Search Results for author:
Found 112 papers, 22 papers with code
A Mean Field Analysis Of Deep ResNet And Beyond: Towards Provably Optimization Via Overparameterization From Depth
Specifically, we propose a \textbf{new continuum limit} of deep residual networks, which enjoys a good landscape in the sense that \textbf{every local minimizer is global}.
Gait Recognition from a Single Image using a Phase-Aware Gait Cycle Reconstruction Network
Specifically, a phase estimation network is introduced for the input single image, and the gait cycle reconstruction network exploits the estimated phase to mitigate the dependence of an encoded feature on the phase of that single image.
DaringFed: A Dynamic Bayesian Persuasion Pricing for Online Federated Learning under Two-sided Incomplete Information
To incentivize clients to participate in training by offering dynamic rewards to each arriving client, we design a novel Dynamic Bayesian persuasion pricing for online Federated learning (DaringFed) under TII.
Bi-Lipschitz Ansatz for Anti-Symmetric Functions
Motivated by applications for simulating quantum many body functions, we propose a new universal ansatz for approximating anti-symmetric functions.
Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control
Generating street-view images from satellite imagery is a challenging task, particularly in maintaining accurate pose alignment and incorporating diverse environmental conditions.
Convergence of two-timescale gradient descent ascent dynamics: finite-dimensional and mean-field perspectives
The two-timescale gradient descent-ascent (GDA) is a canonical gradient algorithm designed to find Nash equilibria in min-max games.
A Unified Blockwise Measurement Design for Learning Quantum Channels and Lindbladians via Low-Rank Matrix Sensing
We propose a robust approach based on the matrix sensing techniques for quantum superoperator learning that extends beyond the positive semidefinite case, encompassing both quantum channels and Lindbladians.
Consistency Posterior Sampling for Diverse Image Synthesis
Posterior sampling in high-dimensional spaces using generative models holds significant promise for various applications, including but not limited to inverse problems and guided generation tasks.
FedCross: Intertemporal Federated Learning Under Evolutionary Games
Federated Learning (FL) mitigates privacy leakage in decentralized machine learning by allowing multiple clients to train collaboratively locally.
TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learning
However, in the context of semi-decentralized FL, clients' communication and training states are dynamic.
Towards characterizing the value of edge embeddings in Graph Neural Networks
In this paper, we consider the benefits of architectures that maintain and update edge embeddings.
Posterior sampling via Langevin dynamics based on generative priors
Posterior sampling in high-dimensional spaces using generative models holds significant promise for various applications, including but not limited to inverse problems and guided generation tasks.
What does guidance do? A fine-grained analysis in a simple setting
The use of guidance in diffusion models was originally motivated by the premise that the guidance-modified score is that of the data distribution tilted by a conditional likelihood raised to some power.
Second Place Solution of WSDM2023 Toloka Visual Question Answering Challenge
We designed a three-stage solution for this task.
First Place Solution of 2023 Global Artificial Intelligence Technology Innovation Competition Track 1
The retrieval augmentation constructs a mini-knowledge base, enriching the input information of the model, while the similarity bucket further perceives the noise information within the mini-knowledge base, guiding the model to generate higher-quality diagnostic reports based on the similarity prompts.
The Solution for Temporal Sound Localisation Task of ICCV 1st Perception Test Challenge 2023
In this paper, we propose a solution for improving the quality of temporal sound localization.
More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling
Empirically, we show that in tasks where deep exploration is necessary, our proposed algorithms that combine FGTS and approximate sampling perform significantly better compared to other strong baselines.
TCMD: A Traditional Chinese Medicine QA Dataset for Evaluating Large Language Models
Moreover, we also analyze the robustness of current LLMs in solving TCM QA tasks by introducing randomness.
TAI++: Text as Image for Multi-Label Image Classification by Co-Learning Transferable Prompt
Then, a co-learning strategy with a dual-adapter module is designed to transfer visual knowledge from pseudo-visual prompt to text prompt, enhancing their visual representation abilities.
SSUMamba: Spatial-Spectral Selective State Space Model for Hyperspectral Image Denoising
Long-range spatial-spectral correlation modeling is beneficial for HSI denoising but often comes with high computational complexity.
AS-FIBA: Adaptive Selective Frequency-Injection for Backdoor Attack on Deep Face Restoration
Extensive experiments demonstrate the efficacy of the degradation objective on state-of-the-art face restoration models.
Adversarial Purification and Fine-tuning for Robust UDC Image Restoration
This study delves into the enhancement of Under-Display Camera (UDC) image restoration models, focusing on their robustness against adversarial attacks.
