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 Chi-Heng Lin

Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity


Nov 03, 2021
Ran Liu, Mehdi Azabou, Max Dabagia, Chi-Heng Lin, Mohammad Gheshlaghi Azar, Keith B. Hengen, Michal Valko, Eva L. Dyer

* To be published in Neurips 2021 

  Access Paper or Ask Questions

Escaping Saddle Points Faster with Stochastic Momentum


Jun 05, 2021
Jun-Kun Wang, Chi-Heng Lin, Jacob Abernethy

* Accepted at ICLR 2020 

  Access Paper or Ask Questions

Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction


Feb 19, 2021
Mehdi Azabou, Mohammad Gheshlaghi Azar, Ran Liu, Chi-Heng Lin, Erik C. Johnson, Kiran Bhaskaran-Nair, Max Dabagia, Keith B. Hengen, William Gray-Roncal, Michal Valko, Eva L. Dyer


  Access Paper or Ask Questions

Making transport more robust and interpretable by moving data through a small number of anchor points


Dec 21, 2020
Chi-Heng Lin, Mehdi Azabou, Eva L. Dyer


  Access Paper or Ask Questions

Bayesian optimization for modular black-box systems with switching costs


Jun 04, 2020
Chi-Heng Lin, Joseph D. Miano, Eva L. Dyer


  Access Paper or Ask Questions