Tom Goldstein
· EmeritusVerifiedUniversity of California, Berkeley · Journalism
Active 1983–2024
Research topics
- Artificial Intelligence
- Computer Science
- Visual arts
- Art
- Human–computer interaction
Selected publications
A Cookbook of Self-Supervised Learning
arXiv (Cornell University) · 2023 · 161 citations
- Computer Science
- Artificial Intelligence
- Computer Science
Self-supervised learning, dubbed the dark matter of intelligence, is a promising path to advance machine learning. Yet, much like cooking, training SSL methods is a delicate art with a high barrier to entry. While many components are familiar, successfully training a SSL method involves a dizzying set of choices from the pretext tasks to training hyper-parameters. Our goal is to lower the barrier to entry into SSL research by laying the foundations and latest SSL recipes in the style of a cookbook. We hope to empower the curious researcher to navigate the terrain of methods, understand the role of the various knobs, and gain the know-how required to explore how delicious SSL can be.
Recent grants
AitF: EXPL: Collaborative Research: Approximate Discrete Programming for Real-Time Systems
NSF · $216k · 2015–2019
Non-convex Variational Image Processing: Boosting Classical Methods with Machine Learning
NSF · $198k · 2019–2022
Frequent coauthors
- 120 shared
Micah Goldblum
- 108 shared
Christoph Studer
ETH Zurich
- 72 shared
Jonas Geiping
- 49 shared
Liam Fowl
- 38 shared
Oscar Castañeda
- 33 shared
Sven Jacobsson
Ericsson (Sweden)
- 31 shared
Avi Schwarzschild
- 31 shared
John P. Dickerson
University of Maryland, College Park
Similar researchers at University of California, Berkeley
- Resume-aware match score
- Save to shortlist
- AI-drafted outreach
See your match with Tom Goldstein
PhdFit ranks faculty by your research interests, methods, and publications — grounded in their actual work, not templates.
- Free to start
- No credit card
- 30-second signup