Learning Memory Kernels in Generalized Langevin Equations
We introduce a novel approach for learning memory kernels in Generalized Langevin Equations.
MoML: Online Meta Adaptation for 3D Human Motion Prediction
In the academic field the research on human motion prediction tasks mainly focuses on exploiting the observed information to forecast human movements accurately in the near future horizon.
Fast Adaptation for Human Pose Estimation via Meta-Optimization
Domain shift is a challenge for supervised human pose estimation where the source data and target data come from different distributions.
Hyperspectral Image Denoising via Spatial-Spectral Recurrent Transformer
This block consists of a spatial branch and a spectral branch.
Deep Equilibrium Based Neural Operators for Steady-State PDEs
Motivated by this observation, we propose FNO-DEQ, a deep equilibrium variant of the FNO architecture that directly solves for the solution of a steady-state PDE as the infinite-depth fixed point of an implicit operator layer using a black-box root solver and differentiates analytically through this fixed point resulting in $\mathcal{O}(1)$ training memory.
Convergence of flow-based generative models via proximal gradient descent in Wasserstein space
Leveraging the exponential convergence of the proximal gradient descent (GD) in Wasserstein space, we prove the Kullback-Leibler (KL) guarantee of data generation by a JKO flow model to be $O(\varepsilon^2)$ when using $N \lesssim \log (1/\varepsilon)$ many JKO steps ($N$ Residual Blocks in the flow) where $\varepsilon $ is the error in the per-step first-order condition.
The Solution for the CVPR2023 NICE Image Captioning Challenge
In this paper, we present our solution to the New frontiers for Zero-shot Image Captioning Challenge.
Solution for SMART-101 Challenge of ICCV Multi-modal Algorithmic Reasoning Task 2023
At the data level, inspired by the challenge paper, we categorized the whole questions into eight types and utilized the llama-2-chat model to directly generate the type for each question in a zero-shot manner.
Learning Dense Flow Field for Highly-accurate Cross-view Camera Localization
We propose a novel end-to-end approach that leverages the learning of dense pixel-wise flow fields in pairs of ground and satellite images to calculate the camera pose.
Diffusion Methods for Generating Transition Paths
In this work, we seek to simulate rare transitions between metastable states using score-based generative models.
Riemannian Langevin Monte Carlo schemes for sampling PSD matrices with fixed rank
This paper introduces two explicit schemes to sample matrices from Gibbs distributions on $\mathcal S^{n, p}_+$, the manifold of real positive semi-definite (PSD) matrices of size $n\times n$ and rank $p$.
NICE: CVPR 2023 Challenge on Zero-shot Image Captioning
In this report, we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation) project and share the results and outcomes of 2023 challenge.
Benchmarking Ultra-High-Definition Image Reflection Removal
To the best of our knowledge, these two datasets are the first largest-scale UHD datasets for SIRR.
Deep Network Approximation: Beyond ReLU to Diverse Activation Functions
This paper explores the expressive power of deep neural networks for a diverse range of activation functions.
Enhanced Fine-grained Motion Diffusion for Text-driven Human Motion Synthesis
The emergence of text-driven motion synthesis technique provides animators with great potential to create efficiently.
Accelerate Langevin Sampling with Birth-Death Process and Exploration Component
Aiming at multimodality, we propose a new sampling method that takes advantage of both birth-death process and exploration component.
Score-based Transport Modeling for Mean-Field Fokker-Planck Equations
We use the score-based transport modeling method to solve the mean-field Fokker-Planck equations, which we call MSBTM.
Convergence of stochastic gradient descent under a local Lojasiewicz condition for deep neural networks
We study the convergence of stochastic gradient descent (SGD) for non-convex objective functions.
Meta-Auxiliary Learning for Adaptive Human Pose Prediction
Predicting high-fidelity future human poses, from a historically observed sequence, is decisive for intelligent robots to interact with humans.
DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedback
Let us rethink the real-world scenarios that require human motion prediction techniques, such as human-robot collaboration.
Global Optimality of Elman-type RNN in the Mean-Field Regime
We analyze Elman-type Recurrent Reural Networks (RNNs) and their training in the mean-field regime.
A Policy Gradient Framework for Stochastic Optimal Control Problems with Global Convergence Guarantee
We consider policy gradient methods for stochastic optimal control problem in continuous time.
On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network
This paper explores the expressive power of deep neural networks through the framework of function compositions.
