English
Related papers

Related papers: Non-equilibrium active noise enhances generative m…

200 papers

With increasing communication rates via quantum channels, memory effects become unavoidable whenever the use rate of the channel is comparable to the typical relaxation time of the channel environment. We introduce a model of a bosonic…

Quantum Physics · Physics 2015-03-17 Cosmo Lupo , Vittorio Giovannetti , Stefano Mancini

We propose self-diffusion, a novel framework for solving inverse problems without relying on pretrained generative models. Traditional diffusion-based approaches require training a model on a clean dataset to learn to reverse the forward…

Machine Learning · Computer Science 2025-12-09 Guanxiong Luo , Shoujin Huang , Yanlong Yang

A noise source model, consisting of a pulse sequence at random times with memory, is presented. By varying the memory we can obtain variable randomness of the stochastic process. The delay time between pulses, i. e. the noise memory,…

Statistical Mechanics · Physics 2009-09-29 O. Chichigina , D. Valenti , B. Spagnolo

Living cells are known to generate non-Gaussian active fluctuations significantly larger than thermal fluctuations owing to various active processes. Understanding the effect of these active fluctuations on various physicochemical…

Soft Condensed Matter · Physics 2022-07-26 Govind Paneru , Jin Tae Park , Hyuk Kyu Pak

It has been generally recognized that stochasticity can play an important role in the information processing accomplished by reaction networks in biological cells. Most treatments of that stochasticity employ Gaussian noise even though it…

Molecular Networks · Quantitative Biology 2015-05-30 Neda Bostani , David A. Kessler , Nadav M. Shnerb , Wouter-Jan Rappel , Herbert Levine

Active fluids generate spontaneous, often chaotic mesoscale flows. Harnessing these flows to drive embedded soft materials into structures with controlled length scales and lifetimes is a key challenge at the interface between the fields of…

Soft Condensed Matter · Physics 2025-02-19 Layne B. Frechette , Aparna Baskaran , Michael F. Hagan

Memory effects arise in many complex systems, from protein folding, to the spreading of epidemics and financial decisions. While so-called non-Markovian dynamics is common in larger systems with interacting components, observations in…

Diffusion models generate high-quality samples but can also memorize training data, raising serious privacy concerns. Understanding the mechanisms governing when memorization versus generalization occurs remains an active area of research.…

Machine Learning · Computer Science 2026-02-23 Nick Dodson , Xinyu Gao , Qingsong Wang , Yusu Wang , Zhengchao Wan

Diffusion-based Deep Generative Models (DDGMs) offer state-of-the-art performance in generative modeling. Their main strength comes from their unique setup in which a model (the backward diffusion process) is trained to reverse the forward…

Machine Learning · Computer Science 2022-06-02 Kamil Deja , Anna Kuzina , Tomasz Trzciński , Jakub M. Tomczak

Non-Markovian dynamics are characterized by information backflows, where the evolving open quantum system retrieves part of the information previously lost in the environment. Hence, the very definition of non-Markovianity implies an…

Quantum Physics · Physics 2023-09-27 Dario De Santis

Stochastic point processes with refractoriness appear frequently in the quantitative analysis of physical and biological systems, such as the generation of action potentials by nerve cells, the release and reuptake of vesicles at a synapse,…

Probability · Mathematics 2015-07-28 Moritz Deger , Moritz Helias , Stefano Cardanobile , Fatihcan M. Atay , Stefan Rotter

Diffusion models have emerged as powerful generative frameworks by progressively adding noise to data through a forward process and then reversing this process to generate realistic samples. While these models have achieved strong…

Machine Learning · Computer Science 2025-03-04 Xingzhuo Guo , Yu Zhang , Baixu Chen , Haoran Xu , Jianmin Wang , Mingsheng Long

The Brownian motion of microscopic particles is driven by the collisions with the molecules of the surrounding fluid. The noise associated with these collisions is not white, but coloured due, e.g., to the presence of hydrodynamic memory.…

Statistical Mechanics · Physics 2012-10-04 Scott Hottovy , Giovanni Volpe , Jan Wehr

Probabilistic regression models the entire predictive distribution of a response variable, offering richer insights than classical point estimates and directly allowing for uncertainty quantification. While diffusion-based generative models…

Machine Learning · Computer Science 2025-10-07 Carlo Kneissl , Christopher Bülte , Philipp Scholl , Gitta Kutyniok

Quantum memory effects can be related to a bidirectional exchange of information between an open system and its environment, which in turn modifies the state and dynamical behavior of the last one. Nevertheless, non-Markovianity can also be…

Quantum Physics · Physics 2021-01-26 Adrián A. Budini

The effect of a change of noise amplitudes in overdamped diffusive systems is linked to their unperturbed behavior by means of a nonequilibrium fluctuation-response relation. This formula holds also for systems with state-independent…

Statistical Mechanics · Physics 2017-06-13 Cem Yolcu , Antoine Bérut , Gianmaria Falasco , Artyom Petrosyan , Sergio Ciliberto , Marco Baiesi

We study memory dependent binary-state dynamics, focusing on the noisy-voter model. This is a non-Markovian process if we consider the set of binary states of the population as the description variables, or Markovian if we incorporate…

Physics and Society · Physics 2020-02-25 Antonio F. Peralta , Nagi Khalil , Raul Toral

Generative diffusion models have recently emerged as a leading approach for generating high-dimensional data. In this paper, we show that the dynamics of these models exhibit a spontaneous symmetry breaking that divides the generative…

Machine Learning · Computer Science 2023-10-27 Gabriel Raya , Luca Ambrogioni

Diffusion models generate data by learning to reverse a forward process, where samples are progressively perturbed with Gaussian noise according to a predefined noise schedule. From a geometric perspective, each noise schedule corresponds…

Image and Video Processing · Electrical Eng. & Systems 2025-10-21 Teng Zhang , Hongxu Jiang , Kuang Gong , Wei Shao

We analyze the thermodynamic structure of jump diffusions combining Brownian and Poisson noise, a class of stochastic dynamics relevant to nonequilibrium statistical physics. For such nonlocal dynamics, the free energy admits a full…

Statistical Mechanics · Physics 2025-12-09 Shuyuan Fan , Qi Zhang