Search Results for author: Julyan Arbel

Found 15 papers, 5 papers with code

Covariance-Adaptive Least-Squares Algorithm for Stochastic Combinatorial Semi-Bandits

no code implementations23 Feb 2024 Julien Zhou, Pierre Gaillard, Thibaud Rahier, Houssam Zenati, Julyan Arbel

We address the problem of stochastic combinatorial semi-bandits, where a player can select from P subsets of a set containing d base items.

Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review

no code implementations20 Nov 2023 Minh Tri Lê, Pierre Wolinski, Julyan Arbel

It then explores MEMS-based applications on ultra-low power MCUs, highlighting their potential for enabling TinyML on resource-constrained devices.

Model Compression Quantization

Something for (almost) nothing: Improving deep ensemble calibration using unlabeled data

no code implementations4 Oct 2023 Konstantinos Pitas, Julyan Arbel

We present a method to improve the calibration of deep ensembles in the small training data regime in the presence of unlabeled data.

A Primer on Bayesian Neural Networks: Review and Debates

1 code implementation28 Sep 2023 Julyan Arbel, Konstantinos Pitas, Mariia Vladimirova, Vincent Fortuin

Neural networks have achieved remarkable performance across various problem domains, but their widespread applicability is hindered by inherent limitations such as overconfidence in predictions, lack of interpretability, and vulnerability to adversarial attacks.

Bayesian Inference

The fine print on tempered posteriors

no code implementations11 Sep 2023 Konstantinos Pitas, Julyan Arbel

Contrary to previous results, we first show that for realistic models and datasets and the tightly controlled case of the Laplace approximation to the posterior, stochasticity does not in general improve test accuracy.

Hybrids of Constraint-based and Noise-based Algorithms for Causal Discovery from Time Series

1 code implementation14 Jun 2023 Charles K. Assaad, Daria Bystrova, Julyan Arbel, Emilie Devijver, Eric Gaussier, Wilfried Thuiller

Constraint-based and noise-based methods have been proposed to discover summary causal graphs from observational time series under strong assumptions which can be violated or impossible to verify in real applications.

Causal Discovery Time Series

Cold Posteriors through PAC-Bayes

no code implementations22 Jun 2022 Konstantinos Pitas, Julyan Arbel

We investigate the cold posterior effect through the lens of PAC-Bayes generalization bounds.

Bayesian Inference Generalization Bounds +1

Gaussian Pre-Activations in Neural Networks: Myth or Reality?

1 code implementation24 May 2022 Pierre Wolinski, Julyan Arbel

The study of feature propagation at initialization in neural networks lies at the root of numerous initialization designs.

Dependence between Bayesian neural network units

no code implementations29 Nov 2021 Mariia Vladimirova, Julyan Arbel, Stéphane Girard

The connection between Bayesian neural networks and Gaussian processes gained a lot of attention in the last few years, with the flagship result that hidden units converge to a Gaussian process limit when the layers width tends to infinity.

Gaussian Processes

Bayesian neural network unit priors and generalized Weibull-tail property

no code implementations6 Oct 2021 Mariia Vladimirova, Julyan Arbel, Stéphane Girard

The connection between Bayesian neural networks and Gaussian processes gained a lot of attention in the last few years.

Gaussian Processes

Approximating the clusters' prior distribution in Bayesian nonparametric models

2 code implementations pproximateinference AABI Symposium 2021 Daria Bystrova, Julyan Arbel, Guillaume Kon Kam King, François Deslandes

In Bayesian nonparametrics, knowledge of the prior distribution induced on the number of clusters is key for prior specification and calibration.

Approximate Bayesian computation via the energy statistic

1 code implementation14 May 2019 Hien D. Nguyen, Julyan Arbel, Hongliang Lü, Florence Forbes

Furthermore, we propose a consistent V-statistic estimator of the energy statistic, under which we show that the large sample result holds, and prove that the rejection ABC algorithm, based on the energy statistic, generates pseudo-posterior distributions that achieves convergence to the correct limits, when implemented with rejection thresholds that converge to zero, in the finite sample setting.

Understanding Priors in Bayesian Neural Networks at the Unit Level

no code implementations11 Oct 2018 Mariia Vladimirova, Jakob Verbeek, Pablo Mesejo, Julyan Arbel

We investigate deep Bayesian neural networks with Gaussian weight priors and a class of ReLU-like nonlinearities.

A moment-matching Ferguson and Klass algorithm

no code implementations8 Jun 2016 Julyan Arbel, Igor Prünster

Completely random measures (CRM) represent the key building block of a wide variety of popular stochastic models and play a pivotal role in modern Bayesian Nonparametrics.

Cannot find the paper you are looking for? You can Submit a new open access paper.