English
Related papers

Related papers: The Feedback Hamiltonian is the Score Function: A …

200 papers

We consider a quantum system driven out of equilibrium via a small Hamiltonian perturbation. Building on the paradigmatic framework of linear response theory (LRT), we derive an expression for the full generating function of the dissipated…

Quantum Physics · Physics 2024-08-28 Giacomo Guarnieri , Jens Eisert , Harry J. D. Miller

Recently, variational quantum metrology was proposed for Hamiltonians with multiplicative parameters, wherein the estimation precision can be optimized via variational circuits. However, systems with generic Hamiltonians still lack these…

Quantum Physics · Physics 2023-09-25 Le Bin Ho

Denoising diffusion models are a class of generative models which have recently achieved state-of-the-art results across many domains. Gradual noise is added to the data using a diffusion process, which transforms the data distribution into…

Machine Learning · Statistics 2024-06-28 Francisco Vargas , Teodora Reu , Anna Kerekes , Michael M Bronstein

Diffusion models have led to significant advancements in generative modelling. Yet their widespread adoption poses challenges regarding data attribution and interpretability. In this paper, we aim to help address such challenges in…

Machine Learning · Computer Science 2025-05-27 Bruno Mlodozeniec , Runa Eschenhagen , Juhan Bae , Alexander Immer , David Krueger , Richard Turner

Consider a probability measure on a Hilbert space defined via its density with respect to a Gaussian. The purpose of this paper is to demonstrate that an appropriately defined Markov chain, which is reversible with respect to the measure in…

Statistics Theory · Mathematics 2014-04-21 Natesh S. Pillai , Andrew M. Stuart , Alexandre H. Thiery

Here, we provide a unified framework for numerical analysis of stochastic nonlinear fractional diffusion equation driven by fractional Gaussian noise with Hurst index $H\in(0,1)$. A novel estimate of the second moment of the stochastic…

Numerical Analysis · Mathematics 2021-04-29 Daxin Nie , Weihua Deng

Enabled by rapidly developing quantum technologies, it is possible to network quantum systems at a much larger scale in the near future. To deal with non-Markovian dynamics that is prevalent in solid-state devices, we propose a general…

Quantum Physics · Physics 2014-12-18 Re-Bing Wu , Jing Zhang , Yu-xi Liu , Tzyh-Jong Tarn

Derivation of two-time second-order correlation function by following approaches such as stochastic differential equation, coherent-state propagator, and quasi-statistical distribution function is presented. In the process, the time…

Quantum Physics · Physics 2024-06-18 Sintayehu Tesfa

This paper introduces Discrete Markov Probabilistic Models (DMPMs), a novel discrete diffusion algorithm for discrete data generation. The algorithm operates in discrete bit space, where the noising process is a continuous-time Markov chain…

Machine Learning · Statistics 2025-10-09 Le-Tuyet-Nhi Pham , Dario Shariatian , Antonio Ocello , Giovanni Conforti , Alain Durmus

We investigate the problem of determining the Hamiltonian of a locally interacting open-quantum system. To do so, we construct model estimators based on inverting a set of stationary, or dynamical, Heisenberg-Langevin equations of motion…

Quantum Physics · Physics 2020-08-19 Eugene F. Dumitrescu , Pavel Lougovski

A generalisation of Takens' delay-coordinate embedding theorem to stochastic systems, the Stochastic Embedding Sufficiency Theorem, is an inverse methodology enabling non-parametric recovery of both drift and diffusion fields from scalar…

Statistical Mechanics · Physics 2026-05-12 Carolina Garcia , Lucía Perea Durán , Agnese Venezia , Alex Conradie

This work introduces a sampling method capable of solving Bayesian inverse problems in function space. It does not assume the log-concavity of the likelihood, meaning that it is compatible with nonlinear inverse problems. The method…

Machine Learning · Statistics 2024-05-27 Lorenzo Baldassari , Ali Siahkoohi , Josselin Garnier , Knut Solna , Maarten V. de Hoop

Using the quantum Hamiltonian for a gravitational system with boundary, we find the partition function and derive the resulting thermodynamics. The Hamiltonian is the boundary term required by functional differentiability of the action for…

General Relativity and Quantum Cosmology · Physics 2009-11-07 Seth A. Major , Kevin L. Setter

The AMIAS/RISE framework formulates emission tomography as a probabilistic inverse problem in which reconstructed images are sampled from a distribution defined by the measurement model and counting statistics. In this work we present a…

Diffusion models are routinely guided in practice by combining multiple score fields, yet the mathematical structure of score mixing is still poorly understood. We study the small-time generation dynamics driven by mixed scores $$…

Optimization and Control · Mathematics 2026-05-13 Kang Liu , Enrique Zuazua

Score-based Generative Models (SGMs) approximate a data distribution by perturbing it with Gaussian noise and subsequently denoising it via a learned reverse diffusion process. These models excel at modeling complex data distributions and…

Machine Learning · Computer Science 2025-09-23 Stefano Bruno , Sotirios Sabanis

Score-based diffusion models have recently emerged as state-of-the-art generative models for a variety of data modalities. Nonetheless, it remains unclear how to adapt these models to generate long multivariate time series. Viewing a time…

Machine Learning · Computer Science 2025-02-28 Barbora Barancikova , Zhuoyue Huang , Cristopher Salvi

The smoothing distribution is the conditional distribution of the diffusion process in the space of trajectories given noisy observations made continuously in time. It is generally difficult to sample from this distribution. We use the…

Probability · Mathematics 2025-03-07 Oskar Eklund , Annika Lang , Moritz Schauer

Diffusion models have emerged as the principal paradigm for generative modeling across various domains. During training, they learn the score function, which in turn is used to generate samples at inference. They raise a basic yet unsolved…

Machine Learning · Computer Science 2025-10-03 Kiwhan Song , Jaeyeon Kim , Sitan Chen , Yilun Du , Sham Kakade , Vincent Sitzmann

We investigate the effective behaviour of a small transversal perturbation of order $\epsilon$ to a completely integrable stochastic Hamiltonian system, by which we mean a stochastic differential equation whose diffusion vector fields are…

Probability · Mathematics 2021-10-11 Xue-Mei Li