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 Sitan Chen

Tight Bounds for Quantum State Certification with Incoherent Measurements


Apr 14, 2022
Sitan Chen, Brice Huang, Jerry Li, Allen Liu

* 55 pages, comments welcome 

  Access Paper or Ask Questions

Learning Polynomial Transformations


Apr 08, 2022
Sitan Chen, Jerry Li, Yuanzhi Li, Anru R. Zhang

* 121 pages, comments welcome 

  Access Paper or Ask Questions

Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks


Feb 10, 2022
Sitan Chen, Aravind Gollakota, Adam R. Klivans, Raghu Meka

* 24 pages, 1 figure, comments welcome 

  Access Paper or Ask Questions

Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs


Jan 18, 2022
Sitan Chen, Jerry Li, Yuanzhi Li, Raghu Meka

* 32 pages, 1 figure 

  Access Paper or Ask Questions

Quantum advantage in learning from experiments


Dec 01, 2021
Hsin-Yuan Huang, Michael Broughton, Jordan Cotler, Sitan Chen, Jerry Li, Masoud Mohseni, Hartmut Neven, Ryan Babbush, Richard Kueng, John Preskill, Jarrod R. McClean

* 6 pages, 17 figures + 46 page appendix; open-source code available at https://github.com/quantumlib/ReCirq/tree/master/recirq/qml_lfe 

  Access Paper or Ask Questions

Exponential separations between learning with and without quantum memory


Nov 18, 2021
Sitan Chen, Jordan Cotler, Hsin-Yuan Huang, Jerry Li

* 77 pages, 2 figures, many diagrams; accepted to FOCS 2021; v2: typos corrected 

  Access Paper or Ask Questions

Kalman Filtering with Adversarial Corruptions


Nov 11, 2021
Sitan Chen, Frederic Koehler, Ankur Moitra, Morris Yau

* 57 pages, comments welcome 

  Access Paper or Ask Questions

A Hierarchy for Replica Quantum Advantage


Nov 10, 2021
Sitan Chen, Jordan Cotler, Hsin-Yuan Huang, Jerry Li

* 3+17 pages, 2 figures 

  Access Paper or Ask Questions

Efficiently Learning Any One Hidden Layer ReLU Network From Queries


Nov 08, 2021
Sitan Chen, Adam R Klivans, Raghu Meka

* To appear in Advances in Neural Information Processing Systems (NeurIPS 2021) 

  Access Paper or Ask Questions

Toward Instance-Optimal State Certification With Incoherent Measurements


Feb 25, 2021
Sitan Chen, Jerry Li, Ryan O'Donnell

* 47 pages, comments welcome 

  Access Paper or Ask Questions

Symmetric Boolean Factor Analysis with Applications to InstaHide


Feb 02, 2021
Sitan Chen, Zhao Song, Runzhou Tao, Ruizhe Zhang


  Access Paper or Ask Questions

On InstaHide, Phase Retrieval, and Sparse Matrix Factorization


Nov 23, 2020
Sitan Chen, Zhao Song, Danyang Zhuo

* 29 pages 

  Access Paper or Ask Questions

Online and Distribution-Free Robustness: Regression and Contextual Bandits with Huber Contamination


Oct 08, 2020
Sitan Chen, Frederic Koehler, Ankur Moitra, Morris Yau

* 37 pages, 1 figure 

  Access Paper or Ask Questions

Learning Deep ReLU Networks Is Fixed-Parameter Tractable


Sep 28, 2020
Sitan Chen, Adam R. Klivans, Raghu Meka

* 39 pages 

  Access Paper or Ask Questions

Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Connections to Evolvability


Jun 08, 2020
Sitan Chen, Frederic Koehler, Ankur Moitra, Morris Yau

* 51 pages, comments welcome 

  Access Paper or Ask Questions

Learning Polynomials of Few Relevant Dimensions


Apr 28, 2020
Sitan Chen, Raghu Meka

* 64 pages 

  Access Paper or Ask Questions

Learning Structured Distributions From Untrusted Batches: Faster and Simpler


Feb 24, 2020
Sitan Chen, Jerry Li, Ankur Moitra

* 34 pages 

  Access Paper or Ask Questions

Learning Mixtures of Linear Regressions in Subexponential Time via Fourier Moments


Dec 16, 2019
Sitan Chen, Jerry Li, Zhao Song

* 83 pages, 1 figure 

  Access Paper or Ask Questions

Efficiently Learning Structured Distributions from Untrusted Batches


Nov 05, 2019
Sitan Chen, Jerry Li, Ankur Moitra

* 46 pages 

  Access Paper or Ask Questions

Learning Mixtures of Product Distributions via Higher Multilinear Moments


Mar 17, 2018
Sitan Chen, Ankur Moitra

* 57 pages, comments welcome 

  Access Paper or Ask Questions