57 citations · 139 across the 10 of their papers we have counts for
10 papers
Daydreaming Hopfield Networks and their surprising effectiveness on correlated data
Ludovica Serricchio, Dario Bocchi, Claudio Chilin +4
To improve the storage capacity of the Hopfield model, we develop a version of the dreaming algorithm that perpetually reinforces the patterns to be stored (as in the Hebb rule), a…
Stochastic Gradient Descent-like relaxation is equivalent to Metropolis dynamics in discrete optimization and inference problems
Maria Chiara Angelini, Angelo Giorgio Cavaliere, Raffaele Marino +1
Is Stochastic Gradient Descent (SGD) substantially different from Metropolis Monte Carlo dynamics? This is a fundamental question at the time of understanding the most used trainin…
Phase transitions in the mini-batch size for sparse and dense two-layer neural networks
Raffaele Marino, Federico Ricci-Tersenghi
The use of mini-batches of data in training artificial neural networks is nowadays very common. Despite its broad usage, theories explaining quantitatively how large or small the o…
Hard Optimization Problems have Soft Edges
Raffaele Marino, Scott Kirkpatrick
Finding a Maximum Clique is a classic property test from graph theory; find any one of the largest complete subgraphs in an Erdös-Rényi G(N, p) random graph. We use Maximum Clique…
Nonequilibrium Monte Carlo for unfreezing variables in hard combinatorial optimization
Masoud Mohseni, Daniel Eppens, Johan Strumpfer +7
Optimizing highly complex cost/energy functions over discrete variables is at the heart of many open problems across different scientific disciplines and industries. A major obstac…
Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
Nicolas Macris, Raffaele Marino
Non-linear partial differential Kolmogorov equations are successfully used to describe a wide range of time dependent phenomena, in natural sciences, engineering or even finance. F…
Learning from Survey Propagation: a Neural Network for MAX-E--SAT
Raffaele Marino
Many natural optimization problems are NP-hard, which implies that they are probably hard to solve exactly in the worst-case. However, it suffices to get reasonably good solutions…
Large independent sets on random -regular graphs with fixed degree
Raffaele Marino, Scott Kirkpatrick
This paper presents a linear prioritized local algorithm that computes large independent sets on a random -regular graph with small and fixed degree . We studied experimental…
Revisiting the Challenges of MaxClique
Raffaele Marino, Scott Kirkpatrick
The MaxClique problem, finding the largest complete subgraph in an Erd{ö}s-R{é}nyi random graph in the large limit, is a well-known example of a simple problem for whi…
The backtracking survey propagation algorithm for solving random K-SAT problems
Raffaele Marino, Giorgio Parisi, Federico Ricci-Tersenghi
Discrete combinatorial optimization has a central role in many scientific disciplines, however, for hard problems we lack linear time algorithms that would allow us to solve very l…