Christopher Brinton

Online Learning of Whittle Indices for Restless Bandits with Non-Stationary Transition Kernels

Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs

TAP: Two-Stage Adaptive Personalization of Multi-task and Multi-Modal Foundation Models in Federated Learning

Gradient Correction in Federated Learning with Adaptive Optimization

Collaborative Device-Cloud LLM Inference through Reinforcement Learning

Elevating the Tradeoff between Privacy and Utility in Zeroth-Order Vertical Federated Learning

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning

Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees

RCCDA: Adaptive Model Updates in the Presence of Concept Drift under a Constrained Resource Budget

Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers, and Gradient Clipping

Unlocking the Potential of Model Calibration in Federated Learning

Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis

SePPO: Semi-Policy Preference Optimization for Diffusion Alignment

Robust Decentralized VFL Over Dynamic Device Environment

A Modified Proximal-Perturbed Lagrangian for Non-Convex Non-Smooth Representatives of Fairness Constraints

Deep Learning Aided Broadcast Codes With Feedback

Federated Learning with Dynamic Client Arrival and Departure: Convergence and Rapid Adaptation via Initial Model Construction