Uri Cohen, PhD
@uricohen42.bsky.social
Theoretical computational neuroscience postdoc at Cambridge University - CBL lab (previously at the Hebrew University)
* Web: https://github.com/uricohen/
* Twitter: @uricohen42
* Web: https://github.com/uricohen/
* Twitter: @uricohen42
Reposted by Uri Cohen, PhD
(1/5) Fun fact: Several classic results in the stat. mech. of learning can be derived in a couple lines of simple algebra!
In this paper with Haim Sompolinsky, we simplify and unify derivations for high-dimensional convex learning problems using a bipartite cavity method.
arxiv.org/abs/2412.01110
In this paper with Haim Sompolinsky, we simplify and unify derivations for high-dimensional convex learning problems using a bipartite cavity method.
arxiv.org/abs/2412.01110
Simplified derivations for high-dimensional convex learning problems
Statistical physics provides tools for analyzing high-dimensional problems in machine learning and theoretical neuroscience. These calculations, particularly those using the replica method, often invo...
arxiv.org
December 3, 2024 at 7:34 PM
(1/5) Fun fact: Several classic results in the stat. mech. of learning can be derived in a couple lines of simple algebra!
In this paper with Haim Sompolinsky, we simplify and unify derivations for high-dimensional convex learning problems using a bipartite cavity method.
arxiv.org/abs/2412.01110
In this paper with Haim Sompolinsky, we simplify and unify derivations for high-dimensional convex learning problems using a bipartite cavity method.
arxiv.org/abs/2412.01110