Cover Image

On Reconstructing Training Data From Bayesian Posteriors and Trained Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Wynne, George
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Statistics Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

SPDE Methods for Nonparametric Bayesian Posterior Contraction and Laplace Approximation
by: Alberola-Boloix, Enric, et al.
Published: (2026)

Robust Bayesian Inference via Variational Approximations of Generalized Rho-Posteriors
by: Khribch, EL Mahdi, et al.
Published: (2026)

Provable Diffusion Posterior Sampling for Bayesian Inversion
by: Chang, Jinyuan, et al.
Published: (2025)

From Collapse to Improvement: Statistical Perspectives on the Evolutionary Dynamics of Iterative Training on Contaminated Sources
by: Bakshi, Soham, et al.
Published: (2026)

Posterior Concentration of Bayesian Physics-Informed Neural Networks for Elliptic PDEs
by: Zhao, Yuxuan, et al.
Published: (2026)

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

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data
by: Frei, Spencer, et al.
Published: (2022)

A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models
by: Suh, Namjoon, et al.
Published: (2024)

Training Diagonal Linear Networks with Stochastic Sharpness-Aware Minimization
by: Clara, Gabriel, et al.
Published: (2025)

Conformal Prediction Under Generalized Covariate Shift with Posterior Drift
by: Wang, Baozhen, et al.
Published: (2025)

Latent-IMH: Efficient Bayesian Inference for Inverse Problems with Approximate Operators
by: Chen, Youguang, et al.
Published: (2026)

Why Self-Training Helps and Hurts: Denoising vs. Signal Forgetting
by: Wu, Mingqi, et al.
Published: (2026)

Generalized Power Priors for Improved Bayesian Inference with Historical Data
by: Kimura, Masanari, et al.
Published: (2025)

Rates of Convergence of Generalised Variational Inference Posteriors under Prior Misspecification
by: Mildner, Terje, et al.
Published: (2025)

Posterior and variational inference for deep neural networks with heavy-tailed weights
by: Castillo, Ismaël, et al.
Published: (2024)

Posterior Contraction Rates for Sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces
by: Oh, Jeunghun, et al.
Published: (2026)

The Statistical Accuracy of Neural Posterior and Likelihood Estimation
by: Frazier, David T., et al.
Published: (2024)

Thermodynamic Response Functions in Singular Bayesian Models
by: Plummer, Sean
Published: (2026)

Training Implicit Generative Models via an Invariant Statistical Loss
by: de Frutos, José Manuel, et al.
Published: (2024)

Learning Dynamic Bayesian Networks from Data: Foundations, First Principles and Numerical Comparisons
by: Kungurtsev, Vyacheslav, et al.
Published: (2024)

Online Performance Estimation with Unlabeled Data: A Bayesian Application of the Hui-Walter Paradigm
by: Slote, Kevin, et al.
Published: (2024)

Post-Hoc Uncertainty Quantification in Pre-Trained Neural Networks via Activation-Level Gaussian Processes
by: Bergna, Richard, et al.
Published: (2025)

Bayesian Cramér-Rao Bound Estimation with Score-Based Models
by: Crafts, Evan Scope, et al.
Published: (2023)

Towards Bayesian Data Selection
by: Rodemann, Julian
Published: (2024)

Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training
by: Wang, Kevin, et al.
Published: (2026)

Asymptotic Behavior of Adversarial Training Estimator under $\ell_\infty$-Perturbation
by: Xie, Yiling, et al.
Published: (2024)

Diffusion Posterior Sampling is Computationally Intractable
by: Gupta, Shivam, et al.
Published: (2024)

Posterior Covariance Structures in Gaussian Processes
by: Cai, Difeng, et al.
Published: (2024)

A Quantitative Characterization of Forgetting in Post-Training
by: Balasubramanian, Krishnakumar, et al.
Published: (2026)

Conditional Generative Models are Provably Robust: Pointwise Guarantees for Bayesian Inverse Problems
by: Altekrüger, Fabian, et al.
Published: (2023)

Deep Bayesian Inversion
by: Adler, Jonas, et al.
Published: (2018)

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

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

On Quantification of Borrowing of Information in Hierarchical Bayesian Models
by: Ghosh, Prasenjit, et al.
Published: (2025)

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

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

The Coverage Principle: How Pre-Training Enables Post-Training
by: Chen, Fan, et al.
Published: (2025)

Susceptibilities and Patterning: A Primer on Linear Response in Bayesian Learning
by: Elliott, Chris, et al.
Published: (2026)

Sequential Bayesian Neural Subnetwork Ensembles
by: Jantre, Sanket, et al.
Published: (2022)