English
Related papers

Related papers: The geometry of jamming algorithms in the random L…

200 papers

Given the fundamental importance of combinatorial optimization across many diverse application domains, there has been widespread interest in the development of unconventional physical computing architectures that can deliver better…

Disordered Systems and Neural Networks · Physics 2023-09-18 Atsushi Yamamura , Hideo Mabuchi , Surya Ganguli

The multiple scattering model of a quantum particle in a random Lorentz gas consisting of fixed point scatterers is considered in arbitrary dimension. An efficient method is developed to numerically compute the map of the density of…

Quantum Physics · Physics 2022-05-11 David Gaspard , Jean-Marc Sparenberg

Network models with latent geometry have been used successfully in many applications in network science and other disciplines, yet it is usually impossible to tell if a given real network is geometric, meaning if it is a typical element in…

Statistical Mechanics · Physics 2016-05-23 Dmitri Krioukov

The inherent structure landscape for a system of hard spheres confined to a hard cylindrical channel, such that spheres can only contact their first and second neighbours, is studied using an analytical model that extends previous results…

Soft Condensed Matter · Physics 2021-12-15 Mahdi Zarif , Raymond J. Spiteri , Richard K. Bowles

An efficient algorithm is developed to construct disconnectivity graphs by a random walk over basins of attraction. This algorithm can detect a large number of local minima, find energy barriers between them, and estimate local thermal…

Statistical Mechanics · Physics 2011-08-08 Qing Zhou

The energy landscape picture is a central tool to study many-body systems. In particular, the energy landscapes of glass-forming liquids, jammed packings, constraint satisfaction problems, or neural networks contain a plethora of minima…

Statistical Mechanics · Physics 2025-12-17 Praharsh Suryadevara , Mathias Casiulis , Stefano Martiniani

Deep neural networks are workhorse models in machine learning with multiple layers of non-linear functions composed in series. Their loss function is highly non-convex, yet empirically even gradient descent minimisation is sufficient to…

Disordered Systems and Neural Networks · Physics 2020-03-18 Simon Becker , Yao Zhang , Alpha A. Lee

Tensor network methods are powerful tools for studying quantum many-body systems. In this paper, we investigate the emergent statistical properties of random high-dimensional tensor-network states and the trainability of variational tensor…

Quantum Physics · Physics 2023-05-23 Zidu Liu , Qi Ye , Li-Wei Yu , L. -M. Duan , Dong-Ling Deng

In this chapter, we identify fundamental geometric structures that underlie the problems of sampling, optimisation, inference and adaptive decision-making. Based on this identification, we derive algorithms that exploit these geometric…

An exact description of the complete jamming landscape is developed for a system of hard discs of diameter $\sigma$, confined between two lines separated by a distance $1+\sqrt{3/4} < H/\sigma < 2$. By considering all possible local packing…

Soft Condensed Matter · Physics 2015-05-13 S. S. Ashwin , Richard k. Bowles

According to the mean-field glass theory, the (free) energy landscape of disordered systems is hierarchical and ultrametric if they belong to the full-replica-symmetry-breaking universality class. However, examining this theoretical picture…

Soft Condensed Matter · Physics 2025-12-23 Shuonan Wu , Yuchen Xie , Deng Pan , Lei Zhang , Yuliang Jin

We study partition of networks into basins of attraction based on a steepest ascent search for the node of highest degree. Each node is associated with, or "attracted" to its neighbor of maximal degree, as long as the degree is increasing.…

Disordered Systems and Neural Networks · Physics 2008-12-30 Shai Carmi , P. L. Krapivsky , Daniel ben-Avraham

Despite the tremendous success of Stochastic Gradient Descent (SGD) algorithm in deep learning, little is known about how SGD finds generalizable solutions in the high-dimensional weight space. By analyzing the learning dynamics and loss…

Data Analysis, Statistics and Probability · Physics 2020-01-07 Yu Feng , Yuhai Tu

We study a family of parametric statistical models based on gamma distributions, which do give realistic descriptions for other stochastic porous media. Gamma distributions contain as a special case the exponential distributions, which…

Astrophysics · Physics 2016-08-30 C. T. J. Dodson

The structural properties of dense random packings of identical hard spheres (HS) are investigated. The bond order parameter method is used to obtain detailed information on the local structural properties of the system for different…

Soft Condensed Matter · Physics 2015-05-27 B. A. Klumov , S. A. Khrapak , G. E. Morfill

The local geometry of high dimensional neural network loss landscapes can both challenge our cherished theoretical intuitions as well as dramatically impact the practical success of neural network training. Indeed recent works have observed…

Machine Learning · Computer Science 2019-10-15 Stanislav Fort , Surya Ganguli

High-dimensional random landscapes underlie phenomena as diverse as glassy physics and optimization in machine learning, and even their simplest toy models already display extraordinarily rich behavior. This thesis aims to deepen our…

Disordered Systems and Neural Networks · Physics 2025-10-28 Alessandro Pacco

Fundamental limits to predictability are central to our understanding of many physical and computational systems. Here we show that, despite its remarkable capabilities, deep learning exhibits such fundamental limits rooted in the fractal,…

Machine Learning · Computer Science 2025-10-08 Andrew Ly , Pulin Gong

Generalized Ising models, also known as cluster expansions, are an important tool in many areas of condensed-matter physics and materials science, as they are often used in the study of lattice thermodynamics, solid-solid phase transitions,…

Statistical Mechanics · Physics 2016-06-27 Wenxuan Huang , Daniil Kitchaev , Stephen Dacek , Ziqin Rong , Zhiwei Ding , Gerbrand Ceder

Many deep generative models are defined as a push-forward of a Gaussian measure by a continuous generator, such as Generative Adversarial Networks (GANs) or Variational Auto-Encoders (VAEs). This work explores the latent space of such deep…

Machine Learning · Computer Science 2023-05-16 Thibaut Issenhuth , Ugo Tanielian , Jérémie Mary , David Picard
‹ Prev 1 2 3 10 Next ›