Mingyi Hong

On the Convergence of A Class of Adam-Type Algorithms for Non-Convex\n Optimization

2018 · arXiv (Cornell University)

This paper studies a class of adaptive gradient based momentum algorithms\nthat update the search directions and learning rates simultaneously using past\ngradients. This class, which we refer to as the "Adam-type", includes the\npopular algorithms such as …

GLASU: A Communication-Efficient Algorithm for Federated Learning with Vertically Distributed Graph Data

2023 · arXiv (Cornell University)

Vertical federated learning (VFL) is a distributed learning paradigm, where computing clients collectively train a model based on the partial features of the same set of samples they possess. Current research on VFL focuses on …

Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate

2024 · arXiv (Cornell University)

Machine unlearning has been used to remove unwanted knowledge acquired by large language models (LLMs). In this paper, we examine machine unlearning from an optimization perspective, framing it as a regularized multi-task optimization problem, where …