Search Results for author:
Found 71 papers, 13 papers with code
Prelimit Coupling and Steady-State Convergence of Constant-stepsize Nonsmooth Contractive SA
Motivated by Q-learning, we study nonsmooth contractive stochastic approximation (SA) with constant stepsize.
Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs
Our result is the first that is minimax optimal (up to log factors) in all parameters $S, A, H$ and $\epsilon$, improving on existing work that either assumes uniformly bounded mixing times for all policies or has suboptimal dependence on the parameters.
Entry-Specific Bounds for Low-Rank Matrix Completion under Highly Non-Uniform Sampling
Our bounds characterize the hardness of estimating each entry as a function of the localized sampling probabilities.
Unichain and Aperiodicity are Sufficient for Asymptotic Optimality of Average-Reward Restless Bandits
We consider the infinite-horizon, average-reward restless bandit problem in discrete time.
Effectiveness of Constant Stepsize in Markovian LSA and Statistical Inference
Our procedure leverages the fast mixing property of constant-stepsize LSA for better covariance estimation and employs Richardson-Romberg (RR) extrapolation to reduce the bias induced by constant stepsize and Markovian data.
Span-Based Optimal Sample Complexity for Average Reward MDPs
Our result is the first that is minimax optimal (up to log factors) in all parameters $S, A, H$ and $\varepsilon$, improving on existing work that either assumes uniformly bounded mixing times for all policies or has suboptimal dependence on the parameters.
GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation
Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their deployments on resource-constrained devices remain challenging due to high computational demands.
Ranked #185 on
Image Classification
on ImageNet
Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and Value
We study the game modification problem, where a benevolent game designer or a malevolent adversary modifies the reward function of a zero-sum Markov game so that a target deterministic or stochastic policy profile becomes the unique Markov perfect Nash equilibrium and has a value within a target range, in a way that minimizes the modification cost.
Understanding the Effects of Projectors in Knowledge Distillation
Interestingly, we discovered that even if the student and the teacher have the same feature dimensions, adding a projector still helps to improve the distillation performance.
Plug n' Play: Channel Shuffle Module for Enhancing Tiny Vision Transformers
Inspired by the channel shuffle design in ShuffleNetV2 \cite{ma2018shufflenet}, our module expands the feature channels of a tiny ViT and partitions the channels into two groups: the \textit{Attended} and \textit{Idle} groups.
No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling
By allowing the idle tokens to be re-selected in the following layers, IdleViT mitigates the negative impact of improper pruning in the early stages.
Towards Joint Modeling of Dialogue Response and Speech Synthesis based on Large Language Model
This paper explores the potential of constructing an AI spoken dialogue system that "thinks how to respond" and "thinks how to speak" simultaneously, which more closely aligns with the human speech production process compared to the current cascade pipeline of independent chatbot and Text-to-Speech (TTS) modules.
Clustering Without an Eigengap
Our gap-free clustering procedure also leads to improved algorithms for recursive clustering.
VISER: A Tractable Solution Concept for Games with Information Asymmetry
Many real-world games suffer from information asymmetry: one player is only aware of their own payoffs while the other player has the full game information.
Stochastic Methods in Variational Inequalities: Ergodicity, Bias and Refinements
Our work endeavors to elucidate and quantify the probabilistic structures intrinsic to these algorithms.
Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces
This latter objective is called stability and is especially important when the state space is unbounded, such that the states can be arbitrarily far from each other and the agent can drift far away from the desired states.
Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption
In both settings, our work is the first asymptotic optimality result that does not require UGAP.
Matrix Estimation for Offline Reinforcement Learning with Low-Rank Structure
We consider offline Reinforcement Learning (RL), where the agent does not interact with the environment and must rely on offline data collected using a behavior policy.
Improved Feature Distillation via Projector Ensemble
Motivated by the positive effect of the projector in feature distillation, we propose an ensemble of projectors to further improve the quality of student features.
Bias and Extrapolation in Markovian Linear Stochastic Approximation with Constant Stepsizes
We consider Linear Stochastic Approximation (LSA) with a constant stepsize and Markovian data.
Asymmetric Transfer Hashing with Adaptive Bipartite Graph Learning
Specifically, ATH characterizes the domain distribution gap by the discrepancy between two asymmetric hash functions, and minimizes the feature gap with the help of a novel adaptive bipartite graph constructed on cross-domain data.
Overcoming the Long Horizon Barrier for Sample-Efficient Reinforcement Learning with Latent Low-Rank Structure
The practicality of reinforcement learning algorithms has been limited due to poor scaling with respect to the problem size, as the sample complexity of learning an $\epsilon$-optimal policy is $\tilde{\Omega}\left(|S||A|H^3 / \epsilon^2\right)$ over worst case instances of an MDP with state space $S$, action space $A$, and horizon $H$.
