199 citations · 1.3k across the 122 of their papers we have counts for
16 papers · 1 filter
A Note on Optimization Formulations of Markov Decision Processes
Lexing Ying, Yuhua Zhu
This note summarizes the optimization formulations used in the study of Markov decision processes. We consider both the discounted and undiscounted processes under the standard and…
Achieving Adversarial Robustness Requires An Active Teacher
Chao Ma, Lexing Ying
A new understanding of adversarial examples and adversarial robustness is proposed by decoupling the data generator and the label generator (which we call the teacher). In our fram…
A semigroup method for high dimensional committor functions based on neural network
Haoya Li, Yuehaw Khoo, Yinuo Ren +1
This paper proposes a new method based on neural networks for computing the high-dimensional committor functions that satisfy Fokker-Planck equations. Instead of working with parti…
Efficient Long-Range Convolutions for Point Clouds
Yifan Peng, Lin Lin, Lexing Ying +1
The efficient treatment of long-range interactions for point clouds is a challenging problem in many scientific machine learning applications. To extract global information, one us…
Operator Shifting for Noisy Elliptic Systems
Philip A. 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…
Distributed-memory -matrix Algebra I: Data Distribution and Matrix-vector Multiplication
Yingzhou Li, Jack Poulson, Lexing Ying
We introduce a data distribution scheme for -matrices and a distributed-memory algorithm for -matrix-vector multiplication. Our data distribution scheme a…
Why resampling outperforms reweighting for correcting sampling bias with stochastic gradients
Jing An, Lexing Ying, Yuhua Zhu
A data set sampled from a certain population is biased if the subgroups of the population are sampled at proportions that are significantly different from their underlying proporti…
A heuristic independent particle approximation to determinantal point processes
Lexing Ying
A determinantal point process is a stochastic point process that is commonly used to capture negative correlations. It has become increasingly popular in machine learning in recent…
A Simple Multiscale Method for Mean Field Games
Haoya Li, Yuwei Fan, Lexing Ying
This paper proposes a multiscale method for solving the numerical solution of mean field games which accelerates the convergence and addresses the problem of determining the initia…
Natural Gradient for Combined Loss Using Wavelets
Lexing Ying
Natural gradients have been widely used in optimization of loss functionals over probability space, with important examples such as Fisher-Rao gradient descent for Kullback-Leibler…
Borrowing From the Future: Addressing Double Sampling in Model-free Control
Yuhua Zhu, Zach Izzo, Lexing Ying
In model-free reinforcement learning, the temporal difference method and its variants become unstable when combined with nonlinear function approximations. Bellman residual minimiz…
Mirror Descent Algorithms for Minimizing Interacting Free Energy
Lexing Ying
This note considers the problem of minimizing interacting free energy. Motivated by the mirror descent algorithm, for a given interacting free energy, we propose a descent dynamics…
Maximizing robustness of point-set registration by leveraging non-convexity
Cindy Orozco Bohorquez, Yuehaw Khoo, Lexing Ying
Point-set registration is a classical image processing problem that looks for the optimal transformation between two sets of points. In this work, we analyze the impact of outliers…
Hierarchical Interpolative Factorization Preconditioner for Parabolic Equations
Jordi Feliu-Fabà, Lexing Ying
This note proposes an efficient preconditioner for solving linear and semi-linear parabolic equations. With the Crank-Nicholson time stepping method, the algebraic system of equati…
A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth
Yiping Lu, Chao Ma, Yulong Lu +2
Training deep neural networks with stochastic gradient descent (SGD) can often achieve zero training loss on real-world tasks although the optimization landscape is known to be hig…
A Sharp Convergence Rate for the Asynchronous Stochastic Gradient Descent
Yuhua Zhu, Lexing Ying
We give a sharp convergence rate for the asynchronous stochastic gradient descent (ASGD) algorithms when the loss function is a perturbed quadratic function based on the stochastic…