Saved in:
Bibliographic Details
Main Authors: Pomarico, Domenico, Monaco, Alfonso, Magnifico, Giuseppe, Lacalamita, Antonio, Pantaleo, Ester, Bellantuono, Loredana, Tangaro, Sabina, Maggipinto, Tommaso, La Rocca, Marianna, Picardi, Ernesto, Amoroso, Nicola, Pesole, Graziano, Stramaglia, Sebastiano, Bellotti, Roberto
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.10483
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909536738082816
author Pomarico, Domenico
Monaco, Alfonso
Magnifico, Giuseppe
Lacalamita, Antonio
Pantaleo, Ester
Bellantuono, Loredana
Tangaro, Sabina
Maggipinto, Tommaso
La Rocca, Marianna
Picardi, Ernesto
Amoroso, Nicola
Pesole, Graziano
Stramaglia, Sebastiano
Bellotti, Roberto
author_facet Pomarico, Domenico
Monaco, Alfonso
Magnifico, Giuseppe
Lacalamita, Antonio
Pantaleo, Ester
Bellantuono, Loredana
Tangaro, Sabina
Maggipinto, Tommaso
La Rocca, Marianna
Picardi, Ernesto
Amoroso, Nicola
Pesole, Graziano
Stramaglia, Sebastiano
Bellotti, Roberto
contents Grokking is a intriguing phenomenon in machine learning where a neural network, after many training iterations with negligible improvement in generalization, suddenly achieves high accuracy on unseen data. By working in the quantum-inspired machine learning framework based on tensor networks, we numerically prove that grokking phenomenon can be related to an entanglement dynamical transition in the underlying quantum many-body systems, consisting in a one-dimensional lattice with each site hosting a qubit. Two datasets are considered as use case scenarios, namely fashion MNIST and gene expression communities of hepatocellular carcinoma. In both cases, we train Matrix Product State (MPS) to perform binary classification tasks, and we analyse the learning dynamics. We exploit measurement of qubits magnetization and correlation functions in the MPS network as a tool to identify meaningful and relevant gene subcommunities, verified by means of enrichment procedures.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10483
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Grokking as an entanglement transition in tensor network machine learning
Pomarico, Domenico
Monaco, Alfonso
Magnifico, Giuseppe
Lacalamita, Antonio
Pantaleo, Ester
Bellantuono, Loredana
Tangaro, Sabina
Maggipinto, Tommaso
La Rocca, Marianna
Picardi, Ernesto
Amoroso, Nicola
Pesole, Graziano
Stramaglia, Sebastiano
Bellotti, Roberto
Quantum Physics
Grokking is a intriguing phenomenon in machine learning where a neural network, after many training iterations with negligible improvement in generalization, suddenly achieves high accuracy on unseen data. By working in the quantum-inspired machine learning framework based on tensor networks, we numerically prove that grokking phenomenon can be related to an entanglement dynamical transition in the underlying quantum many-body systems, consisting in a one-dimensional lattice with each site hosting a qubit. Two datasets are considered as use case scenarios, namely fashion MNIST and gene expression communities of hepatocellular carcinoma. In both cases, we train Matrix Product State (MPS) to perform binary classification tasks, and we analyse the learning dynamics. We exploit measurement of qubits magnetization and correlation functions in the MPS network as a tool to identify meaningful and relevant gene subcommunities, verified by means of enrichment procedures.
title Grokking as an entanglement transition in tensor network machine learning
topic Quantum Physics
url https://arxiv.org/abs/2503.10483