Learning through atypical "phase transitions" in overparameterized
neural networks

v1v2 (latest)

Learning through atypical "phase transitions" in overparameterized neural networks

1 October 2021

Clarissa Lauditi

Enrico M. Malatesta

Gabriele Perugini

ArXiv (abs)PDF HTML

Papers citing "Learning through atypical "phase transitions" in overparameterized neural networks"

16 / 16 papers shown

Title
High-dimensional manifold of solutions in neural networks: insights from statistical physics Enrico M. Malatesta 114 4 0 20 Feb 2025
Exact full-RSB SAT/UNSAT transition in infinitely wide two-layer neural networks B. Annesi Enrico M. Malatesta Francesco Zamponi 92 3 0 09 Oct 2024
ClassiFIM: An Unsupervised Method To Detect Phase Transitions Victor Kasatkin E. Mozgunov Nicholas Ezzell Utkarsh Mishra Itay Hen Daniel Lidar 80 3 0 06 Aug 2024
Random Features Hopfield Networks generalize retrieval to previously unseen examples Silvio Kalaj Clarissa Lauditi Gabriele Perugini Carlo Lucibello Enrico M. Malatesta Matteo Negri AAML 76 9 0 08 Jul 2024
The twin peaks of learning neural networks Elizaveta Demyanenko Christoph Feinauer Enrico M. Malatesta Luca Saglietti 62 0 0 23 Jan 2024
Engineered Ordinary Differential Equations as Classification Algorithm (EODECA): thorough characterization and testing Raffaele Marino L. Buffoni Lorenzo Chicchi Lorenzo Giambagli Duccio Fanelli 98 1 0 22 Dec 2023
Complex Recurrent Spectral Network Lorenzo Chicchi Lorenzo Giambagli L. Buffoni Raffaele Marino Duccio Fanelli 67 6 0 12 Dec 2023
Stochastic Gradient Descent-like relaxation is equivalent to Metropolis dynamics in discrete optimization and inference problems Maria Chiara Angelini A. Cavaliere Raffaele Marino F. Ricci-Tersenghi 124 5 0 11 Sep 2023
Eight challenges in developing theory of intelligence Haiping Huang 98 7 0 20 Jun 2023
Phase transitions in the mini-batch size for sparse and dense two-layer neural networks Raffaele Marino F. Ricci-Tersenghi 110 15 0 10 May 2023
Typical and atypical solutions in non-convex neural networks with discrete and continuous weights Carlo Baldassi Enrico M. Malatesta Gabriele Perugini R. Zecchina MQ 92 13 0 26 Apr 2023
Storage and Learning phase transitions in the Random-Features Hopfield Model M. Negri Clarissa Lauditi Gabriele Perugini Carlo Lucibello Enrico M. Malatesta 28 16 0 29 Mar 2023
Inversion dynamics of class manifolds in deep learning reveals tradeoffs underlying generalisation Simone Ciceri Lorenzo Cassani Matteo Osella P. Rotondo P. Pizzochero M. Gherardi 76 7 0 09 Mar 2023
Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry Fabrizio Pittorino Antonio Ferraro Gabriele Perugini Christoph Feinauer Carlo Baldassi R. Zecchina 265 26 0 07 Feb 2022
Quantum Approximate Optimization Algorithm applied to the binary perceptron Pietro Torta G. Mbeng Carlo Baldassi R. Zecchina G. Santoro 44 8 0 19 Dec 2021
Equivalence between algorithmic instability and transition to replica symmetry breaking in perceptron learning systems Yang Zhao Junbin Qiu Mingshan Xie Haiping Huang 27 4 0 26 Nov 2021