Algorithmic Regularization in Model-free Overparametrized Asymmetric Matrix Factorization
We study the asymmetric matrix factorization problem under a natural nonconvex formulation with arbitrary overparametrization.
A Geometric Approach to $k$-means
This framework consists of alternating between the following two steps iteratively: (i) detect mis-specified clusters in a local solution and (ii) improve the current local solution by non-local operations.
Curriculum Disentangled Recommendation with Noisy Multi-feedback
However, learning such disentangled representations from multi-feedback data is challenging because i) multi-feedback is complex: there exist complex relations among different types of feedback (e. g., click, unclick, and dislike, etc) as well as various user intentions, and ii) multi-feedback is noisy: there exists noisy (useless) information both in features and labels, which may deteriorate the recommendation performance.
Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning
The exponential Bellman equation inspires us to develop a novel analysis of Bellman backup procedures in risk-sensitive RL algorithms, and further motivates the design of a novel exploration mechanism.
Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery
We study the robust recovery of a low-rank matrix from sparsely and grossly corrupted Gaussian measurements, with no prior knowledge on the intrinsic rank.
Deep Self-Adaptive Hashing for Image Retrieval
Secondly, we measure the priorities of data pairs with PIC and assign adaptive weights to them, which is relies on the assumption that more dissimilar data pairs contain more discriminative information for hash learning.
Curriculum Meta-Learning for Next POI Recommendation
Next point-of-interest (POI) recommendation is a hot research field where a recent emerging scenario, next POI to search recommendation, has been deployed in many online map services such as Baidu Maps.
MetaDelta: A Meta-Learning System for Few-shot Image Classification
Meta-learning aims at learning quickly on novel tasks with limited data by transferring generic experience learned from previous tasks.
Towards a Unified Quadrature Framework for Large-Scale Kernel Machines
In this paper, we develop a quadrature framework for large-scale kernel machines via a numerical integration representation.
A Survey on Curriculum Learning
We discuss works on curriculum learning within a general CL framework, elaborating on how to design a manually predefined curriculum or an automatic curriculum.
Local Minima Structures in Gaussian Mixture Models
As the objective function is non-convex, there can be multiple local minima that are not globally optimal, even for well-separated mixture models.
Low-rank matrix recovery with non-quadratic loss: projected gradient method and regularity projection oracle
Existing results for low-rank matrix recovery largely focus on quadratic loss, which enjoys favorable properties such as restricted strong convexity/smoothness (RSC/RSM) and well conditioning over all low rank matrices.
Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret
We study risk-sensitive reinforcement learning in episodic Markov decision processes with unknown transition kernels, where the goal is to optimize the total reward under the risk measure of exponential utility.
Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond
This survey may serve as a gentle introduction to this topic, and as a users' guide for practitioners interested in applying the representative algorithms and understanding theoretical results under various technical assumptions.
High-dimensional, multiscale online changepoint detection
We introduce a new method for high-dimensional, online changepoint detection in settings where a $p$-variate Gaussian data stream may undergo a change in mean.
Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium
In the offline setting, we control both players and aim to find the Nash Equilibrium by minimizing the duality gap.
Structures of Spurious Local Minima in $k$-means
Our theoretical results corroborate existing empirical observations and provide justification for several improved algorithms for $k$-means clustering.
Random Fourier Features via Fast Surrogate Leverage Weighted Sampling
In this paper, we propose a fast surrogate leverage weighted sampling strategy to generate refined random Fourier features for kernel approximation.
Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery
Compared to the max norm and the factored formulation of the nuclear norm, factor group-sparse regularizers are more efficient, accurate, and robust to the initial guess of rank.
Deep Supervised Hashing With Anchor Graph
Recently, a series of deep supervised hashing methods were proposed for binary code learning.
Global Convergence of Least Squares EM for Demixing Two Log-Concave Densities
This work studies the location estimation problem for a mixture of two rotation invariant log-concave densities.
Clustering Degree-Corrected Stochastic Block Model with Outliers
For the degree corrected stochastic block model in the presence of arbitrary or even adversarial outliers, we develop a convex-optimization-based clustering algorithm that includes a penalization term depending on the positive deviation of a node from the expected number of edges to other inliers.
Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence
The task of recovering a low-rank matrix from its noisy linear measurements plays a central role in computational science.
Achieving the Bayes Error Rate in Synchronization and Block Models by SDP, Robustly
We study the statistical performance of semidefinite programming (SDP) relaxations for clustering under random graph models.
