惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Google DeepMind News
Google DeepMind News
F
Fortinet All Blogs
量子位
G
Google Developers Blog
J
Java Code Geeks
N
Netflix TechBlog - Medium
博客园 - 聂微东
宝玉的分享
宝玉的分享
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
月光博客
月光博客
The Cloudflare Blog
Apple Machine Learning Research
Apple Machine Learning Research
爱范儿
爱范儿
雷峰网
雷峰网
M
MIT News - Artificial intelligence
T
Tailwind CSS Blog
V
Visual Studio Blog
阮一峰的网络日志
阮一峰的网络日志
博客园 - 三生石上(FineUI控件)
Microsoft Azure Blog
Microsoft Azure Blog
aimingoo的专栏
aimingoo的专栏
Martin Fowler
Martin Fowler
有赞技术团队
有赞技术团队
T
The Blog of Author Tim Ferriss

math.PR updates on arXiv.org

Visibility in the Boolean Model on Harmonic Manifolds Global estimates on the Brenier map Geodesics and Wandering Exponents in Brochette First-Passage Percolation State-dependent inverse-subordinator time changes of regenerative processes: Excursion structure and multiscale occupation-time limits Randomly twisted transfer operators and singular values statistics Generalized Bessel-Dunkl diffusions An almost sure invariance principle for the Takagi-van der Waerden class functions Central limit theorems for high dimensional lattice polytopes: cosmological polytopes Convergence rate estimates for semigroups and heat kernels associated with resistance forms Second-order Poincaré inequalities and localization on the Poisson space Maximum Probability of Independence in Transitive Matroids On global solutions to the semidiscrete stochastic heat equation The Poisson Tail Conjecture for primes in short intervals A Complete Spectral Analysis of the CEV Operator with Applications to Arbitrage Holographic functions and neural networks From Betting to Empirical Bernstein LIL Concentration of General Stochastic Approximation Under Heavy-Tailed Markovian Noise Pointwise Generalization in Deep Neural Networks Bayesian Latent Space Models for Graphs Are Misspecified: Toward Robust Inference via Generalized Posteriors Wasserstein bounds for denoising diffusion probabilistic models via the Föllmer process A note on connections between the Föllmer process and the denoising diffusion probabilistic model Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures Diffusion-Based Stochastic Operator Networks for Uncertainty Quantification in Stochastic Partial Differential Equations A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights Propagation of Chaos in Contextual Flow Maps Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures $α$-TCAV: A Unified Framework for Testing with Concept Activation Vectors Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model On the Limits of Latent Reuse in Diffusion Models State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives
Large deviations for trajectory observables of diffusion ...
Cecile Monthus · 2023-09-27 · via math.PR updates on arXiv.org

For diffusion processes in dimension $d>1$, the statistics of trajectory observables over the time-window $[0,T]$ can be studied via the Feynman-Kac deformations of the Fokker-Planck generator, that can be interpreted as euclidean non-hermitian electromagnetic quantum Hamiltonians. It is then interesting to compare the four regimes corresponding to the time $T$ either finite or large and to the diffusion coefficient $D$ either finite or small. (1) For finite $T$ and finite $D$, one needs to consider the full time-dependent quantum problem that involves the full spectrum of the Hamiltonian. (2) For large time $T \to + \infty$ and finite $D$, one only needs to consider the ground-state properties of the quantum Hamiltonian to obtain the generating function of rescaled cumulants and to construct the corresponding canonical conditioned processes. (3) For finite $T$ and $D \to 0$, one only needs to consider the dominant classical trajectory and its action satisfying the Hamilton-Jacobi equation, as in the semi-classical WKB approximation of quantum mechanics. (4) In the double limit $T \to + \infty$ and $D \to 0$, the simplifications in the large deviations in $\frac{T}{D}$ of trajectory observables can be analyzed via the two orders of limits, i.e. either from the limit $D \to 0$ of the ground-state properties of the quantum Hamiltonians of (2), or from the limit of long classical trajectories $T \to +\infty$ in the semi-classical WKB approximation of (3). This general framework is illustrated in dimension $d=2$ with rotational invariance.