Search Results for author:
Found 70 papers, 15 papers with code
Accelerating Convergence of Score-Based Diffusion Models, Provably
Score-based diffusion models, while achieving remarkable empirical performance, often suffer from low sampling speed, due to extensive function evaluations needed during the sampling phase.
Towards a mathematical theory for consistency training in diffusion models
Consistency models, which were proposed to mitigate the high computational overhead during the sampling phase of diffusion models, facilitate single-step sampling while attaining state-of-the-art empirical performance.
EgoGen: An Egocentric Synthetic Data Generator
To address this challenge, we introduce EgoGen, a new synthetic data generator that can produce accurate and rich ground-truth training data for egocentric perception tasks.
A non-asymptotic distributional theory of approximate message passing for sparse and robust regression
Characterizing the distribution of high-dimensional statistical estimators is a challenging task, due to the breakdown of classical asymptotic theory in high dimension.
Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal
Visible watermarks, while instrumental in protecting image copyrights, frequently distort the underlying content, complicating tasks like scene interpretation and image editing.
Coupling Fairness and Pruning in a Single Run: a Bi-level Optimization Perspective
To address this, we define a fair pruning task where a sparse model is derived subject to fairness requirements.
One-Shot Open Affordance Learning with Foundation Models
We introduce One-shot Open Affordance Learning (OOAL), where a model is trained with just one example per base object category, but is expected to identify novel objects and affordances.
Watt For What: Rethinking Deep Learning's Energy-Performance Relationship
Deep learning models have revolutionized various fields, from image recognition to natural language processing, by achieving unprecedented levels of accuracy.
STGIN: Spatial-Temporal Graph Interaction Network for Large-scale POI Recommendation
Specifically, we construct subgraphs of spatial, temporal, spatial-temporal, and global views respectively to precisely characterize the user's interests in various contexts.
DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models
After detecting the artifact regions, we develop a finetune procedure to improve GAN-based SR models with a few samples, so that they can deal with similar types of artifacts in more unseen real data.
Referenceless User Controllable Semantic Image Synthesis
Despite recent progress in semantic image synthesis, complete control over image style remains a challenging problem.
Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models
Diffusion models, which convert noise into new data instances by learning to reverse a Markov diffusion process, have become a cornerstone in contemporary generative modeling.
Sharp high-probability sample complexities for policy evaluation with linear function approximation
This paper is concerned with the problem of policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes.
The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model
Assuming access to a generative model that draws samples based on the nominal MDP, we characterize the sample complexity of RMDPs when the uncertainty set is specified via either the total variation (TV) distance or $\chi^2$ divergence.
Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time
A crucial problem in reinforcement learning is learning the optimal policy.
Provable Identifiability of Two-Layer ReLU Neural Networks via LASSO Regularization
In this paper, the territory of LASSO is extended to two-layer ReLU neural networks, a fashionable and powerful nonlinear regression model.
Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning
This paper studies reward-agnostic exploration in reinforcement learning (RL) -- a scenario where the learner is unware of the reward functions during the exploration stage -- and designs an algorithm that improves over the state of the art.
LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding
A key step to acquire this skill is to identify what part of the object affords each action, which is called affordance grounding.
Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting
To reconcile such, we propose a novel method for high-quality and efficient video resolution upscaling tasks, which leverages the spatial-temporal information to accurately divide video into chunks, thus keeping the number of chunks as well as the model size to minimum.
Approximate message passing from random initialization with applications to $\mathbb{Z}_{2}$ synchronization
This paper is concerned with the problem of reconstructing an unknown rank-one matrix with prior structural information from noisy observations.
OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer
Omnidirectional images (ODIs) have obtained lots of research interest for immersive experiences.
Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods
Efficient computation of the optimal transport distance between two distributions serves as an algorithm subroutine that empowers various applications.
Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report
While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints.
Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors
We further qualitatively evaluate the effectiveness of our method on real images and demonstrate its generalizability towards interaction types and object categories.
Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model
This paper studies multi-agent reinforcement learning in Markov games, with the goal of learning Nash equilibria or coarse correlated equilibria (CCE) sample-optimally.
A Non-Asymptotic Framework for Approximate Message Passing in Spiked Models
As two concrete consequences of the proposed analysis recipe: (i) when solving $\mathbb{Z}_2$ synchronization, we predict the behavior of spectrally initialized AMP for up to $O\big(\frac{n}{\mathrm{poly}\log n}\big)$ iterations, showing that the algorithm succeeds without the need of a subsequent refinement stage (as conjectured recently by \citet{celentano2021local}); (ii) we characterize the non-asymptotic behavior of AMP in sparse PCA (in the spiked Wigner model) for a broad range of signal-to-noise ratio.
