Stefano Favaro

J. Mach. Learn. Res., 2024

Function-Space MCMC for Bayesian Wide Neural Networks.

[BibT_eX]

[DOI]

Lucia Pezzetti

CoRR, 2024

Improved prediction of future user activity in online A/B testing.

[BibT_eX]

[DOI]

CoRR, 2024

A Nonparametric Bayes Approach to Online Activity Prediction.

[BibT_eX]

[DOI]

CoRR, 2024

2023

Conformal Frequency Estimation using Discrete Sketched Data with Coverage for Distinct Queries.

[BibT_eX]

[DOI]

Edgar Dobriban

J. Mach. Learn. Res., 2023

Learning-augmented count-min sketches via Bayesian nonparametrics.

[BibT_eX]

[DOI]

Emanuele Dolera

J. Mach. Learn. Res., 2023

Frequency and cardinality recovery from sketched data: a novel approach bridging Bayesian and frequentist views.

[BibT_eX]

[DOI]

Mario Beraha

CoRR, 2023

Quantitative CLTs in Deep Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2023

Non-asymptotic approximations of Gaussian neural networks via second-order Poincaré inequalities.

[BibT_eX]

[DOI]

Alberto Bordino

CoRR, 2023

2022

Infinitely wide limits for deep Stable neural networks: sub-linear, linear and super-linear activation functions.

[BibT_eX]

[DOI]

Alberto Bordino

Trans. Mach. Learn. Res., 2022

Neural tangent kernel analysis of shallow α-Stable ReLU neural networks.

[BibT_eX]

[DOI]

CoRR, 2022

Conformal Frequency Estimation with Sketched Data.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Doubly infinite residual neural networks: a diffusion process approach.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2021

Consistent estimation of small masses in feature sampling.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2021

Deep Stable neural networks: large-width asymptotics and convergence rates.

[BibT_eX]

[DOI]

CoRR, 2021

Infinite-channel deep stable convolutional neural networks.

[BibT_eX]

[DOI]

CoRR, 2021

Large-width functional asymptotics for deep Gaussian neural networks.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

A Bayesian nonparametric approach to count-min sketch under power-law data streams.

[BibT_eX]

[DOI]

Emanuele Dolera

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Doubly infinite residual networks: a diffusion process approach.

[BibT_eX]

[DOI]

CoRR, 2020

Stable behaviour of infinitely wide deep neural networks.

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

Infinitely deep neural networks as diffusion processes.

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Neural Stochastic Differential Equations.

[BibT_eX]

[DOI]

CoRR, 2019

2015

On a class of σ-stable Poisson-Kingman models and an effective marginalized sampler.

[BibT_eX]

[DOI]

Maria Lomeli

Yee Whye Teh

Stat. Comput., 2015

Are Gibbs-Type Priors the Most Natural Generalization of the Dirichlet Process?

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2015

A hybrid sampler for Poisson-Kingman mixture models.

[BibT_eX]

[DOI]

Maria Lomeli

Yee Whye Teh

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

2014

Discussion of "On simulation and properties of the stable law" by L. Devroye and L. James.

[BibT_eX]

[DOI]

Bernardo Nipoti

Stat. Methods Appl., 2014

Posterior analysis of rare variants in Gibbs-type species sampling models.

[BibT_eX]

[DOI]

Oriana Cesari