Ness Shroff

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

Mixture-of-Transformers Learn Faster: A Theoretical Study on Classification Problems

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

Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees

How to Find the Exact Pareto Front for Multi-Objective MDPs?

Theory on Mixture-of-Experts in Continual Learning

Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models

Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers

Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces

Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach

Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective

Provably Efficient Multi-Objective Bandit Algorithms under Preference-Centric Customization

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

BeST - A Novel Source Selection Metric for Transfer Learning

RLHF with Inconsistent Multi-Agent Feedback Under General Function Approximation: A Theoretical Perspective

Provably Efficient Linear Bandits with Instantaneous Constraints in Non-Convex Feature Spaces

Replay concurrently or sequentially? A theoretical perspective on replay in continual learning