Image de couverture de livre

On Reconstructing Training Data From Bayesian Posteriors and Trained Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Wynne, George
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Statistics Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Fourier representation of kernel Stein discrepancy with application to Goodness-of-Fit tests for measures on infinite dimensional Hilbert spaces
par: Wynne, George, et autres
Publié: (2022)

SPDE Methods for Nonparametric Bayesian Posterior Contraction and Laplace Approximation
par: Alberola-Boloix, Enric, et autres
Publié: (2026)

Robust Bayesian Inference via Variational Approximations of Generalized Rho-Posteriors
par: Khribch, EL Mahdi, et autres
Publié: (2026)

Provable Diffusion Posterior Sampling for Bayesian Inversion
par: Chang, Jinyuan, et autres
Publié: (2025)

From Collapse to Improvement: Statistical Perspectives on the Evolutionary Dynamics of Iterative Training on Contaminated Sources
par: Bakshi, Soham, et autres
Publié: (2026)

Posterior Concentration of Bayesian Physics-Informed Neural Networks for Elliptic PDEs
par: Zhao, Yuxuan, et autres
Publié: (2026)

Source-Optimal Training is Transfer-Suboptimal
par: Hedges, C. Evans
Publié: (2025)

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data
par: Frei, Spencer, et autres
Publié: (2022)

A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models
par: Suh, Namjoon, et autres
Publié: (2024)

Training Diagonal Linear Networks with Stochastic Sharpness-Aware Minimization
par: Clara, Gabriel, et autres
Publié: (2025)

Conformal Prediction Under Generalized Covariate Shift with Posterior Drift
par: Wang, Baozhen, et autres
Publié: (2025)

Latent-IMH: Efficient Bayesian Inference for Inverse Problems with Approximate Operators
par: Chen, Youguang, et autres
Publié: (2026)

Why Self-Training Helps and Hurts: Denoising vs. Signal Forgetting
par: Wu, Mingqi, et autres
Publié: (2026)

Generalized Power Priors for Improved Bayesian Inference with Historical Data
par: Kimura, Masanari, et autres
Publié: (2025)

Rates of Convergence of Generalised Variational Inference Posteriors under Prior Misspecification
par: Mildner, Terje, et autres
Publié: (2025)

Posterior and variational inference for deep neural networks with heavy-tailed weights
par: Castillo, Ismaël, et autres
Publié: (2024)

Posterior Contraction Rates for Sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces
par: Oh, Jeunghun, et autres
Publié: (2026)

The Statistical Accuracy of Neural Posterior and Likelihood Estimation
par: Frazier, David T., et autres
Publié: (2024)

Thermodynamic Response Functions in Singular Bayesian Models
par: Plummer, Sean
Publié: (2026)

Training Implicit Generative Models via an Invariant Statistical Loss
par: de Frutos, José Manuel, et autres
Publié: (2024)

Learning Dynamic Bayesian Networks from Data: Foundations, First Principles and Numerical Comparisons
par: Kungurtsev, Vyacheslav, et autres
Publié: (2024)

Online Performance Estimation with Unlabeled Data: A Bayesian Application of the Hui-Walter Paradigm
par: Slote, Kevin, et autres
Publié: (2024)

Post-Hoc Uncertainty Quantification in Pre-Trained Neural Networks via Activation-Level Gaussian Processes
par: Bergna, Richard, et autres
Publié: (2025)

Bayesian Cramér-Rao Bound Estimation with Score-Based Models
par: Crafts, Evan Scope, et autres
Publié: (2023)

Towards Bayesian Data Selection
par: Rodemann, Julian
Publié: (2024)

Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training
par: Wang, Kevin, et autres
Publié: (2026)

Asymptotic Behavior of Adversarial Training Estimator under $\ell_\infty$-Perturbation
par: Xie, Yiling, et autres
Publié: (2024)

Diffusion Posterior Sampling is Computationally Intractable
par: Gupta, Shivam, et autres
Publié: (2024)

Posterior Covariance Structures in Gaussian Processes
par: Cai, Difeng, et autres
Publié: (2024)

A Quantitative Characterization of Forgetting in Post-Training
par: Balasubramanian, Krishnakumar, et autres
Publié: (2026)

Conditional Generative Models are Provably Robust: Pointwise Guarantees for Bayesian Inverse Problems
par: Altekrüger, Fabian, et autres
Publié: (2023)

Deep Bayesian Inversion
par: Adler, Jonas, et autres
Publié: (2018)

Sharp Generalization for Nonparametric Regression in Interpolation Space by Over-Parameterized Neural Networks Trained with Preconditioned Gradient Descent and Early Stopping
par: Yang, Yingzhen, et autres
Publié: (2024)

Linear Convergence of Diffusion Models Under the Manifold Hypothesis
par: Potaptchik, Peter, et autres
Publié: (2024)

On Quantification of Borrowing of Information in Hierarchical Bayesian Models
par: Ghosh, Prasenjit, et autres
Publié: (2025)

Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions
par: Azangulov, Iskander, et autres
Publié: (2024)

Training and Testing with Multiple Splits: A Central Limit Theorem for Split-Sample Estimators
par: Fava, Bruno
Publié: (2025)

The Coverage Principle: How Pre-Training Enables Post-Training
par: Chen, Fan, et autres
Publié: (2025)

Susceptibilities and Patterning: A Primer on Linear Response in Bayesian Learning
par: Elliott, Chris, et autres
Publié: (2026)

Sequential Bayesian Neural Subnetwork Ensembles
par: Jantre, Sanket, et autres
Publié: (2022)