activity
20142023
most citedEigenspace Restructuring: a Principle of Space and Frequency in Neural Networks

4 citations · 14 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL2023

Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?

C. Daniel Freeman, Laura Culp, Aaron Parisi +27

We introduce and study the problem of adversarial arithmetic, which provides a simple yet challenging testbed for language model alignment. This problem is comprised of arithmetic…

cs.LG20234 cited

Small-scale proxies for large-scale Transformer training instabilities

Mitchell Wortsman, Peter J. Liu, Lechao Xiao +13

Teams that have trained large Transformer-based models have reported training instabilities at large scale that did not appear when training with the same hyperparameters at smalle…

cs.LG20224 cited

Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm

Lechao Xiao, Jeffrey Pennington

Although learning in high dimensions is commonly believed to suffer from the curse of dimensionality, modern machine learning methods often exhibit an astonishing power to tackle a…

cs.LG20214 cited

Eigenspace Restructuring: a Principle of Space and Frequency in Neural Networks

Lechao Xiao

Understanding the fundamental principles behind the massive success of neural networks is one of the most important open questions in deep learning. However, due to the highly comp…

math.CA20161 cited

Higher decay inequalities for multilinear oscillatory integrals

Maxim Gilula, Philip T. Gressman, Lechao Xiao

In this paper we establish sharp estimates (up to logarithmic losses) for the multilinear oscillatory integral operator studied by Phong, Stein, and Sturm and Carbery and Wright on…

math.CA20141 cited

Bilinear Hilbert transforms associated to plane curves

Jingwei Guo, Lechao Xiao

We prove that the bilinear Hilbert transforms and maximal functions along certain general plane curves are bounded from to