Maithra Raghu

Senior Research Scientist, Google Brain

Joined

September 2016

Names

Maithra Raghu (Preferred)

Emails

****@gmail.com (Confirmed)

Personal Links

Homepage

Google Scholar

Career & Education History

Senior Research Scientist

Google Brain (cornell.edu)

Present

Advisors, Relations & Conflicts

No relations added

Expertise

Machine Learning

Deep Learning

Representation Learning

Medicine

Healthcare

Present

Publications

On the Origins of the Block Structure Phenomenon in Neural Network Representations
Thao Nguyen, Maithra Raghu, Simon Kornblith
- Accepted by TMLR
- Readers: Everyone
Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures
Emmanuel Abbe, Samy Bengio, Elisabetta Cornacchia, Jon Kleinberg, Aryo Lotfi, Maithra Raghu, Chiyuan Zhang
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone
Dominant Datapoints and the Block Structure Phenomenon in Neural Network Hidden Representations
Thao Nguyen, Maithra Raghu, Simon Kornblith
- Published: 28 Jan 2022, Last Modified: 13 Feb 2023
- ICLR 2022 Submitted
- Readers: Everyone
Do Vision Transformers See Like Convolutional Neural Networks?
Maithra Raghu, Thomas Unterthiner, Simon Kornblith, Chiyuan Zhang, Alexey Dosovitskiy
- Published: 09 Nov 2021, Last Modified: 05 May 2023
- NeurIPS 2021 Poster
- Readers: Everyone
Do Vision Transformers See Like Convolutional Neural Networks?
Maithra Raghu, Thomas Unterthiner, Simon Kornblith, Chiyuan Zhang, Alexey Dosovitskiy
- Published: 09 Nov 2021, Last Modified: 05 May 2023
- NeurIPS 2021 Poster
- Readers: Everyone
Teaching with Commentaries
Aniruddh Raghu, Maithra Raghu, Simon Kornblith, David Duvenaud, Geoffrey Hinton
- Published: 12 Jan 2021, Last Modified: 12 Oct 2025
- ICLR 2021 Poster
- Readers: Everyone
Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth
Thao Nguyen, Maithra Raghu, Simon Kornblith
- Published: 12 Jan 2021, Last Modified: 18 Jul 2023
- ICLR 2021 Poster
- Readers: Everyone
Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
Vinay Venkatesh Ramasesh, Ethan Dyer, Maithra Raghu
- Published: 12 Jan 2021, Last Modified: 12 Oct 2025
- ICLR 2021 Poster
- Readers: Everyone
Direct Uncertainty Prediction for Medical Second Opinions
Maithra Raghu, Katy Blumer, Rory Sayres, Ziad Obermeyer, Robert D. Kleinberg, Sendhil Mullainathan, Jon M. Kleinberg
- 2019 (modified: 11 Nov 2022)
- ICML 2019
- Readers: Everyone
Insights on representational similarity in neural networks with canonical correlation
Ari S. Morcos, Maithra Raghu, Samy Bengio
- 2018 (modified: 11 Nov 2022)
- NeurIPS 2018
- Readers: Everyone

View all 14 publications

Co-Authors

View all 33 co-authors