Xiyu Zhai

Postdoc, Allen School of Computing, University of Washington

Joined

November 2018

Names

Xiyu Zhai (Preferred)

Emails

****@mit.edu (Confirmed)

****@gmail.com (Confirmed)

Personal Links

DBLP

Career & Education History

Postdoc

Allen School of Computing, University of Washington (uw.edu)

2024 – 2026

PhD student

EECS, Massachusetts Institute of Technology (mit.edu)

2018 – 2024

Advisors, Relations & Conflicts

Postdoc Advisor

Simon Shaolei Du

2024 – 2026

PhD Advisor

Alexander Rakhlin

2018 – 2024

Expertise

programming language

2019 – 2026

deep learning theory

2017 – 2019

Publications

Transformers are Efficient Compilers, Provably
Xiyu Zhai, Runlong Zhou, Liao Zhang, Simon Shaolei Du
- COLM 2025
- Readers: Everyone
Transformers are Efficient Compilers, Provably
Xiyu Zhai, Runlong Zhou, Liao Zhang, Simon Shaolei Du
- M3L Poster
- Readers: Everyone
Transformers are Efficient Compilers, Provably
Xiyu Zhai, Runlong Zhou, Liao Zhang, Alexander Rakhlin, Simon Shaolei Du
- Submitted to ICLR 2025
- Readers: Everyone
On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels
Tengyuan Liang, Alexander Rakhlin, Xiyu Zhai
- Published: 01 Jan 2020, Last Modified: 26 Apr 2023
- COLT 2020
- Readers: Everyone
Gradient Descent Finds Global Minima of Deep Neural Networks
Simon S. Du, Jason D. Lee, Haochuan Li, Liwei Wang, Xiyu Zhai
- 2019 (modified: 11 Nov 2022)
- ICML 2019
- Readers: Everyone
On the Risk of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels
Tengyuan Liang, Alexander Rakhlin, Xiyu Zhai
- Published: 01 Jan 2019, Last Modified: 26 Apr 2023
- CoRR 2019
- Readers: Everyone
Consistency of Interpolation with Laplace Kernels is a High-Dimensional Phenomenon
Alexander Rakhlin, Xiyu Zhai
- Published: 01 Jan 2019, Last Modified: 26 Apr 2023
- COLT 2019
- Readers: Everyone
Gradient Descent Provably Optimizes Over-parameterized Neural Networks
Simon S. Du, Xiyu Zhai, Barnabás Póczos, Aarti Singh
- Published: 01 Jan 2019, Last Modified: 26 Apr 2023
- ICLR (Poster) 2019
- Readers: Everyone
How Many Samples are Needed to Estimate a Convolutional Neural Network?
Simon S. Du, Yining Wang, Xiyu Zhai, Sivaraman Balakrishnan, Ruslan R. Salakhutdinov, Aarti Singh
- 2018 (modified: 11 Nov 2022)
- NeurIPS 2018
- Readers: Everyone
How Many Samples are Needed to Learn a Convolutional Neural Network?
Simon S. Du, Yining Wang, Xiyu Zhai, Sivaraman Balakrishnan, Ruslan Salakhutdinov, Aarti Singh
- 2018 (modified: 26 Apr 2023)
- CoRR 2018
- Readers: Everyone

View all 15 publications