Projects per year
Fingerprint
Dive into the research topics where Boris Hanin is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Collaborations and top research areas from the last five years
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
-
Conference: 2026 Princeton Machine Learning Theory Summer School
Hanin, B. (PI)
NSF - National Science Foundation
8/1/26 → 7/31/27
Project: Research project
-
Career: Random Neural Nets and Random Matrix Products
Hanin, B. (PI)
NSF - National Science Foundation
6/1/22 → 5/31/27
Project: Research project
-
Principles for Cheap and Flexible AI Evaluation
Hanin, B. (PI)
Defense Advanced Research Projects Agncy
6/25/25 → 9/23/25
Project: Research project
-
Collaborative Research: Probabilistic, Geometric, and Topological Analysis of Neural Networks, From Theory to Applications
Hanin, B. (PI)
NSF - National Science Foundation
1/1/22 → 12/31/25
Project: Research project
-
Random Neural Networks
Hanin, B. (PI)
NSF - National Science Foundation
8/1/20 → 5/31/23
Project: Research project
-
Deep neural nets as Hamiltonians
Winer, M. & Hanin, B., Jan 2026, In: Physical Review E. 113, 1, 015303.Research output: Contribution to journal › Article › peer-review
-
Gibbs Measures from Deep Shaped Multilayer Perceptrons
Hanin, B. & Zlokapa, A., Feb 13 2026, In: Physical review letters. 136, 6, 067301.Research output: Contribution to journal › Article › peer-review
1 Link opens in a new tab Scopus citations -
Don't be lazy: CompleteP enables compute-efficient deep transformers
Dey, N., Zhang, B. C., Noci, L., Li, M., Bordelon, B., Bergsma, S., Pehlevan, C., Hanin, B. & Hestness, J., 2025, 39th Conference on Neural Information Processing Systems, NeurIPS 2025. Neural information processing systems foundation, p. 152786-152818 33 p. (Advances in Neural Information Processing Systems; vol. 38).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
-
Principles for Initialization and Architecture Selection in Graph Neural Networks with ReLU Activations
DeZoort, G. & Hanin, B., 2025, In: SIAM Journal on Mathematics of Data Science. 7, 1, p. 1-27 27 p.Research output: Contribution to journal › Article › peer-review
Open Access1 Link opens in a new tab Scopus citations -
Quantitative CLTs in deep neural networks
Favaro, S., Hanin, B., Marinucci, D., Nourdin, I. & Peccati, G., Apr 2025, In: Probability Theory and Related Fields. 191, 3, p. 933-977 45 p.Research output: Contribution to journal › Article › peer-review
13 Link opens in a new tab Scopus citations