b'Cong Ma'

research

∙ 06/06/2023

Unraveling Projection Heads in Contrastive Learning: Insights from Expansion and Shrinkage

We investigate the role of projection heads, also known as projectors, w...

0 Yu Gui, et al. ∙

research

∙ 05/30/2023

Sharp high-probability sample complexities for policy evaluation with linear function approximation

This paper is concerned with the problem of policy evaluation with linea...

0 Gen Li, et al. ∙

research

∙ 05/18/2023

Conformalized matrix completion

Matrix completion aims to estimate missing entries in a data matrix, usi...

0 Yu Gui, et al. ∙

research

∙ 05/09/2023

Multi-Teacher Knowledge Distillation For Text Image Machine Translation

Text image machine translation (TIMT) has been widely used in various re...

0 Cong Ma, et al. ∙

research

∙ 05/09/2023

E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation

Text image machine translation (TIMT) aims to translate texts embedded i...

0 Cong Ma, et al. ∙

research

∙ 02/02/2023

The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing

We propose , a preconditioned gradient descent method to tackle the low-...

0 Xingyu Xu, et al. ∙

research

∙ 10/08/2022

Improving End-to-End Text Image Translation From the Auxiliary Text Translation Task

End-to-end text image translation (TIT), which aims at translating the s...

0 Cong Ma, et al. ∙

research

∙ 09/26/2022

O(T^-1) Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games

We prove that optimistic-follow-the-regularized-leader (OFTRL), together...

0 Yuepeng Yang, et al. ∙

research

∙ 07/12/2022

Optimal tuning-free convex relaxation for noisy matrix completion

This paper is concerned with noisy matrix completion–the problem of reco...

0 Yuepeng Yang, et al. ∙

research

∙ 06/18/2022

Fast and Provable Tensor Robust Principal Component Analysis via Scaled Gradient Descent

An increasing number of data science and machine learning problems rely ...

0 Harry Dong, et al. ∙

research

∙ 05/21/2022

Pessimism for Offline Linear Contextual Bandits using ℓ_p Confidence Sets

We present a family {π̂}_p≥ 1 of pessimistic learning rules for offline ...

0 Gene Li, et al. ∙

research

∙ 05/06/2022

Optimally tackling covariate shift in RKHS-based nonparametric regression

We study the covariate shift problem in the context of nonparametric reg...

0 Cong Ma, et al. ∙

research

∙ 04/05/2022

Jump-Start Reinforcement Learning

Reinforcement learning (RL) provides a theoretical framework for continu...

0 Ikechukwu Uchendu, et al. ∙

research

∙ 02/06/2022

A new similarity measure for covariate shift with applications to nonparametric regression

We study covariate shift in the context of nonparametric regression. We ...

0 Reese Pathak, et al. ∙

research

∙ 06/26/2021

TANet++: Triple Attention Network with Filtered Pointcloud on 3D Detection

TANet is one of state-of-the-art 3D object detection method on KITTI and...

0 Cong Ma, et al. ∙

research

∙ 04/29/2021

Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Estimation from Incomplete Measurements

Tensors, which provide a powerful and flexible model for representing mu...

0 Tian Tong, et al. ∙

research

∙ 03/22/2021

Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism

Offline (or batch) reinforcement learning (RL) algorithms seek to learn ...

41 Paria Rashidinejad, et al. ∙

research

∙ 01/19/2021

Minimax Off-Policy Evaluation for Multi-Armed Bandits

We study the problem of off-policy evaluation in the multi-armed bandit ...

0 Cong Ma, et al. ∙

research

∙ 01/13/2021

Beyond Procrustes: Balancing-Free Gradient Descent for Asymmetric Low-Rank Matrix Sensing

Low-rank matrix estimation plays a central role in various applications ...

0 Cong Ma, et al. ∙

research

∙ 12/15/2020

Spectral Methods for Data Science: A Statistical Perspective

Spectral methods have emerged as a simple yet surprisingly effective app...

18 Yuxin Chen, et al. ∙

research

∙ 10/26/2020

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 ma...

0 Tian Tong, et al. ∙

research

∙ 09/23/2020

Learning Mixtures of Low-Rank Models

We study the problem of learning mixtures of low-rank models, i.e. recon...

22 Yanxi Chen, et al. ∙

research

∙ 05/18/2020

Accelerating Ill-Conditioned Low-Rank Matrix Estimation via Scaled Gradient Descent

Low-rank matrix estimation is a canonical problem that finds numerous ap...

0 Tian Tong, et al. ∙

research

∙ 01/15/2020

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

This paper delivers improved theoretical guarantees for the convex progr...

19 Yuxin Chen, et al. ∙

research

∙ 06/10/2019

Inference and Uncertainty Quantification for Noisy Matrix Completion

Noisy matrix completion aims at estimating a low-rank matrix given only ...

0 Yuxin Chen, et al. ∙

research

∙ 04/10/2019

A Selective Overview of Deep Learning

Deep learning has arguably achieved tremendous success in recent years. ...

0 Jianqing Fan, et al. ∙

research

∙ 02/20/2019

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

This paper studies noisy low-rank matrix completion: given partial and c...

0 Yuxin Chen, et al. ∙

research

∙ 04/12/2018

Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Tracking

Multi-Object Tracking (MOT) is a challenging task in the complex scene s...

0 Cong Ma, et al. ∙

research

∙ 03/21/2018

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

This paper considers the problem of solving systems of quadratic equatio...

0 Yuxin Chen, et al. ∙

research

∙ 02/17/2018

Nonconvex Matrix Factorization from Rank-One Measurements

We consider the problem of recovering low-rank matrices from random rank...

0 Yuanxin Li, et al. ∙

research

∙ 11/28/2017

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 effi...

0 Cong Ma, et al. ∙

research

∙ 09/20/2017

Inter-Subject Analysis: Inferring Sparse Interactions with Dense Intra-Graphs

We develop a new modeling framework for Inter-Subject Analysis (ISA). Th...

0 Cong Ma, et al. ∙

research

∙ 07/31/2017

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

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

0 Yuxin Chen, et al. ∙

Cong Ma

Featured Co-authors