no code implementations • 9 Apr 2024 • Yixuan Zhang, Dongyan Huo, Yudong Chen, Qiaomin Xie
Motivated by Q-learning, we study nonsmooth contractive stochastic approximation (SA) with constant stepsize.
no code implementations • 18 Mar 2024 • Matthew Zurek, Yudong Chen
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.
no code implementations • 29 Feb 2024 • Xumei Xi, Christina Lee Yu, Yudong Chen
Our bounds characterize the hardness of estimating each entry as a function of the localized sampling probabilities.
no code implementations • 8 Feb 2024 • Yige Hong, Qiaomin Xie, Yudong Chen, Weina Wang
We consider the infinite-horizon, average-reward restless bandit problem in discrete time.
no code implementations • 18 Dec 2023 • Dongyan Huo, Yudong Chen, Qiaomin Xie
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.
no code implementations • 22 Nov 2023 • Matthew Zurek, Yudong Chen
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.
1 code implementation • 6 Nov 2023 • Xuwei Xu, Sen Wang, Yudong Chen, Yanping Zheng, Zhewei Wei, Jiajun Liu
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
no code implementations • 1 Nov 2023 • Young Wu, Jeremy McMahan, Yiding Chen, Yudong Chen, Xiaojin Zhu, Qiaomin Xie
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.
1 code implementation • 26 Oct 2023 • Yudong Chen, Sen Wang, Jiajun Liu, Xuwei Xu, Frank de Hoog, Brano Kusy, Zi Huang
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.
no code implementations • 9 Oct 2023 • Xuwei Xu, Sen Wang, Yudong Chen, Jiajun Liu
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.
1 code implementation • 9 Oct 2023 • Xuwei Xu, Changlin Li, Yudong Chen, Xiaojun Chang, Jiajun Liu, Sen Wang
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.
1 code implementation • 20 Sep 2023 • Xinyu Zhou, Delong Chen, Yudong Chen
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.
no code implementations • 29 Aug 2023 • Matthew Zurek, Yudong Chen
Our gap-free clustering procedure also leads to improved algorithms for recursive clustering.
1 code implementation • 18 Jul 2023 • Jeremy McMahan, Young Wu, Yudong Chen, Xiaojin Zhu, Qiaomin Xie
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.
no code implementations • 28 Jun 2023 • Emmanouil-Vasileios Vlatakis-Gkaragkounis, Angeliki Giannou, Yudong Chen, Qiaomin Xie
Our work endeavors to elucidate and quantify the probabilistic structures intrinsic to these algorithms.
no code implementations • 2 Jun 2023 • Brahma S. Pavse, Matthew Zurek, Yudong Chen, Qiaomin Xie, Josiah P. Hanna
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.
1 code implementation • NeurIPS 2023 • Yige Hong, Qiaomin Xie, Yudong Chen, Weina Wang
In both settings, our work is the first asymptotic optimality result that does not require UGAP.
no code implementations • 24 May 2023 • Xumei Xi, Christina Lee Yu, Yudong Chen
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.
1 code implementation • 27 Oct 2022 • Yudong Chen, Sen Wang, Jiajun Liu, Xuwei Xu, Frank de Hoog, Zi Huang
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.
no code implementations • 3 Oct 2022 • Dongyan Huo, Yudong Chen, Qiaomin Xie
We consider Linear Stochastic Approximation (LSA) with a constant stepsize and Markovian data.
no code implementations • 25 Jun 2022 • Jianglin Lu, Jie zhou, Yudong Chen, Witold Pedrycz, Kwok-Wai Hung
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.
no code implementations • 7 Jun 2022 • Tyler Sam, Yudong Chen, Christina Lee Yu
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 $H$.
no code implementations • 6 Mar 2022 • Liwei Jiang, Yudong Chen, Lijun Ding
We study the asymmetric matrix factorization problem under a natural nonconvex formulation with arbitrary overparametrization.
no code implementations • 13 Jan 2022 • Jiazhen Hong, Wei Qian, Yudong Chen, Yuqian Zhang
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.
