General theory for Big Bayes

Autori: Veronicka Rockova; Judith Rousseau
Pubblicato in: 2021
Editore: arxiv
DOI: 10.48550/arxiv.2105.12793

Mean-field Behaviour of Neural Tangent Kernel for Deep Neural Networks

Autori: Soufiane Hayou, Arnaud Doucet, Judith Rousseau
Pubblicato in: 2020
Editore: arxiv
DOI: 10.48550/arxiv.1905.13654

Minimax rates without the fixed sample size assumption

Autori: Alisa Kirichenko, Peter Grünwald
Pubblicato in: 2020
Editore: Arxiv

Efficient Bayesian estimation and use of cut posterior in semiparametric hidden Markov models

Autori: Daniel Moss Judith Rousseau
Pubblicato in: 2022
Editore: Arxiv

Evidence estimation in finite and infinite mixture models and applications

Autori: Adrien Hairault; Christian P. Robert, Judith Rousseau
Pubblicato in: 2022
Editore: arxiv
DOI: 10.48550/arxiv.2205.05416

Imposing Gaussian Pre-Activations in a Neural Network

Autori: Pierre Wolinsky, Julyan Arbel
Pubblicato in: 2022
Editore: arxiv
DOI: 10.48550/arxiv.2205.12379

An Equivalence between Bayesian Priors and Penalties in Variational Inference

Autori: Pierre Wolinski, Guillaume Charpiat, Yann Ollivier
Pubblicato in: 2021
Editore: Arxiv

Asymptotic Analysis of Statistical Estimators related to MultiGraphex Processes under Misspecification

Autori: Zacharie Naulet: Judith Rousseau; François Caron
Pubblicato in: 2021
Editore: arxiv
DOI: 10.48550/arxiv.2107.01120

On sparsity, power-law and clustering properties of graphex processes

Autori: F. Caron, F. Panero and J. Rousseau
Pubblicato in: 2020
Editore: Arxiv

Wasserstein convergence in Bayesian deconvolution models

Autori: Judith Rousseau Catia Scricciolo
Pubblicato in: 2022
Editore: arxiv

Besov priors in density estimation: optimal posterior contraction rates and adaptation

Autori: Matteo Giordano
Pubblicato in: 2022
Editore: Arxiv
DOI: 10.48550/arxiv.2208.14350

Bayesian estimation of nonlinearHawkes process

Autori: D. Sulem, V. Rivoirard and J. Rousseau
Pubblicato in: 2021
Editore: Arxiv

Fast Bayesian Coresets via Subsampling and Quasi-Newton Refinement

Autori: Cian Naik Trevor Campbell Judith Rousseau
Pubblicato in: 2022
Editore: Arxiv

Safe-Bayesian Generalized Linear Regression

Autori: Rianne de Heide, Alisa Kirichenko, Nishant Mehta, Peter Grünwald
Pubblicato in: AISTATs, 2020
Editore: MLR

Bayesian nonparametrics for sparse dynamic networks

Autori: Cian Naik, Francois Caron, Judith Rousseau, Yee Whye Teh, Konstantina Palla
Pubblicato in: European Conference on Machine Learning and Data Mining, 2022
Editore: ECML PKDD
DOI: 10.48550/arxiv.1607.01624

On the inability of Gaussian process regression to optimally learn compositional functions

Autori: Matteo Giordano, Johannes Schmidt-Hieber, Kolyan Ra
Pubblicato in: Advances in Neural Information Processing Systems 36, Numero 10495258, 2022, ISSN 1049-5258
Editore: NeurIPS
DOI: 10.48550/arxiv.2205.07764

The Curse of Depth in Kernel Regime

Autori: Soufiane Hayou;Arnaud Doucet; Judith Rousseau
Pubblicato in: 2021
Editore: PMLR

Stable Resnet

Autori: Hayou, Soufiane and Clerico, Eugenio and He, Bobby and Deligiannidis, George and Doucet, Arnaud and Rousseau, Judith
Pubblicato in: Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, Numero 130, 2021, Pagina/e 1324--1332
Editore: PMLR

Sparse networks with core-periphery structure

Autori: Cian Naik, Caron François, Judith Rousseau
Pubblicato in: Electronic Journal of Statistics, Numero 15, 2021, Pagina/e 1814-1868, ISSN 1935-7524
Editore: Institute of Mathematical Statistics
DOI: 10.1214/21-ejs1819

Simple discrete-time self-exciting models can describe complex dynamic processes: A case study of COVID-19

Autori: Raiha Browning, Deborah Sulem, Kerrie Mengersen, Vincent Rivoirard, Judith Rousseau
Pubblicato in: PLOS ONE, Numero 16/4, 2021, Pagina/e e0250015, ISSN 1932-6203
Editore: Public Library of Science
DOI: 10.1371/journal.pone.0250015

Nonparametric Bayesian Inference for Reversible Multi-Dimensional Diffusions

Autori: Matteo Giordano; Kolyan Ray
Pubblicato in: The Annals of Statistics, Numero 00905364, 2022, ISSN 0090-5364
Editore: Institute of Mathematical Statistics
DOI: 10.48550/arxiv.2012.12083

Pubblicazioni

Condividi questa pagina

Scarica