Search Results for author:
Found 74 papers, 17 papers with code
Prompt-prompted Mixture of Experts for Efficient LLM Generation
With the development of transformer-based large language models (LLMs), they have been applied to many fields due to their remarkable utility, but this comes at a considerable computational cost at deployment.
Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction
This work develops an algorithmic framework for employing score-based diffusion models as an expressive data prior in general nonlinear inverse problems.
Sample Complexity of Offline Distributionally Robust Linear Markov Decision Processes
In offline reinforcement learning (RL), the absence of active exploration calls for attention on the model robustness to tackle the sim-to-real gap, where the discrepancy between the simulated and deployed environments can significantly undermine the performance of the learned policy.
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.
Transformers Provably Learn Feature-Position Correlations in Masked Image Modeling
Masked image modeling (MIM), which predicts randomly masked patches from unmasked ones, has emerged as a promising approach in self-supervised vision pretraining.
Counterfactual Generation with Identifiability Guarantees
In this work, we tackle the domain-varying dependence between the content and the style variables inherent in the counterfactual generation task.
Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference
Many computational factors limit broader deployment of large language models.
Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices
Our sample complexity analysis reveals that, with appropriately chosen parameters and synchronization schedules, FedLCB-Q achieves linear speedup in terms of the number of agents without requiring high-quality datasets at individual agents, as long as the local datasets collectively cover the state-action space visited by the optimal policy, highlighting the power of collaboration in the federated setting.
Beyond Expectations: Learning with Stochastic Dominance Made Practical
Stochastic dominance models risk-averse preferences for decision making with uncertain outcomes, which naturally captures the intrinsic structure of the underlying uncertainty, in contrast to simply resorting to the expectations.
Communication-Efficient Federated Optimization over Semi-Decentralized Networks
In large-scale federated and decentralized learning, communication efficiency is one of the most challenging bottlenecks.
Federated Natural Policy Gradient Methods for Multi-task Reinforcement Learning
Federated reinforcement learning (RL) enables collaborative decision making of multiple distributed agents without sharing local data trajectories.
Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression
To our knowledge, Power-EF is the first distributed and compressed SGD algorithm that provably escapes saddle points in heterogeneous FL without any data homogeneity assumptions.
Provably Accelerating Ill-Conditioned Low-rank Estimation via Scaled Gradient Descent, Even with Overparameterization
Many problems encountered in science and engineering can be formulated as estimating a low-rank object (e. g., matrices and tensors) from incomplete, and possibly corrupted, linear measurements.
Global Convergence of Policy Gradient Methods in Reinforcement Learning, Games and Control
Policy gradient methods, where one searches for the policy of interest by maximizing the value functions using first-order information, become increasingly popular for sequential decision making in reinforcement learning, games, and control.
A Multi-Token Coordinate Descent Method for Semi-Decentralized Vertical Federated Learning
Communication efficiency is a major challenge in federated learning (FL).
A Lightweight Transformer for Faster and Robust EBSD Data Collection
Three dimensional electron back-scattered diffraction (EBSD) microscopy is a critical tool in many applications in materials science, yet its data quality can fluctuate greatly during the arduous collection process, particularly via serial-sectioning.
Offline Reinforcement Learning with On-Policy Q-Function Regularization
In this work, we propose to regularize towards the Q-function of the behavior policy instead of the behavior policy itself, under the premise that the Q-function can be estimated more reliably and easily by a SARSA-style estimate and handles the extrapolation error more straightforwardly.
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.
Understanding Masked Autoencoders via Hierarchical Latent Variable Models
In this work, we formally characterize and justify existing empirical insights and provide theoretical guarantees of MAE.
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.
The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond
When the data used for reinforcement learning (RL) are collected by multiple agents in a distributed manner, federated versions of RL algorithms allow collaborative learning without the need for agents to share their local data.
Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression
Achieving communication efficiency in decentralized machine learning has been attracting significant attention, with communication compression recognized as an effective technique in algorithm design.
The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing
We propose $\textsf{ScaledGD($\lambda$)}$, a preconditioned gradient descent method to tackle the low-rank matrix sensing problem when the true rank is unknown, and when the matrix is possibly ill-conditioned.
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.
