
-
Incorporating Orientations into End-to-end Driving Model for Steering Control
In this paper, we present a novel end-to-end deep neural network model f...
read it
-
Structure-preserving numerical schemes for Lindblad equations
We study a family of structure-preserving deterministic numerical scheme...
read it
-
Actor-Critic 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 non-convex optimization
In this work, we analyze the global convergence property of coordinate g...
read it
-
Complexity of zigzag sampling algorithm for strongly log-concave distributions
We study the computational complexity of zigzag sampling algorithm for s...
read it
-
Neural Collapse with Cross-Entropy Loss
We consider the variational problem of cross-entropy loss with n feature...
read it
-
SMDS-Net: Model Guided Spectral-Spatial 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 decomposition-based framework for nonlin...
read it
-
Fast localization of eigenfunctions via smoothed potentials
We study the problem of predicting highly localized low-lying eigenfunct...
read it
-
Global optimality of softmax policy gradient with single hidden layer neural networks in the mean-field regime
We study the problem of policy optimization for infinite-horizon 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^2-convergence rate estimate for piecewise deterministic Markov processes
We establish L^2-exponential 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 Proximal-Gradient 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 Two-Stage Distillation Framework for Pre-training and Fine-tuning
While pre-training and fine-tuning, e.g., BERT <cit.>, GPT-2 <cit.>, hav...
read it
-
MPNet: Masked and Permuted Pre-training for Language Understanding
BERT adopts masked language modeling (MLM) for pre-training 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 zig-zag 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 non-periodic systems in two dimensions and higher
Exponentially-localized Wannier functions (ELWFs) are a basis of the Fer...
read it
-
A Mean-field 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 high-dimensional 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
-
Non-Convex Planar Harmonic Maps
We formulate a novel characterization of a family of invertible maps bet...
read it
-
Universal approximation of symmetric and anti-symmetric functions
We consider universal approximations of symmetric and anti-symmetric fun...
read it
-
Part-based Multi-stream Model for Vehicle Searching
Due to the enormous requirement in public security and intelligent trans...
read it
-
Estimating Normalizing Constants for Log-Concave 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 high-dimensional imbalanced logistic regression
High-dimensional data are routinely collected in many application areas....
read it
-
Temporal-difference learning for nonlinear value function approximation in the lazy training regime
We discuss the approximation of the value function for infinite-horizon ...
read it
-
Accelerating Langevin Sampling with Birth-death
A fundamental problem in Bayesian inference and statistical machine lear...
read it
-
Tensor Ring Decomposition: Energy Landscape and One-loop 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 solve-training framework is proposed to train neural network in ...
read it
-
MASS: Masked Sequence to Sequence Pre-training for Language Generation
Pre-training and fine-tuning, e.g., BERT, have achieved great success in...
read it
-
Tensorization of the strong data processing inequality for quantum chi-square 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 RBM-SVGD, 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 Self-Attention Network for Machine Translation
The encoder-decoder 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
Encoder-decoder 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
-
Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks
Deep networks, especially Convolutional Neural Networks (CNNs), have bee...
read it
-
Stop memorizing: A data-dependent regularization framework for intrinsic pattern learning
Deep neural networks (DNNs) typically have enough capacity to fit random...
read it