Jia Liu

A Tale of Two Problems: Multi-Objective Bilevel Learning Meets Equality Constrained Multi-Objective Optimization

Swift-FedGNN: Federated Graph Learning with Low Communication and Sample Complexities

Global Convergence and Pareto Front Exploration in Deep-Neural Actor-Critic Multi-Objective Reinforcement Learning

SPRINT: Stochastic Performative Prediction With Variance Reduction

The Role of Learning and Memorization in Relabeling-based Unlearning for LLMs

SO-Lazy-BiO: Accelerating Bilevel Optimization with Reduced Second-Order Information Computation

CLAMP: A Chebyshev-Weighted Multi-Gradient Approach for Multi-Objective LLM Alignment

Differentiable Quadratic Optimization For the Maximum Independent Set Problem

DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity

A Lazy Hessian Evaluation Framework for Accelerating Stochastic Bilevel Optimization

Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning

FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimation

Swift-FedGNN: Federated Graph Learning with Low Communication and Sample Complexities

Enabling Pareto-Stationarity Exploration in Multi-Objective Reinforcement Learning: A Weighted-Chebyshev Multi-Objective Actor-Critic Approach