Deep Unfolded Tensor Robust PCA with Self-supervised Learning
Tensor robust principal component analysis (RPCA), which seeks to separate a low-rank tensor from its sparse corruptions, has been crucial in data science and machine learning where tensor structures are becoming more prevalent.
Asynchronous Gradient Play in Zero-Sum Multi-agent Games
Moving beyond, we demonstrate entropy-regularized OMWU -- by adopting two-timescale learning rates in a delay-aware manner -- enjoys faster last-iterate convergence under fixed delays, and continues to converge provably even when the delays are arbitrarily bounded in an average-iterate manner.
Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games
Multi-Agent Reinforcement Learning (MARL) -- where multiple agents learn to interact in a shared dynamic environment -- permeates across a wide range of critical applications.
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.
Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity
This paper concerns the central issues of model robustness and sample efficiency in offline reinforcement learning (RL), which aims to learn to perform decision making from history data without active exploration.
SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression
We then propose a unified framework SoteriaFL for private federated learning, which accommodates a general family of local gradient estimators including popular stochastic variance-reduced gradient methods and the state-of-the-art shifted compression scheme.
Fast and Provable Tensor Robust Principal Component Analysis via Scaled Gradient Descent
An increasing number of data science and machine learning problems rely on computation with tensors, which better capture the multi-way relationships and interactions of data than matrices.
Independent Natural Policy Gradient Methods for Potential Games: Finite-time Global Convergence with Entropy Regularization
We show that the proposed method converges to the quantal response equilibrium (QRE) -- the equilibrium to the entropy-regularized game -- at a sublinear rate, which is independent of the size of the action space and grows at most sublinearly with the number of agents.
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).
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.
BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression
Communication efficiency has been widely recognized as the bottleneck for large-scale decentralized machine learning applications in multi-agent or federated environments.
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.
DESTRESS: Computation-Optimal and Communication-Efficient Decentralized Nonconvex Finite-Sum Optimization
Emerging applications in multi-agent environments such as internet-of-things, networked sensing, autonomous systems and federated learning, call for decentralized algorithms for finite-sum optimizations that are resource-efficient in terms of both computation and communication.
Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization
Motivated by the algorithmic role of entropy regularization in single-agent reinforcement learning and game theory, we develop provably efficient extragradient methods to find the quantal response equilibrium (QRE) -- which are solutions to zero-sum two-player matrix games with entropy regularization -- at a linear rate.
Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence
These can often be accounted for via regularized RL, which augments the target value function with a structure-promoting regularizer.
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").
Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Estimation from Incomplete Measurements
Tensors, which provide a powerful and flexible model for representing multi-attribute data and multi-way interactions, play an indispensable role in modern data science across various fields in science and engineering.
A Large Collection of Real-world Pediatric Sleep Studies
Despite being crucial to health and quality of life, sleep -- especially pediatric sleep -- is not yet well understood.
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).
Beyond Procrustes: Balancing-Free Gradient Descent for Asymmetric Low-Rank Matrix Sensing
Low-rank matrix estimation plays a central role in various applications across science and engineering.
Spectral Methods for Data Science: A Statistical Perspective
While the studies of spectral methods can be traced back to classical matrix perturbation theory and methods of moments, the past decade has witnessed tremendous theoretical advances in demystifying their efficacy through the lens of statistical modeling, with the aid of non-asymptotic random matrix theory.
Low-Rank Matrix Recovery with Scaled Subgradient Methods: Fast and Robust Convergence Without the Condition Number
Many problems in data science can be treated as estimating a low-rank matrix from highly incomplete, sometimes even corrupted, observations.
Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization
This class of methods is often applied in conjunction with entropy regularization -- an algorithmic scheme that encourages exploration -- and is closely related to soft policy iteration and trust region policy optimization.
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)
Accelerating Ill-Conditioned Low-Rank Matrix Estimation via Scaled Gradient Descent
Low-rank matrix estimation is a canonical problem that finds numerous applications in signal processing, machine learning and imaging science.
Manifold Gradient Descent Solves Multi-Channel Sparse Blind Deconvolution Provably and Efficiently
Multi-channel sparse blind deconvolution, or convolutional sparse coding, refers to the problem of learning an unknown filter by observing its circulant convolutions with multiple input signals that are sparse.
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.
Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reduction
There is growing interest in large-scale machine learning and optimization over decentralized networks, e. g. in the context of multi-agent learning and federated learning.
Vector-Valued Graph Trend Filtering with Non-Convex Penalties
This work studies the denoising of piecewise smooth graph signals that exhibit inhomogeneous levels of smoothness over a graph, where the value at each node can be vector-valued.
Convergence of Distributed Stochastic Variance Reduced Methods without Sampling Extra Data
Our theory captures how the convergence of distributed algorithms behaves as the number of machines and the size of local data vary.
Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization
This paper studies noisy low-rank matrix completion: given partial and noisy entries of a large low-rank matrix, the goal is to estimate the underlying matrix faithfully and efficiently.
Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
Substantial progress has been made recently on developing provably accurate and efficient algorithms for low-rank matrix factorization via nonconvex optimization.
Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval and Matrix Completion
Focusing on two statistical estimation problems, i. e. solving random quadratic systems of equations and low-rank matrix completion, we establish that gradient descent achieves near-optimal statistical and computational guarantees without explicit regularization.
Streaming PCA and Subspace Tracking: The Missing Data Case
This survey article reviews a variety of classical and recent algorithms for solving this problem with low computational and memory complexities, particularly those applicable in the big data regime with missing data.
Gradient Descent with Random Initialization: Fast Global Convergence for Nonconvex Phase Retrieval
This paper considers the problem of solving systems of quadratic equations, namely, recovering an object of interest $\mathbf{x}^{\natural}\in\mathbb{R}^{n}$ from $m$ quadratic equations/samples $y_{i}=(\mathbf{a}_{i}^{\top}\mathbf{x}^{\natural})^{2}$, $1\leq i\leq m$.
Harnessing Structures in Big Data via Guaranteed Low-Rank Matrix Estimation
Low-rank modeling plays a pivotal role in signal processing and machine learning, with applications ranging from collaborative filtering, video surveillance, medical imaging, to dimensionality reduction and adaptive filtering.
Guaranteed Recovery of One-Hidden-Layer Neural Networks via Cross Entropy
We prove that with Gaussian inputs, the empirical risk based on cross entropy exhibits strong convexity and smoothness {\em uniformly} in a local neighborhood of the ground truth, as soon as the sample complexity is sufficiently large.
Nonconvex Matrix Factorization from Rank-One Measurements
We consider the problem of recovering low-rank matrices from random rank-one measurements, which spans numerous applications including covariance sketching, phase retrieval, quantum state tomography, and learning shallow polynomial neural networks, among others.
Learning Latent Features with Pairwise Penalties in Low-Rank Matrix Completion
Low-rank matrix completion has achieved great success in many real-world data applications.
Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution
Recent years have seen a flurry of activities in designing provably efficient nonconvex procedures for solving statistical estimation problems.
Nonconvex Low-Rank Matrix Recovery with Arbitrary Outliers via Median-Truncated Gradient Descent
Recent work has demonstrated the effectiveness of gradient descent for directly recovering the factors of low-rank matrices from random linear measurements in a globally convergent manner when initialized properly.
Reshaped Wirtinger Flow and Incremental Algorithm for Solving Quadratic System of Equations
We further develop the incremental (stochastic) reshaped Wirtinger flow (IRWF) and show that IRWF converges linearly to the true signal.
Median-Truncated Nonconvex Approach for Phase Retrieval with Outliers
This paper investigates the phase retrieval problem, which aims to recover a signal from the magnitudes of its linear measurements.
Subspace Learning From Bits
Networked sensing, where the goal is to perform complex inference using a large number of inexpensive and decentralized sensors, has become an increasingly attractive research topic due to its applications in wireless sensor networks and internet-of-things.
Exact and Stable Covariance Estimation from Quadratic Sampling via Convex Programming
Our method admits universally accurate covariance estimation in the absence of noise, as soon as the number of measurements exceeds the information theoretic limits.
Robust Spectral Compressed Sensing via Structured Matrix Completion
The paper explores the problem of \emph{spectral compressed sensing}, which aims to recover a spectrally sparse signal from a small random subset of its $n$ time domain samples.
Spectral Compressed Sensing via Structured Matrix Completion
The paper studies the problem of recovering a spectrally sparse object from a small number of time domain samples.