Robust Single Image Reflection Removal Against Adversarial Attacks
This paper addresses the problem of robust deep single-image reflection removal (SIRR) against adversarial attacks.
Ranked #4 on
Reflection Removal
on Real20
Test-time Personalizable Forecasting of 3D Human Poses
Current motion forecasting approaches typically train a deep end-to-end model from the source domain data, and then apply it directly to target subjects.
A Structure-guided Effective and Temporal-lag Connectivity Network for Revealing Brain Disorder Mechanisms
Brain network provides important insights for the diagnosis of many brain disorders, and how to effectively model the brain structure has become one of the core issues in the domain of brain imaging analysis.
Regularized Stein Variational Gradient Flow
However, a mean-field analysis reveals that the gradient flow corresponding to the SVGD algorithm (i. e., the Stein Variational Gradient Flow) only provides a constant-order approximation to the Wasserstein Gradient Flow corresponding to the KL-divergence minimization.
Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions
We give an improved theoretical analysis of score-based generative modeling.
Neural Network Approximations of PDEs Beyond Linearity: A Representational Perspective
We show that if composing a function with Barron norm $b$ with partial derivatives of $L$ produces a function of Barron norm at most $B_L b^p$, the solution to the PDE can be $\epsilon$-approximated in the $L^2$ sense by a function with Barron norm $O\left(\left(dB_L\right)^{\max\{p \log(1/ \epsilon), p^{\log(1/\epsilon)}\}}\right)$.
On Representing Mixed-Integer Linear Programs by Graph Neural Networks
While Mixed-integer linear programming (MILP) is NP-hard in general, practical MILP has received roughly 100--fold speedup in the past twenty years.
Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction
This process offers a natural way to obtain the "whitened" latents without any trainable parameters, and human motion prediction can be regarded as the reverse diffusion process that converts the noise distribution into realistic future motions conditioned on the observed sequence.
Convergence of score-based generative modeling for general data distributions
Score-based generative modeling (SGM) has grown to be a hugely successful method for learning to generate samples from complex data distributions such as that of images and audio.
On Representing Linear Programs by Graph Neural Networks
In particular, the graph neural network (GNN) is considered a suitable ML model for optimization problems whose variables and constraints are permutation--invariant, for example, the linear program (LP).
A deep learning framework for geodesics under spherical Wasserstein-Fisher-Rao metric and its application for weighted sample generation
In this paper, we develop a deep learning framework to compute the geodesics under the spherical WFR metric, and the learned geodesics can be adopted to generate weighted samples.
MonoSIM: Simulating Learning Behaviors of Heterogeneous Point Cloud Object Detectors for Monocular 3D Object Detection
The insight behind introducing MonoSIM is that we propose to simulate the feature learning behaviors of a point cloud based detector for monocular detector during the training period.
Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction
Previous works on human motion prediction follow the pattern of building a mapping relation between the sequence observed and the one to be predicted.
Convergence for score-based generative modeling with polynomial complexity
Using our guarantee, we give a theoretical analysis of score-based generative modeling, which transforms white-noise input into samples from a learned data distribution given score estimates at different noise scales.
Single Time-scale Actor-critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees
We propose a single time-scale actor-critic algorithm to solve the linear quadratic regulator (LQR) problem.
A Regularity Theory for Static Schrödinger Equations on $\mathbb{R}^d$ in Spectral Barron Spaces
Spectral Barron spaces have received considerable interest recently as it is the natural function space for approximation theory of two-layer neural networks with a dimension-free convergence rate.
Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality
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 (DRM) and Physics-Informed Neural Networks (PINNs).
Statistical Numerical PDE : Fast Rate, Neural Scaling Law and When it’s Optimal
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 (DRM) and Physics-Informed Neural Networks (PINNs).
On the Representation of Solutions to Elliptic PDEs in Barron Spaces
Numerical solutions to high-dimensional partial differential equations (PDEs) based on neural networks have seen exciting developments.
A Priori Generalization Error Analysis of Two-Layer Neural Networks for Solving High Dimensional Schrödinger Eigenvalue Problems
We prove that the convergence rate of the generalization error is independent of the dimension $d$, under the a priori assumption that the ground state lies in a spectral Barron space.
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 for autonomous driving that takes monocular image sequence as input, and directly generates the steering control angle.
A Grid-free Approach for Simulating Sweep and Cyclic Voltammetry
We present a new computational approach to simulate linear sweep and cyclic voltammetry experiments that does not require a discretized grid in space to quantify diffusion.