Global Convergence of EM Algorithm for Mixtures of Two Component Linear Regression
Recent results established that EM enjoys global convergence for Gaussian Mixture Models.
Convex Relaxation Methods for Community Detection
We introduce some important theoretical techniques and results for establishing the consistency of convex community detection under various statistical models.
Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning
In this setting, the Byzantine machines may create fake local minima near a saddle point that is far away from any true local minimum, even when robust gradient estimators are used.
Tensor Robust Principal Component Analysis with A New Tensor Nuclear Norm
Equipped with the new tensor nuclear norm, we then solve the TRPCA problem by solving a convex program and provide the theoretical guarantee for the exact recovery.
Leave-one-out Approach for Matrix Completion: Primal and Dual Analysis
In this paper, we introduce a powerful technique based on Leave-one-out analysis to the study of low-rank matrix completion problems.
Hidden Integrality and Semi-random Robustness of SDP Relaxation for Sub-Gaussian Mixture Model
The error of the integer program, and hence that of the SDP, are further shown to decay exponentially in the signal-to-noise ratio.
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
In particular, these algorithms are shown to achieve order-optimal statistical error rates for strongly convex losses.
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.
Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization
In this work, we prove that under certain suitable assumptions, we can recover both the low-rank and the sparse components exactly by simply solving a convex program whose objective is a weighted combination of the tensor nuclear norm and the $\ell_1$-norm, i. e., $\min_{{\mathcal{L}},\ {\mathcal{E}}} \ \|{{\mathcal{L}}}\|_*+\lambda\|{{\mathcal{E}}}\|_1, \ \text{s. t.}
Exponential error rates of SDP for block models: Beyond Grothendieck's inequality
In this paper we consider the cluster estimation problem under the Stochastic Block Model.
Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent
The total computational complexity of our algorithm is of $O((Nd/m) \log N)$ at each working machine and $O(md + kd \log^3 N)$ at the central server, and the total communication cost is of $O(m d \log N)$.
Fast Algorithms for Robust PCA via Gradient Descent
For the partially observed case, we show the complexity of our algorithm is no more than $\mathcal{O}(r^4d \log d \log(1/\varepsilon))$.
Convexified Modularity Maximization for Degree-corrected Stochastic Block Models
We establish non-asymptotic theoretical guarantees for both approximate clustering and perfect clustering.
Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees
We provide a simple set of conditions under which projected gradient descent, when given a suitable initialization, converges geometrically to a statistically useful solution.
Clustering from Labels and Time-Varying Graphs
Our theoretical results cover and subsume a wide range of existing graph clustering results including planted partition, weighted clustering and partially observed graphs.
Statistical-Computational Tradeoffs in Planted Problems and Submatrix Localization with a Growing Number of Clusters and Submatrices
Of particular interest is the setting where the number of clusters/submatrices is allowed to grow unbounded with the problem size.
A Convex Formulation for Mixed Regression with Two Components: Minimax Optimal Rates
We consider the mixed regression problem with two components, under adversarial and stochastic noise.
Incoherence-Optimal Matrix Completion
We show that it is not necessary to assume joint incoherence, which is a standard but unintuitive and restrictive condition that is imposed by previous studies.
Completing Any Low-rank Matrix, Provably
Matrix completion, i. e., the exact and provable recovery of a low-rank matrix from a small subset of its elements, is currently only known to be possible if the matrix satisfies a restrictive structural constraint---known as {\em incoherence}---on its row and column spaces.
Detecting Overlapping Temporal Community Structure in Time-Evolving Networks
We present a principled approach for detecting overlapping temporal community structure in dynamic networks.
Clustering Sparse Graphs
We develop a new algorithm to cluster sparse unweighted graphs -- i. e. partition the nodes into disjoint clusters so that there is higher density within clusters, and low across clusters.
Improved Graph Clustering
We show that, in the classic stochastic block model setting, it outperforms existing methods by polynomial factors when the cluster size is allowed to have general scalings.
Orthogonal Matching Pursuit with Noisy and Missing Data: Low and High Dimensional Results
Many models for sparse regression typically assume that the covariates are known completely, and without noise.
Clustering Partially Observed Graphs via Convex Optimization
This paper considers the problem of clustering a partially observed unweighted graph---i. e., one where for some node pairs we know there is an edge between them, for some others we know there is no edge, and for the remaining we do not know whether or not there is an edge.
Matrix completion with column manipulation: Near-optimal sample-robustness-rank tradeoffs
Moreover, we show by an information-theoretic argument that our guarantees are nearly optimal in terms of the fraction of sampled entries on the authentic columns, the fraction of corrupted columns, and the rank of the underlying matrix.
