Search Results for author: Yuxin Chen

Found 125 papers, 12 papers with code

On Generative Agents in Recommendation

1 code implementation16 Oct 2023 An Zhang, Leheng Sheng, Yuxin Chen, Hao Li, Yang Deng, Xiang Wang, Tat-Seng Chua

Recommender systems are the cornerstone of today's information dissemination, yet a disconnect between offline metrics and online performance greatly hinders their development.

Collaborative Filtering Movie Recommendation +1

Rethinking Explainability as a Dialogue: A Practitioner's Perspective

1 code implementation3 Feb 2022 Himabindu Lakkaraju, Dylan Slack, Yuxin Chen, Chenhao Tan, Sameer Singh

Overall, we hope our work serves as a starting place for researchers and engineers to design interactive explainability systems.

BIG-bench Machine Learning

Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reduction

1 code implementation12 Sep 2019 Boyue Li, Shicong Cen, Yuxin Chen, Yuejie Chi

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.

Distributed Optimization Federated Learning

Understanding Bias in Anomaly Detection: A Semi-Supervised View with PAC Guarantees

1 code implementation1 Jan 2021 Ziyu Ye, Yuxin Chen, Haitao Zheng

Given two different anomaly score functions, we formally define their difference in performance as the relative scoring bias of the anomaly detectors.

Semi-supervised Anomaly Detection Supervised Anomaly Detection +1

Understanding the Effect of Bias in Deep Anomaly Detection

1 code implementation16 May 2021 Ziyu Ye, Yuxin Chen, Haitao Zheng

We also provide an extensive empirical study on how a biased training anomaly set affects the anomaly score function and therefore the detection performance on different anomaly classes.

Anomaly Detection

Learning Human-Compatible Representations for Case-Based Decision Support

1 code implementation6 Mar 2023 Han Liu, Yizhou Tian, Chacha Chen, Shi Feng, Yuxin Chen, Chenhao Tan

Despite the promising performance of supervised learning, representations learned by supervised models may not align well with human intuitions: what models consider as similar examples can be perceived as distinct by humans.

Classification Decision Making +1

Et Tu Alexa? When Commodity WiFi Devices Turn into Adversarial Motion Sensors

1 code implementation23 Oct 2018 Yanzi Zhu, Zhujun Xiao, Yuxin Chen, Zhijing Li, Max Liu, Ben Y. Zhao, Haitao Zheng

Our work demonstrates a new set of silent reconnaissance attacks, which leverages the presence of commodity WiFi devices to track users inside private homes and offices, without compromising any WiFi network, data packets, or devices.

Cryptography and Security

Active Policy Improvement from Multiple Black-box Oracles

1 code implementation17 Jun 2023 Xuefeng Liu, Takuma Yoneda, Chaoqi Wang, Matthew R. Walter, Yuxin Chen

We introduce MAPS and MAPS-SE, a class of policy improvement algorithms that perform imitation learning from multiple suboptimal oracles.

Imitation Learning Reinforcement Learning (RL)

Teaching Multiple Concepts to a Forgetful Learner

no code implementations NeurIPS 2019 Anette Hunziker, Yuxin Chen, Oisin Mac Aodha, Manuel Gomez Rodriguez, Andreas Krause, Pietro Perona, Yisong Yue, Adish Singla

Our framework is both generic, allowing the design of teaching schedules for different memory models, and also interactive, allowing the teacher to adapt the schedule to the underlying forgetting mechanisms of the learner.

Scheduling

Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners

no code implementations NeurIPS 2018 Yuxin Chen, Adish Singla, Oisin Mac Aodha, Pietro Perona, Yisong Yue

We highlight that adaptivity does not speed up the teaching process when considering existing models of version space learners, such as "worst-case" (the learner picks the next hypothesis randomly from the version space) and "preference-based" (the learner picks hypothesis according to some global preference).

Gradient Descent with Random Initialization: Fast Global Convergence for Nonconvex Phase Retrieval

no code implementations21 Mar 2018 Yuxin Chen, Yuejie Chi, Jianqing Fan, Cong Ma

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 $y_{i}=(\mathbf{a}_{i}^{\top}\mathbf{x}^{\natural})^{2}$, $1\leq i\leq m$.

Retrieval

Nonconvex Matrix Factorization from Rank-One Measurements

no code implementations17 Feb 2018 Yuanxin Li, Cong Ma, Yuxin Chen, Yuejie Chi

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.

Quantum State Tomography Retrieval

The Projected Power Method: An Efficient Algorithm for Joint Alignment from Pairwise Differences

no code implementations19 Sep 2016 Yuxin Chen, Emmanuel Candes

We prove that for a broad class of statistical models, the proposed projected power method makes no error---and hence converges to the maximum likelihood estimate---in a suitable regime.

