activity
20192023
most citedBypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing

4 citations · 7 across the 6 of their papers we have counts for

collaborators

9 papers

quant-ph2023

Revisiting Quantum Algorithms for Linear Regressions: Quadratic Speedups without Data-Dependent Parameters

Zhao Song, Junze Yin, Ruizhe Zhang

Linear regression is one of the most fundamental linear algebra problems. Given a dense matrix and a vector , the goal is to find such that…

math.OC2023

Efficient Algorithm for Solving Hyperbolic Programs

Yichuan Deng, Zhao Song, Lichen Zhang +1

Hyperbolic polynomials is a class of real-roots polynomials that has wide range of applications in theoretical computer science. Each hyperbolic polynomial also induces a hyperboli…

cs.LG20224 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…

quant-ph2022

Quantum Speedups of Optimizing Approximately Convex Functions with Applications to Logarithmic Regret Stochastic Convex Bandits

Tongyang Li, Ruizhe Zhang

We initiate the study of quantum algorithms for optimizing approximately convex functions. Given a convex set and a function $F\colon\mathbb{R}^{n…

cs.DS2022

Fast Distance Oracles for Any Symmetric Norm

Yichuan Deng, Zhao Song, Omri Weinstein +1

In the Distance Oracle problem, the goal is to preprocess vectors in a -dimensional metric space into a cheap data st…

cs.LG20213 cited

Does Preprocessing Help Training Over-parameterized Neural Networks?

Zhao Song, Shuo Yang, Ruizhe Zhang

Deep neural networks have achieved impressive performance in many areas. Designing a fast and provable method for training neural networks is a fundamental question in machine lear…