Copertina

Posterior and variational inference for deep neural networks with heavy-tailed weights

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Castillo, Ismaël, Egels, Paul
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Statistics Theory
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Heavy-tailed and Horseshoe priors for regression and sparse Besov rates
di: Agapiou, Sergios, et al.
Pubblicazione: (2025)

Causal inference through multi-stage learning and doubly robust deep neural networks
di: Zhang, Yuqian, et al.
Pubblicazione: (2024)

A variational Bayes approach to debiased inference for low-dimensional parameters in high-dimensional linear regression
di: Castillo, Ismaël, et al.
Pubblicazione: (2024)

On the VC dimension of deep group convolutional neural networks
di: Sepliarskaia, Anna, et al.
Pubblicazione: (2024)

Deep neural networks with dependent weights: Gaussian Process mixture limit, heavy tails, sparsity and compressibility
di: Lee, Hoil, et al.
Pubblicazione: (2022)

How many samples are needed to train a deep neural network?
di: Golestaneh, Pegah, et al.
Pubblicazione: (2024)

Semiparametric inference using fractional posteriors
di: L'Huillier, Alice, et al.
Pubblicazione: (2023)

The loss landscape of deep linear neural networks: a second-order analysis
di: Achour, El Mehdi, et al.
Pubblicazione: (2021)

PAC-Bayesian risk bounds for fully connected deep neural network with Gaussian priors
di: Mai, The Tien
Pubblicazione: (2025)

Nonlinear spiked covariance matrices and signal propagation in deep neural networks
di: Wang, Zhichao, et al.
Pubblicazione: (2024)

Gaussian mixture layers for neural networks
di: Chewi, Sinho, et al.
Pubblicazione: (2025)

On the rates of convergence for learning with convolutional neural networks
di: Yang, Yunfei, et al.
Pubblicazione: (2024)

Higher-order accurate two-sample network inference and network hashing
di: Shao, Meijia, et al.
Pubblicazione: (2022)

Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
di: Haas, Moritz, et al.
Pubblicazione: (2023)

A theoretical perspective on mode collapse in variational inference
di: Soletskyi, Roman, et al.
Pubblicazione: (2024)

Robust stochastic first order methods in heavy-tailed noise via medoid mini-batch gradient sampling
di: Vukovic, Manojlo, et al.
Pubblicazione: (2026)

Nonparametric regression using over-parameterized shallow ReLU neural networks
di: Yang, Yunfei, et al.
Pubblicazione: (2023)

Deep Horseshoe Gaussian Processes
di: Castillo, Ismaël, et al.
Pubblicazione: (2024)

Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space
di: Jiang, Yiheng, et al.
Pubblicazione: (2023)

High-dimensional robust regression under heavy-tailed data: Asymptotics and Universality
di: Adomaityte, Urte, et al.
Pubblicazione: (2023)

The surrogate Gibbs-posterior of a corrected stochastic MALA: Towards uncertainty quantification for neural networks
di: Bieringer, Sebastian, et al.
Pubblicazione: (2023)

Sliding down the stairs: how correlated latent variables accelerate learning with neural networks
di: Bardone, Lorenzo, et al.
Pubblicazione: (2024)

On Reconstructing Training Data From Bayesian Posteriors and Trained Models
di: Wynne, George
Pubblicazione: (2025)

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

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

Anytime-valid off-policy inference for contextual bandits
di: Waudby-Smith, Ian, et al.
Pubblicazione: (2022)

Adaptively-weighted Nearest Neighbors for Matrix Completion
di: Sadhukhan, Tathagata, et al.
Pubblicazione: (2025)

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

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

Statistical inference for pairwise comparison models
di: Han, Ruijian, et al.
Pubblicazione: (2024)

Variational inference via radial transport
di: Ghafourpour, Luca, et al.
Pubblicazione: (2026)

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

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

Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime
di: Camilli, Francesco, et al.
Pubblicazione: (2025)

Gaussian random field approximation via Stein's method with applications to wide random neural networks
di: Balasubramanian, Krishnakumar, et al.
Pubblicazione: (2023)

Convergence of coordinate ascent variational inference for log-concave measures via optimal transport
di: Arnese, Manuel, et al.
Pubblicazione: (2024)

Instance-dependent uniform tail bounds for empirical processes
di: Bahmani, Sohail
Pubblicazione: (2022)

ForwardFlow: Simulation only statistical inference using deep learning
di: Böhringer, Stefan
Pubblicazione: (2026)

Statistically guided deep learning
di: Kohler, Michael, et al.
Pubblicazione: (2025)

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