Spectral Method and Regularized MLE Are Both Optimal for Top-$K$ Ranking

no code implementations31 Jul 2017 Yuxin Chen, Jianqing Fan, Cong Ma, Kaizheng Wang

This paper is concerned with the problem of top-$K$ ranking from pairwise comparisons.

Efficient Online Learning for Optimizing Value of Information: Theory and Application to Interactive Troubleshooting

no code implementations16 Mar 2017 Yuxin Chen, Jean-Michel Renders, Morteza Haghir Chehreghani, Andreas Krause

We consider the optimal value of information (VoI) problem, where the goal is to sequentially select a set of tests with a minimal cost, so that one can efficiently make the best decision based on the observed outcomes.

The Likelihood Ratio Test in High-Dimensional Logistic Regression Is Asymptotically a Rescaled Chi-Square

no code implementations5 Jun 2017 Pragya Sur, Yuxin Chen, Emmanuel J. Candès

When used for the purpose of statistical inference, logistic models produce p-values for the regression coefficients by using an approximation to the distribution of the likelihood-ratio test.

regression

Near-optimal Bayesian Active Learning with Correlated and Noisy Tests

no code implementations24 May 2016 Yuxin Chen, S. Hamed Hassani, Andreas Krause

We consider the Bayesian active learning and experimental design problem, where the goal is to learn the value of some unknown target variable through a sequence of informative, noisy tests.

Active Learning Experimental Design

Community Recovery in Graphs with Locality

no code implementations11 Feb 2016 Yuxin Chen, Govinda Kamath, Changho Suh, David Tse

Motivated by applications in domains such as social networks and computational biology, we study the problem of community recovery in graphs with locality.

Information Recovery from Pairwise Measurements

no code implementations6 Apr 2015 Yuxin Chen, Changho Suh, Andrea J. Goldsmith

In particular, our results isolate a family of \emph{minimum} \emph{channel divergence measures} to characterize the degree of measurement corruption, which together with the size of the minimum cut of $\mathcal{G}$ dictates the feasibility of exact information recovery.

Stochastic Block Model

Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems

no code implementations NeurIPS 2015 Yuxin Chen, Emmanuel J. Candes

We complement our theoretical study with numerical examples showing that solving random quadratic systems is both computationally and statistically not much harder than solving linear systems of the same size---hence the title of this paper.

Spectral MLE: Top-$K$ Rank Aggregation from Pairwise Comparisons

no code implementations27 Apr 2015 Yuxin Chen, Changho Suh

To approach this minimax limit, we propose a nearly linear-time ranking scheme, called \emph{Spectral MLE}, that returns the indices of the top-$K$ items in accordance to a careful score estimate.

Exact and Stable Covariance Estimation from Quadratic Sampling via Convex Programming

no code implementations2 Oct 2013 Yuxin Chen, Yuejie Chi, Andrea Goldsmith

Our method admits universally accurate covariance estimation in the absence of noise, as soon as the number of measurements exceeds the information theoretic limits.

Retrieval

Robust Spectral Compressed Sensing via Structured Matrix Completion

no code implementations30 Apr 2013 Yuxin Chen, Yuejie Chi

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.

Matrix Completion Super-Resolution

Scalable Semidefinite Relaxation for Maximum A Posterior Estimation

no code implementations19 May 2014 Qixing Huang, Yuxin Chen, Leonidas Guibas

Maximum a posteriori (MAP) inference over discrete Markov random fields is a fundamental task spanning a wide spectrum of real-world applications, which is known to be NP-hard for general graphs.

Near-Optimal Joint Object Matching via Convex Relaxation

no code implementations6 Feb 2014 Yuxin Chen, Leonidas J. Guibas, Qi-Xing Huang

Joint matching over a collection of objects aims at aggregating information from a large collection of similar instances (e. g. images, graphs, shapes) to improve maps between pairs of them.

Object

Spectral Compressed Sensing via Structured Matrix Completion

no code implementations16 Apr 2013 Yuxin Chen, Yuejie Chi

The paper studies the problem of recovering a spectrally sparse object from a small number of time domain samples.

Matrix Completion Super-Resolution

Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview

no code implementations25 Sep 2018 Yuejie Chi, Yue M. Lu, Yuxin Chen

Substantial progress has been made recently on developing provably accurate and efficient algorithms for low-rank matrix factorization via nonconvex optimization.

Matrix Completion Retrieval

Addressing Training Bias via Automated Image Annotation

no code implementations22 Sep 2018 Zhujun Xiao, Yanzi Zhu, Yuxin Chen, Ben Y. Zhao, Junchen Jiang, Hai-Tao Zheng

Build accurate DNN models requires training on large labeled, context specific datasets, especially those matching the target scenario.

