Andres Potapczynski

According to our database, Andres Potapczynski authored at least 10 papers between 2020 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices.

Andres Potapczynski, Shikai Qiu, Marc Finzi, Christopher Ferri, Zixi Chen, Micah Goldblum, C. Bayan Bruss, Christopher De Sa, Andrew Gordon Wilson

CoRR, 2024

Compute Better Spent: Replacing Dense Layers with Structured Matrices.

Shikai Qiu, Andres Potapczynski, Marc Anton Finzi, Micah Goldblum, Andrew Gordon Wilson

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra.

Andres Potapczynski, Marc Finzi, Geoff Pleiss, Andrew Gordon Wilson

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Simple and Fast Group Robustness by Automatic Feature Reweighting.

Shikai Qiu, Andres Potapczynski, Pavel Izmailov, Andrew Gordon Wilson

Proceedings of the International Conference on Machine Learning, 2023

A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks.

Marc Anton Finzi, Andres Potapczynski, Matthew Choptuik, Andrew Gordon Wilson

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

On the Normalizing Constant of the Continuous Categorical Distribution.

Elliott Gordon-Rodríguez, Gabriel Loaiza-Ganem, Andres Potapczynski, John P. Cunningham

CoRR, 2022

Low-precision arithmetic for fast Gaussian processes.

Wesley J. Maddox, Andres Potapczynski, Andrew Gordon Wilson

Proceedings of the Uncertainty in Artificial Intelligence, 2022

PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization.

Sanae Lotfi, Marc Finzi, Sanyam Kapoor, Andres Potapczynski, Micah Goldblum, Andrew Gordon Wilson

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Bias-Free Scalable Gaussian Processes via Randomized Truncations.

Andres Potapczynski, Luhuan Wu, Dan Biderman, Geoff Pleiss, John P. Cunningham

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax.

Andres Potapczynski, Gabriel Loaiza-Ganem, John P. Cunningham

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020