activity
20192024
most citedNoisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization

2 citations · 3 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2022

Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably

Tianyi Liu, Yan Li, Enlu Zhou +1

We investigate the role of noise in optimization algorithms for learning over-parameterized models. Specifically, we consider the recovery of a rank one matrix $Y^*\in R^{d\times d…

cs.LG20221 cited

Deep Learning Assisted End-to-End Synthesis of mm-Wave Passive Networks with 3D EM Structures: A Study on A Transformer-Based Matching Network

Siawpeng Er, Edward Liu, Minshuo Chen +4

This paper presents a deep learning assisted synthesis approach for direct end-to-end generation of RF/mm-wave passive matching network with 3D EM structures. Different from prior…

cs.LG20212 cited

Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization

Tianyi Liu, Yan Li, Song Wei +2

Numerous empirical evidences have corroborated the importance of noise in nonconvex optimization problems. The theory behind such empirical observations, however, is still largely…

cs.LG2020

Residual Network Based Direct Synthesis of EM Structures: A Study on One-to-One Transformers

David Munzer, Siawpeng Er, Minshuo Chen +4

We propose using machine learning models for the direct synthesis of on-chip electromagnetic (EM) passive structures to enable rapid or even automated designs and optimizations of…

cs.LG2019

Towards Understanding the Importance of Noise in Training Neural Networks

Mo Zhou, Tianyi Liu, Yan Li +3

Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of neural networks. The theory behind, however, is still largel…

cs.LG2019

Inductive Bias of Gradient Descent based Adversarial Training on Separable Data

Yan Li, Ethan X. Fang, Huan Xu +1

Adversarial training is a principled approach for training robust neural networks. Despite of tremendous successes in practice, its theoretical properties still remain largely unex…