Real Image Restoration via Structure-preserving Complementarity Attention
Since convolutional neural networks perform well in learning generalizable image priors from large-scale data, these models have been widely used in image denoising tasks.
FaceFormer: Scale-aware Blind Face Restoration with Transformers
Blind face restoration usually encounters with diverse scale face inputs, especially in the real world.
AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos
This paper studies the problem of real-world video super-resolution (VSR) for animation videos, and reveals three key improvements for practical animation VSR.
Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games
This paper makes progress towards learning Nash equilibria in two-player zero-sum Markov games from offline data.
Model-based Reinforcement Learning
reinforcement-learning
+1
VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
Equipped with the VQ codebook as a facial detail dictionary and the parallel decoder design, the proposed VQFR can largely enhance the restored quality of facial details while keeping the fidelity to previous methods.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Settling the Sample Complexity of Model-Based Offline Reinforcement Learning
We demonstrate that the model-based (or "plug-in") approach achieves minimax-optimal sample complexity without burn-in cost for tabular Markov decision processes (MDPs).
The Efficacy of Pessimism in Asynchronous Q-Learning
This paper is concerned with the asynchronous form of Q-learning, which applies a stochastic approximation scheme to Markovian data samples.
Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
Offline or batch reinforcement learning seeks to learn a near-optimal policy using history data without active exploration of the environment.
SuperStyleNet: Deep Image Synthesis with Superpixel Based Style Encoder
First, we directly extract the style codes from the original image based on superpixels to consider local objects.
Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning
Achieving sample efficiency in online episodic reinforcement learning (RL) requires optimally balancing exploration and exploitation.
Provable Identifiability of ReLU Neural Networks via Lasso Regularization
In this paper, the territory of LASSO is extended to the neural network model, a fashionable and powerful nonlinear regression model.
In-depth Analysis of Durations of Discretionary Lane Changes on Freeway Under Varying Traffic Conditions
It was found that the heavy vehicle takes longer time to complete LC maneuver.
The Rate of Convergence of Variation-Constrained Deep Neural Networks
To the best of our knowledge, the rate of convergence of neural networks shown by existing works is bounded by at most the order of $n^{-1/4}$ for a sample size of $n$.
Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting
The current paper pertains to a scenario with value-based linear representation, which postulates the linear realizability of the optimal Q-function (also called the "linear $Q^{\star}$ problem").
Minimax Estimation of Linear Functions of Eigenvectors in the Face of Small Eigen-Gaps
Eigenvector perturbation analysis plays a vital role in various data science applications.
Adaptive Prototype Learning and Allocation for Few-Shot Segmentation
By integrating the SGC and GPA together, we propose the Adaptive Superpixel-guided Network (ASGNet), which is a lightweight model and adapts to object scale and shape variation.
Ranked #58 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
Softmax Policy Gradient Methods Can Take Exponential Time to Converge
The softmax policy gradient (PG) method, which performs gradient ascent under softmax policy parameterization, is arguably one of the de facto implementations of policy optimization in modern reinforcement learning.
Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis
This paper addresses these questions for the synchronous setting: (1) when $|\mathcal{A}|=1$ (so that Q-learning reduces to TD learning), we prove that the sample complexity of TD learning is minimax optimal and scales as $\frac{|\mathcal{S}|}{(1-\gamma)^3\varepsilon^2}$ (up to log factor); (2) when $|\mathcal{A}|\geq 2$, we settle the sample complexity of Q-learning to be on the order of $\frac{|\mathcal{S}||\mathcal{A}|}{(1-\gamma)^4\varepsilon^2}$ (up to log factor).
THE EFFICACY OF L1 REGULARIZATION IN NEURAL NETWORKS
A crucial problem in neural networks is to select the most appropriate number of hidden neurons and obtain tight statistical risk bounds.
The Efficacy of $L_1$ Regularization in Two-Layer Neural Networks
A crucial problem in neural networks is to select the most appropriate number of hidden neurons and obtain tight statistical risk bounds.
Edge and Identity Preserving Network for Face Super-Resolution
In this paper, we propose a novel Edge and Identity Preserving Network for Face SR Network, named as EIPNet, to minimize the distortion by utilizing a lightweight edge block and identity information.
Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction
Focusing on a $\gamma$-discounted MDP with state space $\mathcal{S}$ and action space $\mathcal{A}$, we demonstrate that the $\ell_{\infty}$-based sample complexity of classical asynchronous Q-learning --- namely, the number of samples needed to yield an entrywise $\varepsilon$-accurate estimate of the Q-function --- is at most on the order of $\frac{1}{\mu_{\min}(1-\gamma)^5\varepsilon^2}+ \frac{t_{mix}}{\mu_{\min}(1-\gamma)}$ up to some logarithmic factor, provided that a proper constant learning rate is adopted.
Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model
This paper is concerned with the sample efficiency of reinforcement learning, assuming access to a generative model (or simulator).
Model-based Reinforcement Learning
Reinforcement Learning (RL)
Nonconvex Low-Rank Tensor Completion from Noisy Data
We study a noisy tensor completion problem of broad practical interest, namely, the reconstruction of a low-rank tensor from highly incomplete and randomly corrupted observations of its entries.
Subspace Estimation from Unbalanced and Incomplete Data Matrices: $\ell_{2,\infty}$ Statistical Guarantees
This paper is concerned with estimating the column space of an unknown low-rank matrix $\boldsymbol{A}^{\star}\in\mathbb{R}^{d_{1}\times d_{2}}$, given noisy and partial observations of its entries.
Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training
We propose Unicoder-VL, a universal encoder that aims to learn joint representations of vision and language in a pre-training manner.
Ranked #5 on
Image-to-Text Retrieval
on MS COCO
(Recall@10 metric)
DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation
As a pixel-level prediction task, semantic segmentation needs large computational cost with enormous parameters to obtain high performance.
Theory of Spectral Method for Union of Subspaces-Based Random Geometry Graph
Spectral Method is a commonly used scheme to cluster data points lying close to Union of Subspaces by first constructing a Random Geometry Graph, called Subspace Clustering.
Compressed Subspace Learning Based on Canonical Angle Preserving Property
In this paper, we prove that random projection with the so-called Johnson-Lindenstrauss (JL) property approximately preserves canonical angles between subspaces with overwhelming probability.
Deep Reason: A Strong Baseline for Real-World Visual Reasoning
This paper presents a strong baseline for real-world visual reasoning (GQA), which achieves 60. 93% in GQA 2019 challenge and won the sixth place.
Unraveling the Veil of Subspace RIP Through Near-Isometry on Subspaces
Subspace Restricted Isometry Property, a newly-proposed concept, has proved to be a useful tool in analyzing the effect of dimensionality reduction algorithms on subspaces.
PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones.
Integrative Multi-View Reduced-Rank Regression: Bridging Group-Sparse and Low-Rank Models
Multi-view data have been routinely collected in various fields of science and engineering.
Rigorous Restricted Isometry Property of Low-Dimensional Subspaces
As an analogy to JL Lemma and RIP for sparse vectors, this work allows the use of random projections to reduce the ambient dimension with the theoretical guarantee that the distance between subspaces after compression is well preserved.
Linear Convergence of An Iterative Phase Retrieval Algorithm with Data Reuse
In this work, we study for the first time, without the independence assumption, the convergence behavior of the randomized Kaczmarz method for phase retrieval.
Image Super-Resolution Using Dense Skip Connections
In this study, we present a novel single-image super-resolution method by introducing dense skip connections in a very deep network.
Active Orthogonal Matching Pursuit for Sparse Subspace Clustering
In this letter, we propose a novel Active OMP-SSC, which improves clustering accuracy of OMP-SSC by adaptively updating data points and randomly dropping data points in the OMP process, while still enjoying the low computational complexity of greedy pursuit algorithms.
Structural Learning and Integrative Decomposition of Multi-View Data
We call this model SLIDE for Structural Learning and Integrative DEcomposition of multi-view data.
Restricted Isometry Property of Gaussian Random Projection for Finite Set of Subspaces
Dimension reduction plays an essential role when decreasing the complexity of solving large-scale problems.
Phase Transitions of Spectral Initialization for High-Dimensional Nonconvex Estimation
We study a spectral initialization method that serves a key role in recent work on estimating signals in nonconvex settings.
Supervised multiway factorization
We describe a likelihood-based latent variable representation of the CP factorization, in which the latent variables are informed by additional covariates.
Direction-Projection-Permutation for High Dimensional Hypothesis Tests
Motivated by the prevalence of high dimensional low sample size datasets in modern statistical applications, we propose a general nonparametric framework, Direction-Projection-Permutation (DiProPerm), for testing high dimensional hypotheses.
Methodology
