Copertina

Generalization Bounds for Markov Algorithms through Entropy Flow Computations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dupuis, Benjamin, Haddouche, Maxime, Deligiannidis, George, Simsekli, Umut
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models
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)

Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equation
di: Dupuis, Benjamin, et al.
Pubblicazione: (2024)

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

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

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

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

Federated Learning with Nonvacuous Generalisation Bounds
di: Jobic, Pierre, et al.
Pubblicazione: (2023)

Error Bounds for Flow Matching Methods
di: Benton, Joe, et al.
Pubblicazione: (2023)

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

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

Sequential Off-Policy Learning with Logarithmic Smoothing
di: Haddouche, Maxime, et al.
Pubblicazione: (2025)

Online (Non-)Convex Learning via Tempered Optimism
di: Haddouche, Maxime, et al.
Pubblicazione: (2023)

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

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

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

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

From Denoising Diffusions to Denoising Markov Models
di: Benton, Joe, et al.
Pubblicazione: (2022)

Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization
di: Benton, Joe, et al.
Pubblicazione: (2023)

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

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

Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis
di: Farghly, Tyler, et al.
Pubblicazione: (2025)

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

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

Ranking In Generalized Linear Bandits
di: Shidani, Amitis, et al.
Pubblicazione: (2022)

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

Schrödinger Bridge Matching for Tree-Structured Costs and Entropic Wasserstein Barycentres
di: Howard, Samuel, et al.
Pubblicazione: (2025)

On the Expected Size of Conformal Prediction Sets
di: Dhillon, Guneet S., et al.
Pubblicazione: (2023)

Beyond Real Data: Synthetic Data through the Lens of Regularization
di: Shidani, Amitis, et al.
Pubblicazione: (2025)

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)

Generalisation under gradient descent via deterministic PAC-Bayes
di: Clerico, Eugenio, et al.
Pubblicazione: (2022)

Drift Estimation for Stochastic Differential Equations with Denoising Diffusion Models
di: Costa, Marcos Tapia, et al.
Pubblicazione: (2026)

Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions
di: Azangulov, Iskander, et al.
Pubblicazione: (2024)

Linear Convergence of Diffusion Models Under the Manifold Hypothesis
di: Potaptchik, Peter, et al.
Pubblicazione: (2024)

Online Decision-Focused Learning
di: Capitaine, Aymeric, et al.
Pubblicazione: (2025)

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

Differentiable Cost-Parameterized Monge Map Estimators
di: Howard, Samuel, et al.
Pubblicazione: (2024)

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

Unconventional Computing based on Four Wave Mixing in Highly Nonlinear Waveguides
di: Sozos, Kostas, et al.
Pubblicazione: (2024)