A General Framework for Multi-fidelity Bayesian Optimization with Gaussian Processes

no code implementations2 Nov 2018 Jialin Song, Yuxin Chen, Yisong Yue

How can we efficiently gather information to optimize an unknown function, when presented with multiple, mutually dependent information sources with different costs?

Bayesian Optimization Gaussian Processes

Optimizing Photonic Nanostructures via Multi-fidelity Gaussian Processes

no code implementations15 Nov 2018 Jialin Song, Yury S. Tokpanov, Yuxin Chen, Dagny Fleischman, Kate T. Fountaine, Harry A. Atwater, Yisong Yue

We apply numerical methods in combination with finite-difference-time-domain (FDTD) simulations to optimize transmission properties of plasmonic mirror color filters using a multi-objective figure of merit over a five-dimensional parameter space by utilizing novel multi-fidelity Gaussian processes approach.

Gaussian Processes

Asymmetry Helps: Eigenvalue and Eigenvector Analyses of Asymmetrically Perturbed Low-Rank Matrices

no code implementations30 Nov 2018 Yuxin Chen, Chen Cheng, Jianqing Fan

The aim is to estimate the leading eigenvalue and eigenvector of $\mathbf{M}^{\star}$.

Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval and Matrix Completion

no code implementations ICML 2018 Cong Ma, Kaizheng Wang, Yuejie Chi, Yuxin Chen

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.

Low-Rank Matrix Completion Retrieval

Trip Prediction by Leveraging Trip Histories from Neighboring Users

no code implementations25 Dec 2018 Yuxin Chen, Morteza Haghir Chehreghani

We propose a novel approach for trip prediction by analyzing user's trip histories.

A One-Class Support Vector Machine Calibration Method for Time Series Change Point Detection

no code implementations18 Feb 2019 Baihong Jin, Yuxin Chen, Dan Li, Kameshwar Poolla, Alberto Sangiovanni-Vincentelli

The One-Class Support Vector Machine (OC-SVM) is a popular machine learning model for anomaly detection and hence could be used for identifying change points; however, it is sometimes difficult to obtain a good OC-SVM model that can be used on sensor measurement time series to identify the change points in system health status.

Anomaly Detection Change Point Detection +2

Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization

no code implementations20 Feb 2019 Yuxin Chen, Yuejie Chi, Jianqing Fan, Cong Ma, Yuling Yan

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.

Low-Rank Matrix Completion

Batched Stochastic Bayesian Optimization via Combinatorial Constraints Design

no code implementations17 Apr 2019 Kevin K. Yang, Yuxin Chen, Alycia Lee, Yisong Yue

Importantly, we show that our objective function can be efficiently decomposed as a difference of submodular functions (DS), which allows us to employ DS optimization tools to greedily identify sets of constraints that increase the likelihood of finding items with high utility.

Bayesian Optimization Experimental Design

Inference and Uncertainty Quantification for Noisy Matrix Completion

no code implementations10 Jun 2019 Yuxin Chen, Jianqing Fan, Cong Ma, Yuling Yan

As a byproduct, we obtain a sharp characterization of the estimation accuracy of our de-biased estimators, which, to the best of our knowledge, are the first tractable algorithms that provably achieve full statistical efficiency (including the preconstant).

Matrix Completion Uncertainty Quantification +1

An Encoder-Decoder Based Approach for Anomaly Detection with Application in Additive Manufacturing

no code implementations26 Jul 2019 Baihong Jin, Yingshui Tan, Alexander Nettekoven, Yuxin Chen, Ufuk Topcu, Yisong Yue, Alberto Sangiovanni Vincentelli

We show that the encoder-decoder model is able to identify the injected anomalies in a modern manufacturing process in an unsupervised fashion.

Anomaly Detection

Subspace Estimation from Unbalanced and Incomplete Data Matrices: $\ell_{2,\infty}$ Statistical Guarantees

no code implementations9 Oct 2019 Changxiao Cai, Gen Li, Yuejie Chi, H. Vincent Poor, Yuxin Chen

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.

Preference-Based Batch and Sequential Teaching: Towards a Unified View of Models

no code implementations NeurIPS 2019 Farnam Mansouri, Yuxin Chen, Ara Vartanian, Xiaojin Zhu, Adish Singla

In our framework, each function $\sigma \in \Sigma$ induces a teacher-learner pair with teaching complexity as $\TD(\sigma)$.

Landmark Ordinal Embedding

no code implementations NeurIPS 2019 Nikhil Ghosh, Yuxin Chen, Yisong Yue

In this paper, we aim to learn a low-dimensional Euclidean representation from a set of constraints of the form "item j is closer to item i than item k".

Computational Efficiency

Nonconvex Low-Rank Tensor Completion from Noisy Data

no code implementations NeurIPS 2019 Changxiao Cai, Gen Li, H. Vincent Poor, Yuxin Chen

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.

