
Incorporating Orientations into Endtoend Driving Model for Steering Control
In this paper, we present a novel endtoend deep neural network model f...
read it

Structurepreserving numerical schemes for Lindblad equations
We study a family of structurepreserving deterministic numerical scheme...
read it

ActorCritic Method for High Dimensional Static Hamilton–Jacobi–Bellman Partial Differential Equations based on Neural Networks
We propose a novel numerical method for high dimensional Hamilton–Jacobi...
read it

A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations
This paper concerns the a priori generalization analysis of the Deep Rit...
read it

On the global convergence of randomized coordinate gradient descent for nonconvex optimization
In this work, we analyze the global convergence property of coordinate g...
read it

Complexity of zigzag sampling algorithm for strongly logconcave distributions
We study the computational complexity of zigzag sampling algorithm for s...
read it

Neural Collapse with CrossEntropy Loss
We consider the variational problem of crossentropy loss with n feature...
read it

SMDSNet: Model Guided SpectralSpatial Network for Hyperspectral Image Denoising
Deep learning (DL) based hyperspectral images (HSIs) denoising approache...
read it

Manifold Learning and Nonlinear Homogenization
We describe an efficient domain decompositionbased framework for nonlin...
read it

Fast localization of eigenfunctions via smoothed potentials
We study the problem of predicting highly localized lowlying eigenfunct...
read it

Global optimality of softmax policy gradient with single hidden layer neural networks in the meanfield regime
We study the problem of policy optimization for infinitehorizon discoun...
read it

Random Coordinate Underdamped Langevin Monte Carlo
The Underdamped Langevin Monte Carlo (ULMC) is a popular Markov chain Mo...
read it

Random Coordinate Langevin Monte Carlo
Langevin Monte Carlo (LMC) is a popular Markov chain Monte Carlo samplin...
read it

Efficient sampling from the Bingham distribution
We give a algorithm for exact sampling from the Bingham distribution p(x...
read it

On explicit L^2convergence rate estimate for piecewise deterministic Markov processes
We establish L^2exponential convergence rate for three popular piecewis...
read it

Neural Machine Translation with Error Correction
Neural machine translation (NMT) generates the next target token given a...
read it

A ProximalGradient Algorithm for Crystal Surface Evolution
As a counterpoint to recent numerical methods for crystal surface evolut...
read it

Stable Phase Retrieval from Locally Stable and Conditionally Connected Measurements
This paper is concerned with stable phase retrieval for a family of phas...
read it

Numerical analysis for inchworm Monte Carlo method: Sign problem and error growth
We consider the numerical analysis of the inchworm Monte Carlo method, w...
read it

LightPAFF: A TwoStage Distillation Framework for Pretraining and Finetuning
While pretraining and finetuning, e.g., BERT <cit.>, GPT2 <cit.>, hav...
read it

MPNet: Masked and Permuted Pretraining for Language Understanding
BERT adopts masked language modeling (MLM) for pretraining and is one o...
read it

A Universal Approximation Theorem of Deep Neural Networks for Expressing Distributions
This paper studies the universal approximation property of deep neural n...
read it

Posterior computation with the Gibbs zigzag sampler
Markov chain Monte Carlo (MCMC) sampling algorithms have dominated the l...
read it

Complexity of randomized algorithms for underdamped Langevin dynamics
We establish an information complexity lower bound of randomized algorit...
read it

Existence and computation of generalized Wannier functions for nonperiodic systems in two dimensions and higher
Exponentiallylocalized Wannier functions (ELWFs) are a basis of the Fer...
read it

A Meanfield Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth
Training deep neural networks with stochastic gradient descent (SGD) can...
read it

Ensemble Kalman Inversion for nonlinear problems: weights, consistency, and variance bounds
Ensemble Kalman Inversion (EnKI), originally derived from Enseble Kalman...
read it

Solving highdimensional eigenvalue problems using deep neural networks: A diffusion Monte Carlo like approach
We propose a new method to solve eigenvalue problems for linear and semi...
read it

Deep Network Approximation for Smooth Functions
This paper establishes optimal approximation error characterization of d...
read it

NonConvex Planar Harmonic Maps
We formulate a novel characterization of a family of invertible maps bet...
read it

Universal approximation of symmetric and antisymmetric functions
We consider universal approximations of symmetric and antisymmetric fun...
read it

Partbased Multistream Model for Vehicle Searching
Due to the enormous requirement in public security and intelligent trans...
read it

Estimating Normalizing Constants for LogConcave Distributions: Algorithms and Lower Bounds
Estimating the normalizing constant of an unnormalized probability distr...
read it

Fisher information regularization schemes for Wasserstein gradient flows
We propose a variational scheme for computing Wasserstein gradient flows...
read it

Efficient posterior sampling for highdimensional imbalanced logistic regression
Highdimensional data are routinely collected in many application areas....
read it

Temporaldifference learning for nonlinear value function approximation in the lazy training regime
We discuss the approximation of the value function for infinitehorizon ...
read it

Accelerating Langevin Sampling with Birthdeath
A fundamental problem in Bayesian inference and statistical machine lear...
read it

Tensor Ring Decomposition: Energy Landscape and Oneloop Convergence of Alternating Least Squares
In this work, we study the tensor ring decomposition and its associated ...
read it

Variational training of neural network approximations of solution maps for physical models
A novel solvetraining framework is proposed to train neural network in ...
read it

MASS: Masked Sequence to Sequence Pretraining for Language Generation
Pretraining and finetuning, e.g., BERT, have achieved great success in...
read it

Tensorization of the strong data processing inequality for quantum chisquare divergences
Quantifying the contraction of classical and quantum states under noisy ...
read it

Generating Adversarial Examples With Conditional Generative Adversarial Net
Recently, deep neural networks have significant progress and successful ...
read it

A stochastic version of Stein Variational Gradient Descent for efficient sampling
We propose in this work RBMSVGD, a stochastic version of Stein Variatio...
read it

Weakly supervised segment annotation via expectation kernel density estimation
Since the labelling for the positive images/videos is ambiguous in weakl...
read it

Hybrid SelfAttention Network for Machine Translation
The encoderdecoder is the typical framework for Neural Machine Translat...
read it

Simulated Tempering Method in the Infinite Switch Limit with Adaptive Weight Learning
We investigate the theoretical foundations of the simulated tempering me...
read it

Double Path Networks for Sequence to Sequence Learning
Encoderdecoder based Sequence to Sequence learning (S2S) has made remar...
read it

Stochastic modified equations for the asynchronous stochastic gradient descent
We propose a stochastic modified equations (SME) for modeling the asynch...
read it

ButterflyNet: Optimal Function Representation Based on Convolutional Neural Networks
Deep networks, especially Convolutional Neural Networks (CNNs), have bee...
read it

Stop memorizing: A datadependent regularization framework for intrinsic pattern learning
Deep neural networks (DNNs) typically have enough capacity to fit random...
read it
Jianfeng Lu
is this you? claim profile