199 citations · 1.3k across the 122 of their papers we have counts for
16 papers · 1 filter
How to Learn when Data Gradually Reacts to Your Model
Zachary Izzo, James Zou, Lexing Ying
A recent line of work has focused on training machine learning (ML) models in the performative setting, i.e. when the data distribution reacts to the deployed model. The goal in th…
Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality
Yiping Lu, Haoxuan Chen, Jianfeng Lu +2
In this paper, we study the statistical limits of deep learning techniques for solving elliptic partial differential equations (PDEs) from random samples using the Deep Ritz Method…
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…
Operator Shifting for Model-based Policy Evaluation
Xun Tang, Lexing Ying, Yuhua Zhu
In model-based reinforcement learning, the transition matrix and reward vector are often estimated from random samples subject to noise. Even if the estimated model is an unbiased…
Approximate Newton policy gradient algorithms
Haoya Li, Samarth Gupta, Hsiangfu Yu +2
Policy gradient algorithms have been widely applied to Markov decision processes and reinforcement learning problems in recent years. Regularization with various entropy functions…
Variational Actor-Critic Algorithms
Yuhua Zhu, Lexing Ying
We introduce a class of variational actor-critic algorithms based on a variational formulation over both the value function and the policy. The objective function of the variationa…
Shrinkage Estimation of Functions of Large Noisy Symmetric Matrices
Panagiotis Lolas, Lexing Ying
We study the problem of estimating functions of a large symmetric matrix when we only have access to a noisy estimate We are interested in the…
Enterprise-Scale Search: Accelerating Inference for Sparse Extreme Multi-Label Ranking Trees
Philip A. Etter, Kai Zhong, Hsiang-Fu Yu +2
Tree-based models underpin many modern semantic search engines and recommender systems due to their sub-linear inference times. In industrial applications, these models operate at…
Approximate inversion of discrete Fourier integral operators
Jordi Feliu-Fabà, Lexing Ying
This paper introduces a factorization for the inverse of discrete Fourier integral operators that can be applied in quasi-linear time. The factorization starts by approximating the…
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…
On Linear Stability of SGD and Input-Smoothness of Neural Networks
Chao Ma, Lexing Ying
The multiplicative structure of parameters and input data in the first layer of neural networks is explored to build connection between the landscape of the loss function with resp…
A semigroup method for high dimensional elliptic PDEs and eigenvalue problems based on neural networks
Haoya Li, Lexing Ying
In this paper, we propose a semigroup method for solving high-dimensional elliptic partial differential equations (PDEs) and the associated eigenvalue problems based on neural netw…
Operator Shifting for General Noisy Matrix Systems
Philip Etter, Lexing Ying
In the computational sciences, one must often estimate model parameters from data subject to noise and uncertainty, leading to inaccurate results. In order to improve the accuracy…
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…
Multi-Level Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data
Zhihan Li, Yuwei Fan, Lexing Ying
In scientific machine learning, regression networks have been recently applied to approximate solution maps (e.g., potential-ground state map of Schrödinger equation). In this pape…
An efficient dynamical low-rank algorithm for the Boltzmann-BGK equation close to the compressible viscous flow regime
Lukas Einkemmer, Jingwei Hu, Lexing Ying
It has recently been demonstrated that dynamical low-rank algorithms can provide robust and efficient approximation to a range of kinetic equations. This is true especially if the…