2

SynPAT: A System for Generating Synthetic Physical Theories with Data
Machine-assisted methods for discovering new physical laws of nature, starting from a given background theory and data, have recently …
Karan Srivastava, Jonathan Lenchner, Joao Goncalves, Lior Horesh
PDF Cite DOI
Generative Modeling for Mathematical Discovery
We present a new implementation of the LLM-driven genetic algorithm {\it funsearch}, whose aim is to generate examples of interest to …
Karan Srivastava, Jordan S. Ellenberg, Cristofero S. Fraser-Taliente, Thomas R. Harvey, Andrew V. Sutherland
PDF Cite DOI
A Perturbation Bound on the Subspace Estimator from Canonical Projections
Given only the noisy projections of a subspace U onto lower dimensions, we give a method of reconstructing U based on previous work and an upper bound on the error of estimation alongside experiments.
Karan Srivastava, Daniel Pimentel-Alarcón
PDF Cite DOI