Tackling small eigen-gaps: Fine-grained eigenvector estimation and inference under heteroscedastic noise

no code implementations14 Jan 2020 Chen Cheng, Yuting Wei, Yuxin Chen

This paper aims to address two fundamental challenges arising in eigenvector estimation and inference for a low-rank matrix from noisy observations: (1) how to estimate an unknown eigenvector when the eigen-gap (i. e. the spacing between the associated eigenvalue and the rest of the spectrum) is particularly small; (2) how to perform estimation and inference on linear functionals of an eigenvector -- a sort of "fine-grained" statistical reasoning that goes far beyond the usual $\ell_2$ analysis.

Uncertainty Quantification

Bridging Convex and Nonconvex Optimization in Robust PCA: Noise, Outliers, and Missing Data

no code implementations15 Jan 2020 Yuxin Chen, Jianqing Fan, Cong Ma, Yuling Yan

This paper delivers improved theoretical guarantees for the convex programming approach in low-rank matrix estimation, in the presence of (1) random noise, (2) gross sparse outliers, and (3) missing data.

Adaptive Teaching of Temporal Logic Formulas to Learners with Preferences

no code implementations27 Jan 2020 Zhe Xu, Yuxin Chen, Ufuk Topcu

In the context of teaching temporal logic formulas, an exhaustive search even for a myopic solution takes exponential time (with respect to the time span of the task).

An Online Learning Framework for Energy-Efficient Navigation of Electric Vehicles

no code implementations3 Mar 2020 Niklas Åkerblom, Yuxin Chen, Morteza Haghir Chehreghani

In order to learn the model parameters, we develop an online learning framework and investigate several exploration strategies such as Thompson Sampling and Upper Confidence Bound.

Navigate Thompson Sampling

A Financial Service Chatbot based on Deep Bidirectional Transformers

no code implementations17 Feb 2020 Shi Yu, Yuxin Chen, Hussain Zaidi

Our main novel contribution is the discussion about uncertainty measure for BERT, where three different approaches are systematically compared on real problems.

Chatbot intent-classification +3

Understanding the Power and Limitations of Teaching with Imperfect Knowledge

no code implementations21 Mar 2020 Rati Devidze, Farnam Mansouri, Luis Haug, Yuxin Chen, Adish Singla

Machine teaching studies the interaction between a teacher and a student/learner where the teacher selects training examples for the learner to learn a specific task.

Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction

no code implementations NeurIPS 2020 Gen Li, Yuting Wei, Yuejie Chi, Yuantao Gu, Yuxin Chen

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.

Q-Learning

Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality

no code implementations ICML 2020 Changxiao Cai, H. Vincent Poor, Yuxin Chen

Furthermore, our findings unveil the statistical optimality of nonconvex tensor completion: it attains un-improvable $\ell_{2}$ accuracy -- including both the rates and the pre-constants -- when estimating both the unknown tensor and the underlying tensor factors.

Uncertainty Quantification valid

Average-case Complexity of Teaching Convex Polytopes via Halfspace Queries

no code implementations25 Jun 2020 Akash Kumar, Adish Singla, Yisong Yue, Yuxin Chen

We investigate the average teaching complexity of the task, i. e., the minimal number of samples (halfspace queries) required by a teacher to help a version-space learner in locating a randomly selected target.

Are Ensemble Classifiers Powerful Enough for the Detection and Diagnosis of Intermediate-Severity Faults?

no code implementations7 Jul 2020 Baihong Jin, Yingshui Tan, Yuxin Chen, Kameshwar Poolla, Alberto Sangiovanni Vincentelli

Intermediate-Severity (IS) faults present milder symptoms compared to severe faults, and are more difficult to detect and diagnose due to their close resemblance to normal operating conditions.

Fault Detection

Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization

no code implementations13 Jul 2020 Shicong Cen, Chen Cheng, Yuxin Chen, Yuting Wei, Yuejie Chi

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.

Policy Gradient Methods

Convex and Nonconvex Optimization Are Both Minimax-Optimal for Noisy Blind Deconvolution under Random Designs

no code implementations4 Aug 2020 Yuxin Chen, Jianqing Fan, Bingyan Wang, Yuling Yan

We investigate the effectiveness of convex relaxation and nonconvex optimization in solving bilinear systems of equations under two different designs (i. e.$~$a sort of random Fourier design and Gaussian design).

Using Ensemble Classifiers to Detect Incipient Anomalies

no code implementations20 Aug 2020 Baihong Jin, Yingshui Tan, Albert Liu, Xiangyu Yue, Yuxin Chen, Alberto Sangiovanni Vincentelli

Incipient anomalies present milder symptoms compared to severe ones, and are more difficult to detect and diagnose due to their close resemblance to normal operating conditions.

