11 citations · 21 across the 11 of their papers we have counts for
4 papers · 1 filter
Learning the Geometry of Materials Space with Trained Neural Tangent Kernels
Daniel Kaplan, Gabriel Kotliar, Anirvan M Sengupta
Neural networks trained to predict materials properties learn representations whose physical content can be difficult to extract. We use the neural tangent kernel (NTK), evaluated…
Flexible Online Representation Learning Based on Similarity Matching
Shagesh Sridharan, Yanis Bahroun, Anirvan M. Sengupta
Sparse high-dimensional representations are conducive to uncovering nontrivial structures in unsupervised exploration of data. Such a representation can deal with the dense connect…
Attention as In-Context Empirical Bayes: A Two-Stage View via Particle Dynamics
Matthew Smart, Soumya Ganguly, Nilava Metya +2
We study minimal attention-only transformers under all-token corruption and show they admit a two-stage empirical Bayes interpretation. A single attention step computes a kernel-we…
Beyond Variational Bias: Resolving Intertwined Orders in the Hubbard Model
Luciano Loris Viteritti, Riccardo Rende, Christopher Roth +3
The two-dimensional Hubbard model at finite doping hosts competing or intertwined orders, resulting in conflicting conclusions from different computational approaches regarding its…