activity
20192022
most citedGradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks

154 citations · 228 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG20221 cited

Locally Differentially Private Distributed Deep Learning via Knowledge Distillation

Di Zhuang, Mingchen Li, J. Morris Chang

Deep learning often requires a large amount of data. In real-world applications, e.g., healthcare applications, the data collected by a single organization (e.g., hospital) is ofte…

cs.LG202228 cited

AutoBalance: Optimized Loss Functions for Imbalanced Data

Mingchen Li, Xuechen Zhang, Christos Thrampoulidis +2

Imbalanced datasets are commonplace in modern machine learning problems. The presence of under-represented classes or groups with sensitive attributes results in concerns about gen…

cs.LG20201 cited

On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?

Yao-Chun Chan, Mingchen Li, Samet Oymak

Active learning is the set of techniques for intelligently labeling large unlabeled datasets to reduce the labeling effort. In parallel, recent developments in self-supervised and…

cs.LG20205 cited

Exploring Weight Importance and Hessian Bias in Model Pruning

Mingchen Li, Yahya Sattar, Christos Thrampoulidis +1

Model pruning is an essential procedure for building compact and computationally-efficient machine learning models. A key feature of a good pruning algorithm is that it accurately…

cs.LG201939 cited

Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian

Samet Oymak, Zalan Fabian, Mingchen Li +1

Modern neural network architectures often generalize well despite containing many more parameters than the size of the training dataset. This paper explores the generalization capa…

cs.LG2019154 cited

Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks

Mingchen Li, Mahdi Soltanolkotabi, Samet Oymak

Modern neural networks are typically trained in an over-parameterized regime where the parameters of the model far exceed the size of the training data. Such neural networks in pri…