Anomaly Detection Ensemble Learning

Learning Mixtures of Low-Rank Models

no code implementations23 Sep 2020 Yanxi Chen, Cong Ma, H. Vincent Poor, Yuxin Chen

We study the problem of learning mixtures of low-rank models, i. e. reconstructing multiple low-rank matrices from unlabelled linear measurements of each.

Learning to Make Decisions via Submodular Regularization

no code implementations ICLR 2021 Ayya Alieva, Aiden Aceves, Jialin Song, Stephen Mayo, Yisong Yue, Yuxin Chen

In particular, we focus on a class of combinatorial problems that can be solved via submodular maximization (either directly on the objective function or via submodular surrogates).

Active Learning Bayesian Optimization +2

Learning Collision-free Latent Space for Bayesian Optimization

no code implementations1 Jan 2021 Fengxue Zhang, Yair Altas, Louise Fan, Kaustubh Vinchure, Brian Nord, Yuxin Chen

To address this issue, we propose Collision-Free Latent Space Optimization (CoFLO), which employs a novel regularizer to reduce the collision in the learned latent space and encourage the mapping from the latent space to objective value to be Lipschitz continuous.

Bayesian Optimization Experimental Design

Preference-Based Batch and Sequential Teaching

no code implementations17 Oct 2020 Farnam Mansouri, Yuxin Chen, Ara Vartanian, Xiaojin Zhu, Adish Singla

We analyze several properties of the teaching complexity parameter $TD(\sigma)$ associated with different families of the preference functions, e. g., comparison to the VC dimension of the hypothesis class and additivity/sub-additivity of $TD(\sigma)$ over disjoint domains.

The Teaching Dimension of Kernel Perceptron

no code implementations27 Oct 2020 Akash Kumar, Hanqi Zhang, Adish Singla, Yuxin Chen

As a warm-up, we show that the teaching complexity is $\Theta(d)$ for the exact teaching of linear perceptrons in $\mathbb{R}^d$, and $\Theta(d^k)$ for kernel perceptron with a polynomial kernel of order $k$.

Spectral Methods for Data Science: A Statistical Perspective

no code implementations15 Dec 2020 Yuxin Chen, Yuejie Chi, Jianqing Fan, Cong Ma

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.

Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis

no code implementations12 Feb 2021 Gen Li, Changxiao Cai, Yuxin Chen, Yuting Wei, Yuejie Chi

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).

Natural Questions Q-Learning

Softmax Policy Gradient Methods Can Take Exponential Time to Converge

no code implementations22 Feb 2021 Gen Li, Yuting Wei, Yuejie Chi, Yuxin Chen

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.

Policy Gradient Methods

Towards an Interpretable Data-driven Trigger System for High-throughput Physics Facilities

no code implementations14 Apr 2021 Chinmaya Mahesh, Kristin Dona, David W. Miller, Yuxin Chen

Data-intensive science is increasingly reliant on real-time processing capabilities and machine learning workflows, in order to filter and analyze the extreme volumes of data being collected.

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting

no code implementations NeurIPS 2021 Gen Li, Yuxin Chen, Yuejie Chi, Yuantao Gu, Yuting Wei

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").

reinforcement-learning Reinforcement Learning (RL)

Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence

no code implementations24 May 2021 Wenhao Zhan, Shicong Cen, Baihe Huang, Yuxin Chen, Jason D. Lee, Yuejie Chi

These can often be accounted for via regularized RL, which augments the target value function with a structure-promoting regularizer.

Reinforcement Learning (RL)

Inference for Heteroskedastic PCA with Missing Data

no code implementations26 Jul 2021 Yuling Yan, Yuxin Chen, Jianqing Fan

This paper studies how to construct confidence regions for principal component analysis (PCA) in high dimension, a problem that has been vastly under-explored.

valid

A Contract Theory based Incentive Mechanism for Federated Learning

no code implementations12 Aug 2021 Mengmeng Tian, Yuxin Chen, YuAn Liu, Zehui Xiong, Cyril Leung, Chunyan Miao

It is challenging to design proper incentives for the FL clients due to the fact that the task is privately trained by the clients.

Federated Learning

Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning

no code implementations NeurIPS 2021 Gen Li, Laixi Shi, Yuxin Chen, Yuejie Chi

Achieving sample efficiency in online episodic reinforcement learning (RL) requires optimally balancing exploration and exploitation.

Q-Learning reinforcement-learning +1

Class-wise Thresholding for Robust Out-of-Distribution Detection

no code implementations28 Oct 2021 Matteo Guarrera, Baihong Jin, Tung-Wei Lin, Maria Zuluaga, Yuxin Chen, Alberto Sangiovanni-Vincentelli

We consider the problem of detecting OoD(Out-of-Distribution) input data when using deep neural networks, and we propose a simple yet effective way to improve the robustness of several popular OoD detection methods against label shift.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Teaching an Active Learner with Contrastive Examples

no code implementations NeurIPS 2021 Chaoqi Wang, Adish Singla, Yuxin Chen

Our focus is to design a teaching algorithm that can provide an informative sequence of contrastive examples to the learner to speed up the learning process.

