2 papers
cond-mat.dis-nn2026
Pruning-induced phases in fully-connected neural networks: the eumentia, the dementia, and the amentia
Haining Pan, Nakul Aggarwal, J. H. Pixley
Modern neural networks are heavily overparameterized, and pruning, which removes redundant neurons or connections, has emerged as a key approach to compressing them without sacrifi…
quant-ph2024
Discovering Factorization Surface of Quantum Spin Chains with Machine Learning
Nakul Aggarwal, Keshav Das Agarwal, Tanoy Kanti Konar +2
Entanglement in quantum many-body systems is required for a variety of quantum information tasks, making it crucial to identify the parameter space in which the ground state is ful…