Yi Xu

发表

NEON+: Accelerated Gradient Methods for Extracting Negative Curvature for Non-Convex Optimization

Tianbao Yang, Yi Xu, Rong Jin, 2017, 1712.01033.

Accelerate stochastic subgradient method by leveraging local growth condition

Tianbao Yang, Yi Xu, Qihang Lin, 2016, Analysis and Applications.

Stochastic Proximal Gradient Methods for Non-smooth Non-Convex Regularized Problems.

Tianbao Yang, Yi Xu, Rong Jin, 2019 .

Adaptive SVRG Methods under Error Bound Conditions with Unknown Growth Parameter

Tianbao Yang, Yi Xu, Qihang Lin, 2017, NIPS.

Towards Understanding Label Smoothing

Yi Xu, Rong Jin, Yuanhong Xu, 2020, ArXiv.

Accelerated Stochastic Subgradient Methods under Local Error Bound Condition

Tianbao Yang, Yi Xu, Qihang Lin, 2016 .

Frank-Wolfe Method is Automatically Adaptive to Error Bound Condition

Tianbao Yang, Yi Xu, 2018, 1810.04765.

Supplement for ” Katalyst : Boosting Convex Katyusha for Non-Convex Problems with a Large Condition Number ”

Tianbao Yang, Yi Xu, Zaiyi Chen, 2019 .

Improved Fine-Tuning by Better Leveraging Pre-Training Data

Antoni B. Chan, Yi Xu, Yuanhong Xu, 2021, NeurIPS.

An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation

Antoni B. Chan, Yi Xu, Yuanhong Xu, 2022, ArXiv.

Fairness via Adversarial Attribute Neighbourhood Robust Learning

Tianbao Yang, Yi Xu, Q. Qi, 2022, ArXiv.

Attentional-Biased Stochastic Gradient Descent

Tianbao Yang, Yi Xu, W. Yin, 2020, 2012.06951.

On the Convergence of Deep Networks with Sample Quadratic Overparameterization pdf

Yi Xu, Yonathan Aflalo, Rong Jin, 2021, ArXiv.

A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks

Lihi Zelnik-Manor, Rong Jin, Yonathan Aflalo, 2021, 2101.04243.

WeMix: How to Better Utilize Data Augmentation pdf

Yi Xu, Qi Qian, Hao Li, 2020, ArXiv.

On the Convergence of (Stochastic) Gradient Descent with Extrapolation for Non-Convex Minimization

Rong Jin, Tianbao Yang, Sen Yang, 2019, IJCAI.

Dash: Semi-Supervised Learning with Dynamic Thresholding

Rong Jin, Qi Qian, Baigui Sun, 2021, ICML.

Homotopy Smoothing for Non-Smooth Problems with Lower Complexity than O(1/\epsilon)

Tianbao Yang, Yi Xu, Yan Yan, 2016, NIPS.

Effective Model Sparsification by Scheduled Grow-and-Prune Methods pdf

Rong Jin, Xiaolong Ma, Zejiang Hou, 2021, ICLR.

A Novel Convergence Analysis for Algorithms of the Adam Family and Beyond

Tianbao Yang, Yi Xu, Rong Jin, 2021, 2104.14840.

On Stochastic Moving-Average Estimators for Non-Convex Optimization

Tianbao Yang, Yi Xu, Rong Jin, 2021, ArXiv.

ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization

Mingrui Liu, Tianbao Yang, Yi Xu, 2017, NIPS.

Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization

Wei Liu, Yan Yan, Yi Xu, 2020, NeurIPS.

Stochastic Primal-Dual Algorithms with Faster Convergence than O(1/√T) for Problems without Bilinear Structure pdf

Tianbao Yang, Yan Yan, Qihang Lin, 2019, ArXiv.

Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity pdf

Tianbao Yang, Yiming Ying, Zhuoning Yuan, 2021, ICML.

Improved Fine-tuning by Leveraging Pre-training Data: Theory and Practice pdf

Rong Jin, Qi Qian, Antoni B. Chan, 2021, ArXiv.

An Online Method for A Class of Distributionally Robust Optimization with Non-convex Objectives

Tianbao Yang, Yi Xu, Rong Jin, 2020, NeurIPS.

Self-Supervised Pre-Training for Transformer-Based Person Re-Identification pdf

Hao Li, Hao Luo, Pichao Wang, 2021, ArXiv.

First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time

Tianbao Yang, Jing Rong, Yi Xu, 2017, NeurIPS.

Attentional Biased Stochastic Gradient for Imbalanced Classification pdf

Qi Qi, Yi Xu, Tianbao Yang, 2020, ArXiv.

Attentional-Biased Stochastic Gradient Descent

Tianbao Yang, Yi Xu, W. Yin, 2020, 2012.06951.

Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problems

Tianbao Yang, Yi Xu, Rong Jin, 2019, NeurIPS.

Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence

Rong Jin, Tianbao Yang, Qihang Lin, 2018, ICML.

A Novel Convergence Analysis for Algorithms of the Adam Family pdf

Rong Jin, Tianbao Yang, Wotao Yin, 2021, ArXiv.

A Practical Online Method for Distributionally Deep Robust Optimization pdf

Qi Qi, Yi Xu, Tianbao Yang, 2020, ArXiv.

An Online Method for Distributionally Deep Robust Optimization

Qi Qi, Yi Xu, Tianbao Yang, 2020 .

Sharp Analysis of Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization pdf

Wei Liu, Yi Xu, Tianbao Yang, 2020, ArXiv.

SADAGRAD: Strongly Adaptive Stochastic Gradient Methods

Enhong Chen, Tianbao Yang, Yi Xu, 2018, ICML.

Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence

Tianbao Yang, Yi Xu, Qihang Lin, 2017, ICML.

Accelerate Stochastic Subgradient Method by Leveraging Local Error Bound pdf

Tianbao Yang, Yi Xu, Qihang Lin, 2016, ArXiv.

Sharp Analysis of Simple Restarted Stochastic Gradient Methods for Min-Max Optimization

Tianbao Yang, Wei Liu, Yan Yan, 2019 .

Learning with Non-Convex Truncated Losses by SGD

Rong Jin, Tianbao Yang, Shenghuo Zhu, 2018, UAI.

On Stochastic Moving-Average Estimators for Non-Convex Optimization

Tianbao Yang, Yi Xu, Rong Jin, 2021, ArXiv.

Effective Model Sparsification by Scheduled Grow-and-Prune Methods

Yi Xu, Rong Jin, Yanzhi Wang, 2021, ICLR.