English
Related papers

Related papers: Sampling from Spherical Spin Glasses in Total Vari…

200 papers

We show that Glauber dynamics for $ p$-spin glass mixes exponentially slowly at inverse temperatures larger than a constant times $ \ln (p)/p $ for large enough $ p $. This is done by analyzing the energy landscape using Gaussian…

Probability · Mathematics 2026-05-15 Anouar Kouraich , Simone Warzel

We develop a mean-field theory for random quantum spin systems using the spin coherent state path integral representation. After the model is reduced to the mean field one-body Hamiltonian, the integral is analyzed with the aid of several…

Disordered Systems and Neural Networks · Physics 2007-11-20 Kazutaka Takahashi

The pseudo-marginal algorithm is a popular variant of the Metropolis--Hastings scheme which allows us to sample asymptotically from a target probability density $\pi$, when we are only able to estimate an unnormalized version of $\pi$…

Computation · Statistics 2017-07-20 George Deligiannidis , Arnaud Doucet , Michael K. Pitt

We investigate the properties of the glass phase of a recently introduced spin glass model of soft spins subjected to an anharmonic quartic local potential, which serves as a model of low temperature molecular or soft glasses. We solve the…

Disordered Systems and Neural Networks · Physics 2025-11-11 Giampaolo Folena , Pierfrancesco Urbani

In this paper, we study the Crisanti-Sommers variational problem, which is a variational formula for the free energy of spherical mixed $p$-spin glasses. We begin by computing the dual of this problem using a min-max argument. We find that…

Probability · Mathematics 2018-08-06 Aukosh Jagannath , Ian Tobasco

We provide an algorithm for properly learning mixtures of two single-dimensional Gaussians without any separability assumptions. Given $\tilde{O}(1/\varepsilon^2)$ samples from an unknown mixture, our algorithm outputs a mixture that is…

Data Structures and Algorithms · Computer Science 2014-05-20 Constantinos Daskalakis , Gautam Kamath

Stochastic master equations are often used to describe conditional spin squeezing of atomic ensemble, but are limited so far to the systems with few atoms due to the exponentially increased Hilbert space. In this article, we present an…

Quantum Physics · Physics 2024-02-06 ZhiQing Zhang , Yuan Zhang , HaiZhong Guo , ChongXin Shan , Gang Chen , Klaus Mølmer

The use of parameters measuring order-parameter fluctuations (OPF) has been encouraged by the recent results reported in \cite{RS} which show that two of these parameters, $G$ and $G_c$, take universal values in the $\lim_{T\to 0}$. In this…

Disordered Systems and Neural Networks · Physics 2009-10-31 Marco Picco , Felix Ritort , Marta Sales

In the present paper we analyze the critical properties of a quantum spherical spin glass model with short range, random interactions. Since the model allows for rigorous detailed calculations, we can show how the effective partition…

Disordered Systems and Neural Networks · Physics 2008-06-10 Pedro Castro Menezes , Alba Theumann

In this paper, we present a flow-based method for global optimization of continuous Sobolev functions, called Stein Boltzmann Sampling (SBS). SBS initializes uniformly a number of particles representing candidate solutions, then uses the…

Optimization and Control · Mathematics 2025-02-21 Gaëtan Serré , Argyris Kalogeratos , Nicolas Vayatis

We introduce a new paradigm, $\textit{measure synchronization}$, for synchronizing graphs with measure-valued edges. We formulate this problem as maximization of the cycle-consistency in the space of probability measures over relative…

Computer Vision and Pattern Recognition · Computer Science 2020-04-03 Tolga Birdal , Michael Arbel , Umut Şimşekli , Leonidas Guibas

Recently, sharp results concerning the critical points of the Hamiltonian of the $p$-spin spherical spin glass model have been obtained by means of moments computations. In particular, these moments computations allow for the evaluation of…

Probability · Mathematics 2016-06-07 Eliran Subag , Ofer Zeitouni

We study $p$-spin glass models on regular random graphs. By analyzing the Franz-Parisi potential with a two-body cavity field approximation under the replica symmetric ansatz, we obtain a good approximation of the 1RSB transition…

Statistical Mechanics · Physics 2014-03-05 Masahiko Ueda , Shin-ichi Sasa

In this paper, the worst-case probability measure over the data is introduced as a tool for characterizing the generalization capabilities of machine learning algorithms. More specifically, the worst-case probability measure is a Gibbs…

Machine Learning · Computer Science 2023-12-20 Xinying Zou , Samir M. Perlaza , Iñaki Esnaola , Eitan Altman

In this paper we review the predictions of the replica approach on the probability distribution of the overlaps among replicas and on the sample to sample fluctuations of this probability. We stress the role of replica equivalence in…

Disordered Systems and Neural Networks · Physics 2007-05-23 Giorgio Parisi

Statistical models with constrained probability distributions are abundant in machine learning. Some examples include regression models with norm constraints (e.g., Lasso), probit, many copula models, and latent Dirichlet allocation (LDA).…

Computation · Statistics 2015-06-22 Shiwei Lan , Babak Shahbaba

We prove the existence of one-step replica symmetry breaking (1RSB) for the mean field Ising spin glasses at finite temperature and identify the first critical temperature in Gardner transition. Specifically, Gardner conjectured that for…

Probability · Mathematics 2024-09-11 Yuxin Zhou

We study the problem of determining the Hamiltonian of a fully connected Ising Spin Glass of $N$ units from a set of measurements, whose sizes needs to be ${\cal O}(N^2)$ bits. The student-teacher scenario, used to study learning in…

Disordered Systems and Neural Networks · Physics 2010-06-10 Silvia Kuva , Osame Kinouchi , Nestor Caticha

We introduce and analytically study a generalized p-spin glass like model that captures some of the main features of attractive glasses, recently found by Mode Coupling investigations, such as a glass/glass transition line and dynamical…

Statistical Mechanics · Physics 2009-11-10 Antonio Caiazzo , Antonio Coniglio , Mario Nicodemi

We give the first rigorous proof of the convergence of Riemannian Hamiltonian Monte Carlo, a general (and practical) method for sampling Gibbs distributions. Our analysis shows that the rate of convergence is bounded in terms of natural…

Data Structures and Algorithms · Computer Science 2017-10-18 Yin Tat Lee , Santosh S. Vempala