collaborators

12 papers

cs.LG2026

FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Caching

Haoran Zhang, Cainã Figueiredo Pereira, Marie Siew +3

Federated learning (FL) is often subject to aggregation variance if clients do not consistently participate in training rounds. While reusing stale model updates from inactive clie…

cs.LG2026

Unlearning Offline Stochastic Multi-Armed Bandits

Zichun Ye, Runqi Wang, Xuchuang Wang +3

Machine unlearning aims to unlearn data points from a learned model, offering a principled way to process data-deletion requests and mitigate privacy risks without full retraining.…

cs.LG2026

Scaling Federated Linear Contextual Bandits via Sketching

Hantao Yang, Hong Xie, Xutong Liu +1

In federated contextual linear bandits, high data dimensionality incurs prohibitive computation and communication costs: local agents perform -time determinant computation…

cs.LG2026

Continuous Semantic Caching for Low-Cost LLM Serving

Baran Atalar, Xutong Liu, Jinhang Zuo +3

As Large Language Models (LLMs) become increasingly popular, caching responses so that they can be reused by users with semantically similar queries has become a vital strategy for…

cs.LG2026

Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing

Zeyu Zhang, Xiangxiang Dai, Ziyi Han +2

Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy during deployment and inference. However, r…

cs.LG2025

Online Learning to Rank under Corruption: A Robust Cascading Bandits Approach

Fatemeh Ghaffari, Siddarth Sitaraman, Xutong Liu +2

Online learning to rank (OLTR) studies how to recommend a short ranked list of items from a large pool and improves future rankings based on user clicks. This setting is commonly m…