Active Learning

Online Learning of Energy Consumption for Navigation of Electric Vehicles

no code implementations3 Nov 2021 Niklas Åkerblom, Yuxin Chen, Morteza Haghir Chehreghani

In order to learn the model parameters, we develop an online learning framework and investigate several exploration strategies such as Thompson Sampling and Upper Confidence Bound.

Navigate Thompson Sampling

Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries Paradigm

no code implementations NeurIPS 2021 Akash Kumar, Yuxin Chen, Adish Singla

This learning paradigm has been extensively studied when the learner receives worst-case or random counterexamples; in this paper, we consider the optimal teacher who picks best-case counterexamples to teach the target hypothesis within a hypothesis class.

Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealing

1 code implementation27 Dec 2021 Renyu Zhang, Aly A. Khan, Robert L. Grossman, Yuxin Chen

To scale up the computation of queries to large batches, we further propose an efficient batch-mode acquisition procedure, which aims to maximize a novel information measure defined through the acquisition function.

Active Learning Multi-class Classification

LRSVRG-IMC: An SVRG-Based Algorithm for LowRank Inductive Matrix Completion

no code implementations21 Jan 2022 Shangrong Yu, Yuxin Chen, Hejun Wu

Low-rank inductive matrix completion (IMC) is currently widely used in IoT data completion, recommendation systems, and so on, as the side information in IMC has demonstrated great potential in reducing sample point remains a major obstacle for the convergence of the nonconvex solutions to IMC.

Matrix Completion Recommendation Systems

Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity

no code implementations28 Feb 2022 Laixi Shi, Gen Li, Yuting Wei, Yuxin Chen, Yuejie Chi

Offline or batch reinforcement learning seeks to learn a near-optimal policy using history data without active exploration of the environment.

Offline RL Q-Learning +2

The Efficacy of Pessimism in Asynchronous Q-Learning

no code implementations14 Mar 2022 Yuling Yan, Gen Li, Yuxin Chen, Jianqing Fan

This paper is concerned with the asynchronous form of Q-learning, which applies a stochastic approximation scheme to Markovian data samples.

Q-Learning

Learning Representation for Bayesian Optimization with Collision-free Regularization

no code implementations16 Mar 2022 Fengxue Zhang, Brian Nord, Yuxin Chen

We show that even with proper network design, such learned representation often leads to collision in the latent space: two points with significantly different observations collide in the learned latent space, leading to degraded optimization performance.

Bayesian Optimization

CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation

no code implementations31 Mar 2022 Ziqi Zhang, Yuxin Chen, Zongyang Ma, Zhongang Qi, Chunfeng Yuan, Bing Li, Ying Shan, Weiming Hu

In this paper, we propose to CREATE, the first large-scale Chinese shoRt vidEo retrievAl and Title gEneration benchmark, to facilitate research and application in video titling and video retrieval in Chinese.

Retrieval Video Captioning +1

Settling the Sample Complexity of Model-Based Offline Reinforcement Learning

no code implementations11 Apr 2022 Gen Li, Laixi Shi, Yuxin Chen, Yuejie Chi, Yuting Wei

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).

Offline RL reinforcement-learning +1

On the Permanence of Backdoors in Evolving Models

no code implementations8 Jun 2022 Huiying Li, Arjun Nitin Bhagoji, Yuxin Chen, Haitao Zheng, Ben Y. Zhao

Existing research on training-time attacks for deep neural networks (DNNs), such as backdoors, largely assume that models are static once trained, and hidden backdoors trained into models remain active indefinitely.

Cost-Effective Online Contextual Model Selection

no code implementations13 Jul 2022 Xuefeng Liu, Fangfang Xia, Rick L. Stevens, Yuxin Chen

In particular, we focus on the task of selecting pre-trained classifiers, and propose a contextual active model selection algorithm (CAMS), which relies on a novel uncertainty sampling query criterion defined on a given policy class for adaptive model selection.

Model Selection

Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model

no code implementations22 Aug 2022 Gen Li, Yuejie Chi, Yuting Wei, Yuxin Chen

This paper studies multi-agent reinforcement learning in Markov games, with the goal of learning Nash equilibria or coarse correlated equilibria (CCE) sample-optimally.

Multi-agent Reinforcement Learning

Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods

no code implementations30 Jan 2023 Gen Li, Yanxi Chen, Yuejie Chi, H. Vincent Poor, Yuxin Chen

Efficient computation of the optimal transport distance between two distributions serves as an algorithm subroutine that empowers various applications.

