Copertina

Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dupuis, Benjamin, Şimşekli, Umut
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Rényi Differential Privacy for Heavy-Tailed SDEs via Fractional Poincaré Inequalities
di: Dupuis, Benjamin, et al.
Pubblicazione: (2025)

Generalization Bounds for Markov Algorithms through Entropy Flow Computations
di: Dupuis, Benjamin, et al.
Pubblicazione: (2025)

Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets
di: Dupuis, Benjamin, et al.
Pubblicazione: (2024)

Heavy-Tailed Diffusion with Denoising Lévy Probabilistic Models
di: Shariatian, Dario, et al.
Pubblicazione: (2024)

Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models
di: Dupuis, Benjamin, et al.
Pubblicazione: (2025)

Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms
di: Andreeva, Rayna, et al.
Pubblicazione: (2024)

Variational Inference for Lévy Process-Driven SDEs via Neural Tilting
di: Kindap, Yaman, et al.
Pubblicazione: (2026)

Stability, Complexity and Data-Dependent Worst-Case Generalization Bounds
di: Tuci, Mario, et al.
Pubblicazione: (2025)

Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
di: Wan, Yijun, et al.
Pubblicazione: (2023)

Heavy-Tail Phenomenon in Decentralized SGD
di: Gurbuzbalaban, Mert, et al.
Pubblicazione: (2022)

Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping
di: Şimşekli, Umut, et al.
Pubblicazione: (2024)

Tighter Generalisation Bounds via Interpolation
di: Viallard, Paul, et al.
Pubblicazione: (2024)

Algorithmic Stability of Stochastic Gradient Descent with Momentum under Heavy-Tailed Noise
di: Dang, Thanh, et al.
Pubblicazione: (2025)

A PAC-Bayesian Link Between Generalisation and Flat Minima
di: Haddouche, Maxime, et al.
Pubblicazione: (2024)

Generalization at the Edge of Stability
di: Tuci, Mario, et al.
Pubblicazione: (2026)

Latent-Augmented Discrete Diffusion Models
di: Shariatian, Dario, et al.
Pubblicazione: (2025)

Piecewise deterministic generative models
di: Bertazzi, Andrea, et al.
Pubblicazione: (2024)

Error Bounds for Physics-Informed Neural Networks in Fokker-Planck PDEs
di: Kong, Chun-Wei, et al.
Pubblicazione: (2024)

The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
di: Schaipp, Fabian, et al.
Pubblicazione: (2025)

FP-AbDiff: Improving Score-based Antibody Design by Capturing Nonequilibrium Dynamics through the Underlying Fokker-Planck Equation
di: Chen, Jiameng, et al.
Pubblicazione: (2025)

Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards
di: Tajdini, Artin, et al.
Pubblicazione: (2025)

An Analysis of Regularization and Fokker-Planck Residuals in Diffusion Models for Image Generation
di: Niemann, Onno, et al.
Pubblicazione: (2026)

On the Interaction of Compressibility and Adversarial Robustness
di: Barsbey, Melih, et al.
Pubblicazione: (2025)

Tracking the Median of Gradients with a Stochastic Proximal Point Method
di: Schaipp, Fabian, et al.
Pubblicazione: (2024)

Fokker-Planck to Callan-Symanzik: evolution of weight matrices under training
di: Bu, Wei, et al.
Pubblicazione: (2025)

Score-fPINN: Fractional Score-Based Physics-Informed Neural Networks for High-Dimensional Fokker-Planck-Levy Equations
di: Hu, Zheyuan, et al.
Pubblicazione: (2024)

Tail Annealing for Heavy-Tailed Flow Matching
di: Pachebat, Jean
Pubblicazione: (2026)

Neural Pushforward Samplers for the Fokker-Planck Equation on Embedded Riemannian Manifolds
di: He, Andrew Qing, et al.
Pubblicazione: (2026)

Probing Implicit Bias in Semi-gradient Q-learning: Visualizing the Effective Loss Landscapes via the Fokker--Planck Equation
di: Yin, Shuyu, et al.
Pubblicazione: (2024)

Stability and Generalization of Nonconvex Optimization with Heavy-Tailed Noise
di: Chen, Hongxu, et al.
Pubblicazione: (2026)

Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits
di: Tamás, Ambrus, et al.
Pubblicazione: (2024)

Score-Based Physics-Informed Neural Networks for High-Dimensional Fokker-Planck Equations
di: Hu, Zheyuan, et al.
Pubblicazione: (2024)

Heavy-Tailed Diffusion Models
di: Pandey, Kushagra, et al.
Pubblicazione: (2024)

Asynchronous Heavy-Tailed Optimization
di: Sun, Junfei, et al.
Pubblicazione: (2026)

Adaptive Probability Flow Residual Minimization for High-Dimensional Fokker-Planck Equations
di: Wu, Xiaolong, et al.
Pubblicazione: (2025)

Time Asymptotics and Scaling Limits for a Nonlocal Fokker-Planck Equation with Heavy-Tailed Kernel
di: Tassi, Niccolò
Pubblicazione: (2026)

DNN-Based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel
di: Dupuis, Benjamin, et al.
Pubblicazione: (2021)

Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
di: Gourevitch, Samson, et al.
Pubblicazione: (2026)

Heavy-Tailed Principal Component Analysis
di: Sayde, Mario, et al.
Pubblicazione: (2026)

Models of Heavy-Tailed Mechanistic Universality
di: Hodgkinson, Liam, et al.
Pubblicazione: (2025)