relevance ranking. To address thi…
Enabling Pareto-Stationarity Exploration in Multi-Objective Reinforcement Learning: A Multi-Objective Weighted-Chebyshev Actor-Critic Approach
Fnu Hairi, Jiao Yang, Tianchen Zhou +6
In many multi-objective reinforcement learning (MORL) applications, being able to systematically explore the Pareto-stationary solutions under multiple non-convex reward objectives…
STIMULUS: Achieving Fast Convergence and Low Sample Complexity in Stochastic Multi-Objective Learning
Zhuqing Liu, Chaosheng Dong, Michinari Momma +5
Recently, multi-objective optimization (MOO) has gained attention for its broad applications in ML, operations research, and engineering. However, MOO algorithm design remains in i…
Converge Faster, Talk Less: Hessian-Informed Federated Zeroth-Order Optimization
Zhe Li, Bicheng Ying, Zidong Liu +2
Zeroth-order (ZO) optimization enables dimension-free communication in federated learning (FL), making it attractive for fine-tuning of large language models (LLMs) due to signific…