English
Related papers

Related papers: Gradient descent dynamics and the jamming transiti…

200 papers

Classical optimisation theory guarantees monotonic objective decrease for gradient descent (GD) when employed in a small step size, or ``stable", regime. In contrast, gradient descent on neural networks is frequently performed in a large…

Machine Learning · Computer Science 2025-10-21 Lachlan Ewen MacDonald , Hancheng Min , Leandro Palma , Salma Tarmoun , Ziqing Xu , René Vidal

The random Lorentz gas (RLG) is a minimal model of both percolation and glassiness, which leads to a paradox in the infinite-dimensional, $d\rightarrow\infty$ limit: the localization transition is then expected to be continuous for the…

Disordered Systems and Neural Networks · Physics 2021-06-18 Giulio Biroli , Patrick Charbonneau , Yi Hu , Harukuni Ikeda , Grzegorz Szamel , Francesco Zamponi

We consider an infinite lattice system of interacting spins living on a smooth compact manifold, with short- but not necessarily finite-range pairwise interactions. We construct the gradient flow of the infinite-volume free energy on the…

Probability · Mathematics 2025-02-19 Ronan Herry , Thomas Leblé

Various disordered dense systems such as foams, gels, emulsions and colloidal suspensions, exhibit a jamming transition from a liquid state (they flow) to a solid state below a yield stress. Their structure, thoroughly studied with powerful…

Soft Condensed Matter · Physics 2011-05-04 Guillaume Ovarlez , Quentin Barral , Philippe Coussot

This paper introduces the $(\alpha, \Gamma)$-descent, an iterative algorithm which operates on measures and performs $\alpha$-divergence minimisation in a Bayesian framework. This gradient-based procedure extends the commonly-used…

Statistics Theory · Mathematics 2021-10-25 Kamélia Daudel , Randal Douc , François Portier

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

For a system consisting of active soft spheres in three dimensions, we study the transition from a fluid where overlaps between particles can only occur for a short time after a collision to a state where clusters of overlapping particles…

Soft Condensed Matter · Physics 2019-06-28 Moumita Maiti , Michael Schmiedeberg

We report a surprising result, established by numerical simulations and analytical arguments for a one-dimensional lattice model of random sequential adsorption, that even an arbitrarily small imprecision in the lattice-site localization…

Statistical Mechanics · Physics 2016-07-12 Vladimir Privman , Han Yan

The criticality of the jamming transition responsible for amorphous solidification has been theoretically linked to the marginal stability of a thermodynamic Gardner phase. While the critical exponents of jamming appear independent of the…

Disordered Systems and Neural Networks · Physics 2023-06-23 Qinyi Liao , Ludovic Berthier , Hai-Jun Zhou , Ning Xu

We study the statistical mechanics and the equilibrium dynamics of a system of classical Heisenberg spins with frustrated interactions on a $d$-dimensional simple hypercubic lattice, in the limit of infinite dimensionality $d \to \infty$.…

Disordered Systems and Neural Networks · Physics 2024-04-25 Achille Mauri , Mikhail I. Katsnelson

This paper establishes risk convergence and asymptotic weight matrix alignment --- a form of implicit regularization --- of gradient flow and gradient descent when applied to deep linear networks on linearly separable data. In more detail,…

Machine Learning · Computer Science 2019-02-26 Ziwei Ji , Matus Telgarsky

Despite decades of work, gaining a first-principle understanding of amorphous materials remains an extremely challenging problem. However, recent theoretical breakthroughs have led to the formulation of an exact solution in the mean-field…

Disordered Systems and Neural Networks · Physics 2017-04-20 Patrick Charbonneau , Jorge Kurchan , Giorgio Parisi , Pierfrancesco Urbani , Francesco Zamponi

We study thermodynamics properties of a one dimensional gas of hard elongated particles. The particle centers are restricted to a line, while they can rotate in two-dimensional space. Correlations between orientations of the objects are…

Statistical Mechanics · Physics 2009-10-27 Yacov Kantor , Mehran Kardar

We study, using numerical simulations, the dynamical evolution of self-gravitating point particles in static euclidean space, starting from a simple class of infinite ``shuffled lattice'' initial conditions. These are obtained by applying…

Statistical Mechanics · Physics 2008-11-26 Thierry Baertschiger , Michael Joyce , Andrea Gabrielli , Francesco Sylos Labini

Collapse, or a gravitational-like phase transition is studied in a microcanonical ensemble of particles with an attractive $1/r^{\alpha}$ potential. A mean field continuous integral equation is used to determine a saddle-point density…

Statistical Mechanics · Physics 2007-05-23 I. Ispolatov , E. G. D. Cohen

We discuss the zero-temperature susceptibility of elastic manifolds with quenched randomness. It diverges with system size due to low-lying local minima. The distribution of energy gaps is deduced to be constant in the limit of vanishing…

Disordered Systems and Neural Networks · Physics 2009-10-31 E. T. Seppala , M. J. Alava

We develop an algorithm suitable for parallel molecular dynamics simulations in $d$ spatial dimensions and describe its implementation in C++. All routines work in arbitrary $d$; the maximum simulated $d$ is limited only by available…

Soft Condensed Matter · Physics 2022-05-18 Robert S. Hoy , Kevin A. Interiano-Alberto

We investigate the dynamics of overdamped $D$-dimensional systems of particles repulsively interacting through short-ranged power-law potentials, $V(r)\sim r^{-\lambda}\;(\lambda/D>1)$. We show that such systems obey a non-linear diffusion…

Statistical Mechanics · Physics 2018-10-03 André A. Moreira , César M. Vieira , Humberto A. Carmona , José S. Andrade , Constantino Tsallis

We present a finite-size scaling analysis of the droplet condensation-evaporation transition of a lattice gas (in two and three dimensions) and a Lennard-Jones gas (in three dimensions) at fixed density. Parallel multicanonical simulations…

Soft Condensed Matter · Physics 2015-08-04 Johannes Zierenberg , Wolfhard Janke

The usual thermodynamic limit for systems of classical self-gravitating point particles becomes well defined, as a {\it dynamical} problem, using a simple physical prescription for the calculation of the force, equivalent to the so-called…

Statistical Mechanics · Physics 2008-05-12 Michael Joyce