Scholar
Avi Schwarzschild
Google Scholar ID: toRWjDUAAAAJ
Postdoc, Carnegie Mellon University
Citations & Impact
Citations
3,916
H-index
19
i10-index
24
Publications
20
Co-authors
4
list available
Publications
Resume (English only)
Academic Achievements
- His Ph.D. research included work on adversarial attacks and data poisoning, as well as the ability of neural networks to extrapolate from easy training tasks to more difficult problems at test time.
Research Experience
- Researcher at Arthur AI in New York City from June 2022 to March 2023; During his Ph.D., his work spanned from security to generalization and broadly focused on expanding our understanding of when and why neural networks work.
Education
- Ph.D. in Applied Math and Scientific Computation from the University of Maryland in 2023, advised by Tom Goldstein; Bachelor's degree in Applied Math from Columbia Engineering; Master's degree in Applied Math from the University of Washington.
Background
- Research interests: safe and secure ML as well as reasoning in AI systems. Brief introduction: trying to learn about deep learning faster than deep learning can learn about me.
Miscellany
- Contact: avis4k@gmail.com; Links provided for Google Scholar, Twitter, GitHub, and CV.
