activity
20112024
most citedWavelet Burst Accumulation for turbulence mitigation

27 citations · 49 across the 9 of their papers we have counts for

collaborators
Showing 2019Show all

6 papers · 1 filter

cs.LG2019

Graph Interpolating Activation Improves Both Natural and Robust Accuracies in Data-Efficient Deep Learning

Bao Wang, Stanley J. Osher

Improving the accuracy and robustness of deep neural nets (DNNs) and adapting them to small training data are primary tasks in deep learning research. In this paper, we replace the…

eess.IV2019

A semi-implicit relaxed Douglas-Rachford algorithm (sir-DR) for Ptychograhpy

Minh Pham, Arjun Rana, Jianwei Miao +1

Alternating projection based methods, such as ePIE and rPIE, have been used widely in ptychography. However, they only work well if there are adequate measurements (diffraction pat…

cs.LG2019

DP-LSSGD: A Stochastic Optimization Method to Lift the Utility in Privacy-Preserving ERM

Bao Wang, Quanquan Gu, March Boedihardjo +2

Machine learning (ML) models trained by differentially private stochastic gradient descent (DP-SGD) have much lower utility than the non-private ones. To mitigate this degradation,…

cs.LG2019

Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets

Penghang Yin, Jiancheng Lyu, Shuai Zhang +3

Training activation quantized neural networks involves minimizing a piecewise constant function whose gradient vanishes almost everywhere, which is undesirable for the standard bac…

math.OC2019

Unnormalized Optimal Transport

Wilfrid Gangbo, Wuchen Li, Stanley Osher +1

We propose an extension of the computational fluid mechanics approach to the Monge-Kantorovich mass transfer problem, which was developed by Benamou-Brenier. Our extension allows o…

cs.LG2019

A Deterministic Gradient-Based Approach to Avoid Saddle Points

Lisa Maria Kreusser, Stanley J. Osher, Bao Wang

Loss functions with a large number of saddle points are one of the major obstacles for training modern machine learning models efficiently. First-order methods such as gradient des…