Chemical Physics
Algebraic localization implies exponential localization in non-periodic insulators
In two and three spatial dimensions, it is well understood for periodic insulators that exponentially-localized Wannier functions exist if and only if there exists an orthonormal basis for the Fermi projection with finite second moment (i. e. all basis elements satisfy $\int |\boldsymbol{x}|^2 |w(\boldsymbol{x})|^2 \,\text{d}{\boldsymbol{x}} < \infty$).
Mathematical Physics Mesoscale and Nanoscale Physics Mathematical Physics
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 Ritz Method (DRM) [W. E and B. Yu, 2017], a popular neural-network-based method for solving high dimensional partial differential equations.
Complexity of zigzag sampling algorithm for strongly log-concave distributions
We study the computational complexity of zigzag sampling algorithm for strongly log-concave distributions.
Neural Collapse with Cross-Entropy Loss
We consider the variational problem of cross-entropy loss with $n$ feature vectors on a unit hypersphere in $\mathbb{R}^d$.
SMDS-Net: Model Guided Spectral-Spatial Network for Hyperspectral Image Denoising
This model first projects the observed HSIs into a low-dimensional orthogonal subspace, and then represents the projected image with a multidimensional dictionary.
Random Coordinate Underdamped Langevin Monte Carlo
We investigate the computational complexity of RC-ULMC and compare it with the classical ULMC for strongly log-concave probability distributions.
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 discounted Markov Decision Processes with softmax policy and nonlinear function approximation trained with policy gradient algorithms.
Random Coordinate Langevin Monte Carlo
We investigate the total complexity of RC-LMC and compare it with the classical LMC for log-concave probability distributions.
Efficient sampling from the Bingham distribution
We give a algorithm for exact sampling from the Bingham distribution $p(x)\propto \exp(x^\top A x)$ on the sphere $\mathcal S^{d-1}$ with expected runtime of $\operatorname{poly}(d, \lambda_{\max}(A)-\lambda_{\min}(A))$.
Neural Machine Translation with Error Correction
Neural machine translation (NMT) generates the next target token given as input the previous ground truth target tokens during training while the previous generated target tokens during inference, which causes discrepancy between training and inference as well as error propagation, and affects the translation accuracy.
End-to-end Learning for Inter-Vehicle Distance and Relative Velocity Estimation in ADAS with a Monocular Camera
In this paper, we propose a monocular camera-based inter-vehicle distance and relative velocity estimation method based on end-to-end training of a deep neural network.
LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuning
While pre-training and fine-tuning, e. g., BERT~\citep{devlin2018bert}, GPT-2~\citep{radford2019language}, have achieved great success in language understanding and generation tasks, the pre-trained models are usually too big for online deployment in terms of both memory cost and inference speed, which hinders them from practical online usage.
MPNet: Masked and Permuted Pre-training for Language Understanding
Since BERT neglects dependency among predicted tokens, XLNet introduces permuted language modeling (PLM) for pre-training to address this problem.
Ranked #16 on
Only Connect Walls Dataset Task 1 (Grouping)
on OCW
(using extra training data)
A Universal Approximation Theorem of Deep Neural Networks for Expressing Probability Distributions
In particular, the size of neural network can grow exponentially in $d$ when $1$-Wasserstein distance is used as the discrepancy, whereas for both MMD and KSD the size of neural network only depends on $d$ at most polynomially.
A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth
Specifically, we propose a new continuum limit of deep residual networks, which enjoys a good landscape in the sense that every local minimizer is global.
A Mean-field Analysis of Deep ResNet and Beyond:Towards Provable Optimization Via Overparameterization From Depth
Specifically, we propose a \textbf{new continuum limit} of deep residual networks, which enjoys a good landscape in the sense that \textbf{every local minimizer is global}.
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 semilinear second order differential operators in high dimensions based on deep neural networks.
Deep Network Approximation for Smooth Functions
This paper establishes the (nearly) optimal approximation error characterization of deep rectified linear unit (ReLU) networks for smooth functions in terms of both width and depth simultaneously.
Part-based Multi-stream Model for Vehicle Searching
We can easily measure the similarity of two vehicle images by computing the Euclidean distance of the features from FC layer.
Estimating Normalizing Constants for Log-Concave Distributions: Algorithms and Lower Bounds
Estimating the normalizing constant of an unnormalized probability distribution has important applications in computer science, statistical physics, machine learning, and statistics.
Temporal-difference learning for nonlinear value function approximation in the lazy training regime
We then give examples of such convergence results in the case of models that diverge if trained with non-lazy TD learning, and in the case of neural networks.
