Scholar
Andrew Gordon Wilson
Google Scholar ID: twWX2LIAAAAJ
New York University
Citations & Impact
Citations
22,969
H-index
61
i10-index
127
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- Published multiple papers, such as 'PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization' (Sanae Lotfi, Marc Finzi, Sanyam Kapoor, Andres Potapczynski, Micah Goldblum, Andrew Gordon Wilson, NeurIPS, 2022); 'Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors' (Ravid Shwartz-Ziv, Micah Goldblum, Hossein Souri, Sanyam Kapoor, Chen Zhu, Yann LeCun, Andrew Gordon Wilson, NeurIPS, 2022); 'On Feature Learning in the Presence of Spurious Correlations' (Pavel Izmailov, Polina Kirichenko, Nate Gruver, Andrew Gordon Wilson, NeurIPS, 2022); 'On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification' (Sanyam Kapoor, Wesley Maddox, Pavel Izmailov, Andrew Gordon Wilson, NeurIPS, 2022); 'Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers' (Wanqian Yang, Polina Kirichenko, Micah Goldblum, Andrew Gordon Wilson, NeurIPS, 2022); 'Bayesian Model Selection, the Marginal Likelihood, and Generalization' (Sanae Lotfi, Pavel Izmailov, Gregory Benton, Micah Goldblum, Andrew Gordon Wilson, ICML, 2022), which won an Outstanding Paper Award.
Research Experience
- Research areas include understanding deep learning models, uncertainty representation, distribution shifts, encoding and learning inductive biases, linear algebra as a foundation for ML, machine learning for physics, simple practical methods, and scientific discovery.
Education
- Professor at Courant Institute of Mathematical Sciences and Center for Data Science, New York University.
Background
- Research Interests: theory and empirical science of deep learning; Areas of expertise: understanding deep learning models, uncertainty representation, distribution shifts, encoding and learning inductive biases, linear algebra as a foundation for ML, machine learning for physics, simple practical methods, scientific discovery.
Miscellany
- A classical pianist outside of work, particularly enjoying Glenn Gould's playing of Bach. Contact: andrewgw@cims.nyu.edu, on Bluesky and Twitter as @andrewgwils.