1 code implementation • NeurIPS 2021 • Hong Chen, Yudong Chen, Xin Wang, Ruobing Xie, Rui Wang, Feng Xia, Wenwu Zhu
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.
no code implementations • NeurIPS 2021 • Yingjie Fei, Zhuoran Yang, Yudong Chen, Zhaoran Wang
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.
no code implementations • NeurIPS 2021 • Lijun Ding, Liwei Jiang, Yudong Chen, Qing Qu, Zhihui Zhu
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.
no code implementations • 16 Aug 2021 • Qinghong Lin, Xiaojun Chen, Qin Zhang, Shangxuan Tian, Yudong Chen
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.
no code implementations • KDD 2021 • Yudong Chen, Xin Wang, Miao Fan, Jizhou Huang, Shengwen Yang, and Wenwu Zhu.
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.
1 code implementation • 22 Feb 2021 • Yudong Chen, Chaoyu Guan, Zhikun Wei, Xin Wang, Wenwu Zhu
Meta-learning aims at learning quickly on novel tasks with limited data by transferring generic experience learned from previous tasks.
no code implementations • 3 Nov 2020 • Fanghui Liu, Xiaolin Huang, Yudong Chen, Johan A. K. Suykens
In this paper, we develop a quadrature framework for large-scale kernel machines via a numerical integration representation.
no code implementations • 25 Oct 2020 • Xin Wang, Yudong Chen, Wenwu Zhu
We discuss works on curriculum learning within a general CL framework, elaborating on how to design a manually predefined curriculum or an automatic curriculum.
no code implementations • 28 Sep 2020 • Yudong Chen, Dogyoon Song, Xumei Xi, Yuqian Zhang
As the objective function is non-convex, there can be multiple local minima that are not globally optimal, even for well-separated mixture models.
no code implementations • 31 Aug 2020 • Lijun Ding, Yuqian Zhang, Yudong Chen
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.
no code implementations • NeurIPS 2020 • Yingjie Fei, Zhuoran Yang, Yudong Chen, Zhaoran Wang, Qiaomin Xie
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.
no code implementations • 23 Apr 2020 • Fanghui Liu, Xiaolin Huang, Yudong Chen, Johan A. K. Suykens
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.
no code implementations • 7 Mar 2020 • Yudong Chen, Tengyao Wang, Richard J. Samworth
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.
no code implementations • 17 Feb 2020 • Qiaomin Xie, Yudong Chen, Zhaoran Wang, Zhuoran Yang
In the offline setting, we control both players and aim to find the Nash Equilibrium by minimizing the duality gap.
no code implementations • 16 Feb 2020 • Wei Qian, Yuqian Zhang, Yudong Chen
Our theoretical results corroborate existing empirical observations and provide justification for several improved algorithms for $k$-means clustering.
no code implementations • 20 Nov 2019 • Fanghui Liu, Xiaolin Huang, Yudong Chen, Jie Yang, Johan A. K. Suykens
In this paper, we propose a fast surrogate leverage weighted sampling strategy to generate refined random Fourier features for kernel approximation.
no code implementations • NeurIPS 2019 • Jicong Fan, Lijun Ding, Yudong Chen, Madeleine Udell
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.
no code implementations • ICCV 2019 • Yudong Chen, Zhihui Lai, Yujuan Ding, Kaiyi Lin, Wai Keung Wong
Recently, a series of deep supervised hashing methods were proposed for binary code learning.
1 code implementation • NeurIPS 2019 • Wei Qian, Yuqian Zhang, Yudong Chen
This work studies the location estimation problem for a mixture of two rotation invariant log-concave densities.
no code implementations • 7 Jun 2019 • Xin Qian, Yudong Chen, Andreea Minca
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.
no code implementations • 22 Apr 2019 • Vasileios Charisopoulos, Yudong Chen, Damek Davis, Mateo Díaz, Lijun Ding, Dmitriy Drusvyatskiy
The task of recovering a low-rank matrix from its noisy linear measurements plays a central role in computational science.
no code implementations • 21 Apr 2019 • Yingjie Fei, Yudong Chen
We study the statistical performance of semidefinite programming (SDP) relaxations for clustering under random graph models.
no code implementations • 12 Oct 2018 • Jeongyeol Kwon, Wei Qian, Constantine Caramanis, Yudong Chen, Damek Davis
Recent results established that EM enjoys global convergence for Gaussian Mixture Models.
no code implementations • 30 Sep 2018 • Xiao-Dong Li, Yudong Chen, Jiaming Xu
We introduce some important theoretical techniques and results for establishing the consistency of convex community detection under various statistical models.
no code implementations • 14 Jun 2018 • Dong Yin, Yudong Chen, Kannan Ramchandran, Peter Bartlett
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.
