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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Daniel Hsu

Generalization bounds via distillation


Apr 12, 2021
Daniel Hsu, Ziwei Ji, Matus Telgarsky, Lan Wang

* To appear, ICLR 2021 

  Access Paper or Ask Questions

On the Approximation Power of Two-Layer Networks of Random ReLUs


Feb 03, 2021
Daniel Hsu, Clayton Sanford, Rocco A. Servedio, Emmanouil-Vasileios Vlatakis-Gkaragkounis


  Access Paper or Ask Questions

Detecting Foodborne Illness Complaints in Multiple Languages Using English Annotations Only


Oct 11, 2020
Ziyi Liu, Giannis Karamanolakis, Daniel Hsu, Luis Gravano

* Accepted for the 11th International Workshop on Health Text Mining and Information Analysis ([email protected] 2020) 

  Access Paper or Ask Questions

Cross-Lingual Text Classification with Minimal Resources by Transferring a Sparse Teacher


Oct 06, 2020
Giannis Karamanolakis, Daniel Hsu, Luis Gravano

* Accepted to Findings of EMNLP 2020 (Long Paper) 

  Access Paper or Ask Questions

On the proliferation of support vectors in high dimensions


Sep 22, 2020
Daniel Hsu, Vidya Muthukumar, Ji Xu


  Access Paper or Ask Questions

Contrastive learning, multi-view redundancy, and linear models


Aug 24, 2020
Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu


  Access Paper or Ask Questions

Statistical Query Lower Bounds for Tensor PCA


Aug 10, 2020
Rishabh Dudeja, Daniel Hsu


  Access Paper or Ask Questions

Ensuring Fairness Beyond the Training Data


Jul 12, 2020
Debmalya Mandal, Samuel Deng, Suman Jana, Jeannette M. Wing, Daniel Hsu

* 18 pages, 3 figures 

  Access Paper or Ask Questions

Classification vs regression in overparameterized regimes: Does the loss function matter?


May 16, 2020
Vidya Muthukumar, Adhyyan Narang, Vignesh Subramanian, Mikhail Belkin, Daniel Hsu, Anant Sahai


  Access Paper or Ask Questions

Contrastive estimation reveals topic posterior information to linear models


Mar 04, 2020
Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu


  Access Paper or Ask Questions

A New Framework for Query Efficient Active Imitation Learning


Dec 30, 2019
Daniel Hsu


  Access Paper or Ask Questions

Weakly Supervised Attention Networks for Fine-Grained Opinion Mining and Public Health


Sep 30, 2019
Giannis Karamanolakis, Daniel Hsu, Luis Gravano

* Accepted for the 5th Workshop on Noisy User-generated Text (W-NUT 2019), held in conjunction with EMNLP 2019 

  Access Paper or Ask Questions

Privacy Accounting and Quality Control in the Sage Differentially Private ML Platform


Sep 06, 2019
Mathias Lecuyer, Riley Spahn, Kiran Vodrahalli, Roxana Geambasu, Daniel Hsu

* Extended version of a paper presented at the 27th ACM Symposium on Operating Systems Principles (SOSP '19) 

  Access Paper or Ask Questions

Leveraging Just a Few Keywords for Fine-Grained Aspect Detection Through Weakly Supervised Co-Training


Sep 01, 2019
Giannis Karamanolakis, Daniel Hsu, Luis Gravano

* Accepted to EMNLP 2019 

  Access Paper or Ask Questions

Unbiased estimators for random design regression


Jul 08, 2019
MichaƂ DereziƄski, Manfred K. Warmuth, Daniel Hsu


  Access Paper or Ask Questions

A gradual, semi-discrete approach to generative network training via explicit Wasserstein minimization


Jun 11, 2019
Yucheng Chen, Matus Telgarsky, Chao Zhang, Bolton Bailey, Daniel Hsu, Jian Peng

* Appears in ICML 2019 

  Access Paper or Ask Questions

A cryptographic approach to black box adversarial machine learning


Jun 07, 2019
Kevin Shi, Daniel Hsu, Allison Bishop


  Access Paper or Ask Questions

Diameter-based Interactive Structure Search


Jun 05, 2019
Christopher Tosh, Daniel Hsu

* Presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA 

  Access Paper or Ask Questions

How many variables should be entered in a principal component regression equation?


Jun 04, 2019
Ji Xu, Daniel Hsu


  Access Paper or Ask Questions

Two models of double descent for weak features


Mar 18, 2019
Mikhail Belkin, Daniel Hsu, Ji Xu


  Access Paper or Ask Questions

Reconciling modern machine learning and the bias-variance trade-off


Dec 28, 2018
Mikhail Belkin, Daniel Hsu, Siyuan Ma, Soumik Mandal


  Access Paper or Ask Questions

Benefits of over-parameterization with EM


Oct 26, 2018
Ji Xu, Daniel Hsu, Arian Maleki

* Accepted at NIPS 2018 

  Access Paper or Ask Questions

Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate


Oct 26, 2018
Mikhail Belkin, Daniel Hsu, Partha Mitra


  Access Paper or Ask Questions

Multi-period Time Series Modeling with Sparsity via Bayesian Variational Inference


Oct 23, 2018
Daniel Hsu


  Access Paper or Ask Questions

Certified Robustness to Adversarial Examples with Differential Privacy


Oct 07, 2018
Mathias Lecuyer, Vaggelis Atlidakis, Roxana Geambasu, Daniel Hsu, Suman Jana


  Access Paper or Ask Questions

Leveraged volume sampling for linear regression


Sep 05, 2018
MichaƂ DereziƄski, Manfred K. Warmuth, Daniel Hsu


  Access Paper or Ask Questions

Non-Gaussian information from weak lensing data via deep learning


May 01, 2018
Arushi Gupta, José Manuel Zorrilla Matilla, Daniel Hsu, Zoltån Haiman

* Phys. Rev. D 97, 103515 (2018) 
* 15 pages, 13 figures, accepted to PRD 

  Access Paper or Ask Questions

Linear regression without correspondence


Nov 07, 2017
Daniel Hsu, Kevin Shi, Xiaorui Sun


  Access Paper or Ask Questions

Anomaly Detection on Graph Time Series


Nov 01, 2017
Daniel Hsu


  Access Paper or Ask Questions