Deflated HeteroPCA: Overcoming the curse of ill-conditioning in heteroskedastic PCA

no code implementations10 Mar 2023 Yuchen Zhou, Yuxin Chen

This paper is concerned with estimating the column subspace of a low-rank matrix $\boldsymbol{X}^\star \in \mathbb{R}^{n_1\times n_2}$ from contaminated data.

A force-sensing surgical drill for real-time force feedback in robotic mastoidectomy

no code implementations5 Apr 2023 Yuxin Chen, Anna Goodridge, Manish Sahu, Aditi Kishore, Seena Vafaee, Harsha Mohan, Katherina Sapozhnikov, Francis Creighton, Russell Taylor, Deepa Galaiya

Results: The force measurements on the tip of the surgical drill are validated with raw-egg drilling experiments, where a force sensor mounted below the egg serves as ground truth.

Anatomy

Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning

no code implementations14 Apr 2023 Gen Li, Yuling Yan, Yuxin Chen, Jianqing Fan

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.

Offline RL reinforcement-learning +1

Efficient Online Decision Tree Learning with Active Feature Acquisition

no code implementations3 May 2023 Arman Rahbar, Ziyu Ye, Yuxin Chen, Morteza Haghir Chehreghani

Specifically, we employ a surrogate information acquisition function based on adaptive submodularity to actively query feature values with a minimal cost, while using a posterior sampling scheme to maintain a low regret for online prediction.

Medical Diagnosis

ViLEM: Visual-Language Error Modeling for Image-Text Retrieval

no code implementations CVPR 2023 Yuxin Chen, Zongyang Ma, Ziqi Zhang, Zhongang Qi, Chunfeng Yuan, Ying Shan, Bing Li, Weiming Hu, XiaoHu Qie, Jianping Wu

ViLEM then enforces the model to discriminate the correctness of each word in the plausible negative texts and further correct the wrong words via resorting to image information.

Contrastive Learning Retrieval +3

Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models

no code implementations15 Jun 2023 Gen Li, Yuting Wei, Yuxin Chen, Yuejie Chi

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.

Denoising

Settling the Sample Complexity of Online Reinforcement Learning

no code implementations25 Jul 2023 Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon S. Du

While a number of recent works achieved asymptotically minimal regret in online RL, the optimality of these results is only guaranteed in a ``large-sample'' regime, imposing enormous burn-in cost in order for their algorithms to operate optimally.

reinforcement-learning Reinforcement Learning (RL)

Learning Regions of Interest for Bayesian Optimization with Adaptive Level-Set Estimation

no code implementations25 Jul 2023 Fengxue Zhang, Jialin Song, James Bowden, Alexander Ladd, Yisong Yue, Thomas A. Desautels, Yuxin Chen

Our approach is easy to tune, and is able to focus on local region of the optimization space that can be tackled by existing BO methods.

Bayesian Optimization

BitCoin: Bidirectional Tagging and Supervised Contrastive Learning based Joint Relational Triple Extraction Framework

no code implementations21 Sep 2023 Luyao He, Zhongbao Zhang, Sen Su, Yuxin Chen

To address these issues, we propose BitCoin, an innovative Bidirectional tagging and supervised Contrastive learning based joint relational triple extraction framework.

Contrastive Learning graph construction +5

Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints

no code implementations28 Sep 2023 Chaoqi Wang, Yibo Jiang, Chenghao Yang, Han Liu, Yuxin Chen

The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but concurrently amplify safety concerns, such as potential misuse of AI systems, necessitating effective AI alignment.

Blending Imitation and Reinforcement Learning for Robust Policy Improvement

no code implementations3 Oct 2023 Xuefeng Liu, Takuma Yoneda, Rick L. Stevens, Matthew R. Walter, Yuxin Chen

Integral to RPI are Robust Active Policy Selection (RAPS) and Robust Policy Gradient (RPG), both of which reason over whether to perform state-wise imitation from the oracles or learn from its own value function when the learner's performance surpasses that of the oracles in a specific state.

Imitation Learning reinforcement-learning +1

Quantifying Agent Interaction in Multi-agent Reinforcement Learning for Cost-efficient Generalization

no code implementations11 Oct 2023 Yuxin Chen, Chen Tang, Ran Tian, Chenran Li, Jinning Li, Masayoshi Tomizuka, Wei Zhan

We observe that, generally, a more diverse set of co-play agents during training enhances the generalization performance of the ego agent; however, this improvement varies across distinct scenarios and environments.

Multi-agent Reinforcement Learning

Constrained Bayesian Optimization with Adaptive Active Learning of Unknown Constraints

no code implementations12 Oct 2023 Fengxue Zhang, Zejie Zhu, Yuxin Chen

Optimizing objectives under constraints, where both the objectives and constraints are black box functions, is a common scenario in real-world applications such as scientific experimental design, design of medical therapies, and industrial process optimization.

