Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Empirical Risk Minimization in the Non-interactive Local Model of Differential Privacy

Nov 11, 2020
Di Wang, Marco Gaboardi, Adam Smith, Jinhui Xu

* Appeared at Journal of Machine Learning Research. The journal version of arXiv:1802.04085, fixed a bug in arXiv:1812.06825 

  Access Paper or Ask Questions

Differentially Private (Gradient) Expectation Maximization Algorithm with Statistical Guarantees

Oct 22, 2020
Di Wang, Jiahao Ding, Zejun Xie, Miao Pan, Jinhui Xu

* Submiited. arXiv admin note: text overlap with arXiv:2010.09576 

  Access Paper or Ask Questions

On Differentially Private Stochastic Convex Optimization with Heavy-tailed Data

Oct 21, 2020
Di Wang, Hanshen Xiao, Srini Devadas, Jinhui Xu

* Published in ICML 2020 

  Access Paper or Ask Questions

Robust High Dimensional Expectation Maximization Algorithm via Trimmed Hard Thresholding

Oct 19, 2020
Di Wang, Xiangyu Guo, Shi Li, Jinhui Xu

* Accepted at Machine Learning 

  Access Paper or Ask Questions

Estimating Stochastic Linear Combination of Non-linear Regressions Efficiently and Scalably

Oct 19, 2020
Di Wang, Xiangyu Guo, Chaowen Guan, Shi Li, Jinhui Xu

* This paper is a substantially extended version of our previous work appeared in AAAI'20 

  Access Paper or Ask Questions

Learning Manifold Implicitly via Explicit Heat-Kernel Learning

Oct 05, 2020
Yufan Zhou, Changyou Chen, Jinhui Xu

* Accepted by NeurIPS 2020, code will be available at https://github.com/drboog/Heat-Kernel 

  Access Paper or Ask Questions

Towards Assessment of Randomized Smoothing Mechanisms for Certifying Adversarial Robustness

Jun 07, 2020
Tianhang Zheng, Di Wang, Baochun Li, Jinhui Xu

* Correct the some details of the theorems and proofs 

  Access Paper or Ask Questions

Towards Assessment of Randomized Mechanisms for Certifying Adversarial Robustness

May 27, 2020
Tianhang Zheng, Di Wang, Baochun Li, Jinhui Xu

* Refine the proofs, and add more theorems and experiments 

  Access Paper or Ask Questions

Graph Neural Networks with Composite Kernels

May 16, 2020
Yufan Zhou, Jiayi Xian, Changyou Chen, Jinhui Xu


  Access Paper or Ask Questions

KernelNet: A Data-Dependent Kernel Parameterization for Deep Generative Modeling

Dec 02, 2019
Yufan Zhou, Changyou Chen, Jinhui Xu


  Access Paper or Ask Questions

Estimating Smooth GLM in Non-interactive Local Differential Privacy Model with Public Unlabeled Data

Oct 01, 2019
Di Wang, Huanyu Zhang, Marco Gaboardi, Jinhui Xu


  Access Paper or Ask Questions

Differentially Private High Dimensional Sparse Covariance Matrix Estimation

Jan 18, 2019
Di Wang, Jinhui Xu

* A short version will be appeared in CISS 2019 

  Access Paper or Ask Questions

Differentially Private Empirical Risk Minimization in Non-interactive Local Model via Polynomial of Inner Product Approximation

Dec 17, 2018
Di Wang, Adam Smith, Jinhui Xu

* To appear in Algorithmic Learning Theory 2019 (ALT 2019), draft version 

  Access Paper or Ask Questions

A Unified Framework for Clustering Constrained Data without Locality Property

Oct 02, 2018
Hu Ding, Jinhui Xu


  Access Paper or Ask Questions

Empirical Risk Minimization in Non-interactive Local Differential Privacy: Efficiency and High Dimensional Case

May 16, 2018
Di Wang, Marco Gaboardi, Jinhui Xu

* Add a new section on high dimensional case 

  Access Paper or Ask Questions

Differentially Private Empirical Risk Minimization Revisited: Faster and More General

Feb 14, 2018
Di Wang, Minwei Ye, Jinhui Xu

* Thirty-first Annual Conference on Neural Information Processing Systems (NIPS-2017) 

  Access Paper or Ask Questions

Large Scale Constrained Linear Regression Revisited: Faster Algorithms via Preconditioning

Feb 09, 2018
Di Wang, Jinhui Xu

* Appear in AAAI-18 

  Access Paper or Ask Questions

Deep Extreme Feature Extraction: New MVA Method for Searching Particles in High Energy Physics

Mar 24, 2016
Chao Ma, Tianchenghou, Bin Lan, Jinhui Xu, Zhenhua Zhang

* 20 pages, 9 figures 

  Access Paper or Ask Questions