activity
20202023
most citedScatterbrain: Unifying Sparse and Low-rank Attention Approximation

9 citations · 49 across the 15 of their papers we have counts for

collaborators
Showing 2022Show all

5 papers · 1 filter

cs.LG2022★ 4 cited

Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing

Josh Alman, Jiehao Liang, Zhao Song +2

Over the last decade, deep neural networks have transformed our society, and they are already widely applied in various machine learning applications. State-of-art deep neural netw…

cs.LG2022★ 2 cited

Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability

Zhao Song, Yitan Wang, Zheng Yu +1

Sketching is one of the most fundamental tools in large-scale machine learning. It enables runtime and memory saving via randomly compressing the original large problem into lower…

cs.LG2022★ 2 cited

A Sublinear Adversarial Training Algorithm

Yeqi Gao, Lianke Qin, Zhao Song +1

Adversarial training is a widely used strategy for making neural networks resistant to adversarial perturbations. For a neural network of width , input training data in …

quant-ph2022★ 3 cited

A Faster Quantum Algorithm for Semidefinite Programming via Robust IPM Framework

Baihe Huang, Shunhua Jiang, Zhao Song +2

This paper studies a fundamental problem in convex optimization, which is to solve semidefinite programming (SDP) with high accuracy. This paper follows from the existing robust SD…

cs.LG2022★ 3 cited

Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis

Alexander Munteanu, Simon Omlor, Zhao Song +1

A common method in training neural networks is to initialize all the weights to be independent Gaussian vectors. We observe that by instead initializing the weights into independen…