Active Learning Bayesian Optimization +1

Learning to Rank for Active Learning via Multi-Task Bilevel Optimization

no code implementations25 Oct 2023 Zixin Ding, Si Chen, Ruoxi Jia, Yuxin Chen

To address these limitations, we propose a novel approach for active learning, which aims to select batches of unlabeled instances through a learned surrogate model for data acquisition.

Active Learning Bilevel Optimization +1

Federated Natural Policy Gradient Methods for Multi-task Reinforcement Learning

no code implementations1 Nov 2023 Tong Yang, Shicong Cen, Yuting Wei, Yuxin Chen, Yuejie Chi

Federated reinforcement learning (RL) enables collaborative decision making of multiple distributed agents without sharing local data trajectories.

Decision Making Policy Gradient Methods +2

Heteroskedastic Tensor Clustering

no code implementations4 Nov 2023 Yuchen Zhou, Yuxin Chen

Tensor clustering, which seeks to extract underlying cluster structures from noisy tensor observations, has gained increasing attention.

Clustering

Enhancing Instance-Level Image Classification with Set-Level Labels

no code implementations9 Nov 2023 Renyu Zhang, Aly A. Khan, Yuxin Chen, Robert L. Grossman

Our experimental results demonstrate the effectiveness of our approach, showcasing improved classification performance compared to traditional single-instance label-based methods.

Classification Few-Shot Learning +2

Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale

no code implementations14 Nov 2023 Wei Wen, Kuang-Hung Liu, Igor Fedorov, Xin Zhang, Hang Yin, Weiwei Chu, Kaveh Hassani, Mengying Sun, Jiang Liu, Xu Wang, Lin Jiang, Yuxin Chen, Buyun Zhang, Xi Liu, Dehua Cheng, Zhengxing Chen, Guang Zhao, Fangqiu Han, Jiyan Yang, Yuchen Hao, Liang Xiong, Wen-Yen Chen

In industry system, such as ranking system in Meta, it is unclear whether NAS algorithms from the literature can outperform production baselines because of: (1) scale - Meta ranking systems serve billions of users, (2) strong baselines - the baselines are production models optimized by hundreds to thousands of world-class engineers for years since the rise of deep learning, (3) dynamic baselines - engineers may have established new and stronger baselines during NAS search, and (4) efficiency - the search pipeline must yield results quickly in alignment with the productionization life cycle.

Neural Architecture Search

Optimal Multi-Distribution Learning

no code implementations8 Dec 2023 Zihan Zhang, Wenhao Zhan, Yuxin Chen, Simon S. Du, Jason D. Lee

Focusing on a hypothesis class of Vapnik-Chervonenkis (VC) dimension $d$, we propose a novel algorithm that yields an $varepsilon$-optimal randomized hypothesis with a sample complexity on the order of $(d+k)/\varepsilon^2$ (modulo some logarithmic factor), matching the best-known lower bound.

Fairness

Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context

no code implementations11 Dec 2023 Xiang Cheng, Yuxin Chen, Suvrit Sra

Many neural network architectures are known to be Turing Complete, and can thus, in principle implement arbitrary algorithms.

In-Context Learning

Direct Acquisition Optimization for Low-Budget Active Learning

no code implementations8 Feb 2024 Zhuokai Zhao, Yibo Jiang, Yuxin Chen

Active Learning (AL) has gained prominence in integrating data-intensive machine learning (ML) models into domains with limited labeled data.

Active Learning

Disaggregated Multi-Tower: Topology-aware Modeling Technique for Efficient Large-Scale Recommendation

no code implementations1 Mar 2024 Liang Luo, Buyun Zhang, Michael Tsang, Yinbin Ma, Ching-Hsiang Chu, Yuxin Chen, Shen Li, Yuchen Hao, Yanli Zhao, Guna Lakshminarayanan, Ellie Dingqiao Wen, Jongsoo Park, Dheevatsa Mudigere, Maxim Naumov

We study a mismatch between the deep learning recommendation models' flat architecture, common distributed training paradigm and hierarchical data center topology.

Accelerating Convergence of Score-Based Diffusion Models, Provably

no code implementations6 Mar 2024 Gen Li, Yu Huang, Timofey Efimov, Yuting Wei, Yuejie Chi, Yuxin Chen

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.

Horizon-Free Regret for Linear Markov Decision Processes

no code implementations15 Mar 2024 Zihan Zhang, Jason D. Lee, Yuxin Chen, Simon S. Du

A recent line of works showed regret bounds in reinforcement learning (RL) can be (nearly) independent of planning horizon, a. k. a.~the horizon-free bounds.

LEMMA Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.