Temporal-difference learning with nonlinear function approximation: lazy training and mean field regimes
We finally give examples of our convergence results in the case of models that diverge if trained with non-lazy TD learning, and in the case of neural networks.
Accelerating Langevin Sampling with Birth-death
A fundamental problem in Bayesian inference and statistical machine learning is to efficiently sample from multimodal distributions.
Variational training of neural network approximations of solution maps for physical models
A novel solve-training framework is proposed to train neural network in representing low dimensional solution maps of physical models.
MASS: Masked Sequence to Sequence Pre-training for Language Generation
Pre-training and fine-tuning, e. g., BERT, have achieved great success in language understanding by transferring knowledge from rich-resource pre-training task to the low/zero-resource downstream tasks.
Generating Adversarial Examples With Conditional Generative Adversarial Net
Recently, deep neural networks have significant progress and successful application in various fields, but they are found vulnerable to attack instances, e. g., adversarial examples.
Coordinate descent full configuration interaction
We develop an efficient algorithm, coordinate descent FCI (CDFCI), for the electronic structure ground state calculation in the configuration interaction framework.
Chemical Physics Computational Physics
A stochastic version of Stein Variational Gradient Descent for efficient sampling
We propose in this work RBM-SVGD, a stochastic version of Stein Variational Gradient Descent (SVGD) method for efficiently sampling from a given probability measure and thus useful for Bayesian inference.
Content-Based Brain Tumor Retrieval for MR Images Using Transfer Learning
It is necessary to design a feature extraction framework to reduce this gap without using handcrafted features by encoding/combining low-level and high-level features.
Weakly supervised segment annotation via expectation kernel density estimation
In this paper, we propose a voting scheme involving not only the definite negative instances but also the ambiguous positive instances to make use of the extra useful information in the weakly labelled positive bags.
Hybrid Self-Attention Network for Machine Translation
The encoder-decoder is the typical framework for Neural Machine Translation (NMT), and different structures have been developed for improving the translation performance.
Single Image Water Hazard Detection using FCN with Reflection Attention Units
Water bodies, such as puddles and flooded areas, on and off road pose significant risks to autonomous cars.
Goal-Oriented Visual Question Generation via Intermediate Rewards
Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge.
Double Path Networks for Sequence to Sequence Learning
In this work we propose Double Path Networks for Sequence to Sequence learning (DPN-S2S), which leverage the advantages of both models by using double path information fusion.
Stochastic modified equations for the asynchronous stochastic gradient descent
The resulting SME of Langevin type extracts more information about the ASGD dynamics and elucidates the relationship between different types of stochastic gradient algorithms.
Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks
Theoretical analysis of the approximation power of Butterfly-Net to the Fourier representation of input data shows that the error decays exponentially as the depth increases.
Stop memorizing: A data-dependent regularization framework for intrinsic pattern learning
Deep neural networks (DNNs) typically have enough capacity to fit random data by brute force even when conventional data-dependent regularizations focusing on the geometry of the features are imposed.
Scaling limit of the Stein variational gradient descent: the mean field regime
We study an interacting particle system in $\mathbf{R}^d$ motivated by Stein variational gradient descent [Q. Liu and D. Wang, NIPS 2016], a deterministic algorithm for sampling from a given probability density with unknown normalization.
Solving for high dimensional committor functions using artificial neural networks
In this note we propose a method based on artificial neural network to study the transition between states governed by stochastic processes.
Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards
Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge.
Kill Two Birds with One Stone: Weakly-Supervised Neural Network for Image Annotation and Tag Refinement
These comments can be a description of the image, or some objects, attributes, scenes in it, which are normally used as the user-provided tags.
Solving parametric PDE problems with artificial neural networks
The representability of such quantity using a neural-network can be justified by viewing the neural-network as performing time evolution to find the solutions to the PDE.
Numerical Analysis 65Nxx
Discontinuous Hamiltonian Monte Carlo for discrete parameters and discontinuous likelihoods
Hamiltonian Monte Carlo has emerged as a standard tool for posterior computation.
Computation
Multi-Label Image Classification with Regional Latent Semantic Dependencies
Recent state-of-the-art approaches to multi-label image classification exploit the label dependencies in an image, at global level, largely improving the labeling capacity.
Numerical scheme for a spatially inhomogeneous matrix-valued quantum Boltzmann equation
We develop an efficient algorithm for a spatially inhomogeneous matrix-valued quantum Boltzmann equation derived from the Hubbard model.
Computational Physics Mesoscale and Nanoscale Physics