1 code implementation • 10 Apr 2018 • Canyi Lu, Jiashi Feng, Yudong Chen, Wei Liu, Zhouchen Lin, Shuicheng Yan
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.
no code implementations • 20 Mar 2018 • Lijun Ding, Yudong Chen
In this paper, we introduce a powerful technique based on Leave-one-out analysis to the study of low-rank matrix completion problems.
no code implementations • 17 Mar 2018 • Yingjie Fei, Yudong Chen
The error of the integer program, and hence that of the SDP, are further shown to decay exponentially in the signal-to-noise ratio.
1 code implementation • ICML 2018 • Dong Yin, Yudong Chen, Kannan Ramchandran, Peter Bartlett
In particular, these algorithms are shown to achieve order-optimal statistical error rates for strongly convex losses.
no code implementations • 23 Feb 2018 • Yudong Chen, Yuejie Chi
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.
no code implementations • CVPR 2016 • Canyi Lu, Jiashi Feng, Yudong Chen, Wei Liu, Zhouchen Lin, Shuicheng Yan
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.}
no code implementations • 23 May 2017 • Yingjie Fei, Yudong Chen
In this paper we consider the cluster estimation problem under the Stochastic Block Model.
2 code implementations • 16 May 2017 • Yudong Chen, Lili Su, Jiaming Xu
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 $O(m d \log N)$.
no code implementations • NeurIPS 2016 • Xinyang Yi, Dohyung Park, Yudong Chen, Constantine Caramanis
For the partially observed case, we show the complexity of our algorithm is no more than $\mathcal{O}(r^4d \log d \log(1/\varepsilon))$.
no code implementations • 28 Dec 2015 • Yudong Chen, Xiao-Dong Li, Jiaming Xu
We establish non-asymptotic theoretical guarantees for both approximate clustering and perfect clustering.
no code implementations • 10 Sep 2015 • Yudong Chen, Martin J. Wainwright
We provide a simple set of conditions under which projected gradient descent, when given a suitable initialization, converges geometrically to a statistically useful solution.
no code implementations • NeurIPS 2014 • Shiau Hong Lim, Yudong Chen, Huan Xu
Our theoretical results cover and subsume a wide range of existing graph clustering results including planted partition, weighted clustering and partially observed graphs.
no code implementations • 6 Feb 2014 • Yudong Chen, Jiaming Xu
Of particular interest is the setting where the number of clusters/submatrices is allowed to grow unbounded with the problem size.
no code implementations • 25 Dec 2013 • Yudong Chen, Xinyang Yi, Constantine Caramanis
We consider the mixed regression problem with two components, under adversarial and stochastic noise.
no code implementations • 1 Oct 2013 • Yudong Chen
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.
no code implementations • 12 Jun 2013 • Yudong Chen, Srinadh Bhojanapalli, Sujay Sanghavi, Rachel Ward
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.
no code implementations • 28 Mar 2013 • Yudong Chen, Vikas Kawadia, Rahul Urgaonkar
We present a principled approach for detecting overlapping temporal community structure in dynamic networks.
no code implementations • NeurIPS 2012 • Yudong Chen, Sujay Sanghavi, Huan Xu
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.
no code implementations • 11 Oct 2012 • Yudong Chen, Sujay Sanghavi, Huan Xu
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.
no code implementations • 5 Jun 2012 • Yudong Chen, Constantine Caramanis
Many models for sparse regression typically assume that the covariates are known completely, and without noise.
no code implementations • 25 Apr 2011 • Yudong Chen, Ali Jalali, Sujay Sanghavi, Huan Xu
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.
no code implementations • 10 Feb 2011 • Yudong Chen, Huan Xu, Constantine Caramanis, Sujay Sanghavi
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.