activity
20182023
most citedHow to Learn when Data Reacts to Your Model: Performative Gradient Descent

11 citations · 44 across the 29 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG20223 cited

High-dimensional density estimation with tensorizing flow

Yinuo Ren, Hongli Zhao, Yuehaw Khoo +1

We propose the tensorizing flow method for estimating high-dimensional probability density functions from the observed data. The method is based on tensor-train and flow-based gene…

cs.LG2022

Why self-attention is Natural for Sequence-to-Sequence Problems? A Perspective from Symmetries

Chao Ma, Lexing Ying

In this paper, we show that structures similar to self-attention are natural to learn many sequence-to-sequence problems from the perspective of symmetry. Inspired by language proc…

cs.LG2022

Bayesian regularization of empirical MDPs

Samarth Gupta, Daniel N. Hill, Lexing Ying +1

In most applications of model-based Markov decision processes, the parameters for the unknown underlying model are often estimated from the empirical data. Due to noise, the policy…

cs.LG2021

A Riemannian Mean Field Formulation for Two-layer Neural Networks with Batch Normalization

Chao Ma, Lexing Ying

The training dynamics of two-layer neural networks with batch normalization (BN) is studied. It is written as the training dynamics of a neural network without BN on a Riemannian m…

cs.LG2021

Combining resampling and reweighting for faithful stochastic optimization

Jing An, Lexing Ying

Many machine learning and data science tasks require solving non-convex optimization problems. When the loss function is a sum of multiple terms, a popular method is the stochastic…

cs.LG202111 cited

How to Learn when Data Reacts to Your Model: Performative Gradient Descent

Zachary Izzo, Lexing Ying, James Zou

Performative distribution shift captures the setting where the choice of which ML model is deployed changes the data distribution. For example, a bank which uses the number of open…