English
Related papers

Related papers: Score Reversal Is Not Free for Quantum Diffusion M…

200 papers

Classical reverse diffusion is generated by changing the drift at fixed noise. We show that the quantum version of this principle obeys an exact law with a sharp phase boundary. For Gaussian pure-loss dynamics -- the canonical model of…

Quantum Physics · Physics 2026-03-20 Ammar Fayad

The ensemble-averaged dynamics of open quantum systems are typically irreversible. We show that this irreversibility need not hold at the level of individually monitored quantum trajectories. Our main results are analytical stochastic…

Quantum Physics · Physics 2025-12-23 Einar Gabbassov

Diffusion models generate high-quality synthetic data. They operate by defining a continuous-time forward process which gradually adds Gaussian noise to data until fully corrupted. The corresponding reverse process progressively "denoises"…

We consider the problem of reversing quantum dynamics, with the goal of preserving an initial state's quantum entanglement or classical correlation with a reference system. We exhibit an approximate reversal operation, adapted to the…

Quantum Physics · Physics 2026-01-21 H. Barnum , E. Knill

Standard diffusion models involve an image transform -- adding Gaussian noise -- and an image restoration operator that inverts this degradation. We observe that the generative behavior of diffusion models is not strongly dependent on the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-22 Arpit Bansal , Eitan Borgnia , Hong-Min Chu , Jie S. Li , Hamid Kazemi , Furong Huang , Micah Goldblum , Jonas Geiping , Tom Goldstein

Recent diffusion models have achieved promising performances in audio-denoising tasks. The unique property of the reverse process could recover clean signals. However, the distribution of real-world noises does not comply with a single…

Sound · Computer Science 2024-06-14 Pu Wang , Junhui Li , Jialu Li , Liangdong Guo , Youshan Zhang

Diffusion models have recently attained significant interest within the community owing to their strong performance as generative models. Furthermore, its application to inverse problems have demonstrated state-of-the-art performance.…

Image and Video Processing · Electrical Eng. & Systems 2022-03-22 Hyungjin Chung , Byeongsu Sim , Jong Chul Ye

Based on the modelling of quantum systems with the aid of (classical) non-equilibrium thermodynamics, both the emergence and the collapse of the superposition principle are understood within one and the same framework. Both are shown to…

Quantum Physics · Physics 2010-08-31 Gerhard Groessing , Siegfried Fussy , Johannes Mesa Pascasio , Herbert Schwabl

Generative diffusion models synthesize new samples by reversing a diffusive process that converts a given data set to generic noise. This is accomplished by training a neural network to match the gradient of the log of the probability…

Machine Learning · Computer Science 2023-10-11 Akhil Premkumar

Typical generative diffusion models rely on a Gaussian diffusion process for training the backward transformations, which can then be used to generate samples from Gaussian noise. However, real world data often takes place in discrete-state…

Machine Learning · Computer Science 2023-05-19 Javier E Santos , Zachary R. Fox , Nicholas Lubbers , Yen Ting Lin

By modelling quantum systems as emerging from a (classical) sub-quantum thermodynamics, the quantum mechanical "decay of the wave packet" is shown to simply result from sub-quantum diffusion with a specific diffusion coefficient varying in…

General Physics · Physics 2011-08-30 Gerhard Groessing , Siegfried Fussy , Johannes Mesa Pascasio , Herbert Schwabl

We propose an efficient framework for amortized conditional inference by leveraging exact conditional score-guided diffusion models to train a non-reversible neural network as a conditional generative model. Traditional normalizing flow…

Computational Engineering, Finance, and Science · Computer Science 2025-06-24 Zezhong Zhang , Caroline Tatsuoka , Dongbin Xiu , Guannan Zhang

Diffusion models have become fundamental tools for modeling data distributions in machine learning. Despite their success, these models face challenges when generating data with extreme brightness values, as evidenced by limitations…

Machine Learning · Statistics 2026-04-10 Takuro Kutsuna

Generative models realized with machine learning techniques are powerful tools to infer complex and unknown data distributions from a finite number of training samples in order to produce new synthetic data. Diffusion models are an emerging…

Quantum Physics · Physics 2024-07-18 Marco Parigi , Stefano Martina , Filippo Caruso

We study the spreading of a quantum-mechanical wavepacket in a one-dimensional tight-binding model with a noisy potential, and analyze the emergence of classical diffusion from the quantum dynamics due to decoherence. We consider a finite…

Quantum Physics · Physics 2015-05-13 Ariel Amir , Yoav Lahini , Hagai B. Perets

Diffusion models have become the de facto framework for generating new datasets. The core of these models lies in the ability to reverse a diffusion process in time. The goal of this manuscript is to explain, from a PDE perspective, how…

Probability · Mathematics 2025-01-29 Fei Cao , Kimball Johnston , Thomas Laurent , Justin Le , Sébastien Motsch

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

Diffusion models generate samples by incrementally reversing a process that turns data into noise. We show that when the step size goes to zero, the reversed process is invariant to the distribution of these increments. This reveals a…

Machine Learning · Computer Science 2024-12-12 Henry Li

We present a concise, self-contained derivation of diffusion-based generative models. Starting from basic properties of Gaussian distributions (densities, quadratic expectations, re-parameterisation, products, and KL divergences), we…

Machine Learning · Computer Science 2025-11-18 Sepehr Maleki , Negar Pourmoazemi

Denoising diffusion models are a popular class of generative models providing state-of-the-art results in many domains. One adds gradually noise to data using a diffusion to transform the data distribution into a Gaussian distribution.…

Machine Learning · Computer Science 2023-08-21 Francisco Vargas , Will Grathwohl , Arnaud Doucet
‹ Prev 1 2 3 10 Next ›