activity
20182021
most citedLearning PAC-Bayes Priors for Probabilistic Neural Networks

7 citations · 10 across the 3 of their papers we have counts for

collaborators

7 papers

cs.LG20217 cited

Learning PAC-Bayes Priors for Probabilistic Neural Networks

Maria Perez-Ortiz, Omar Rivasplata, Benjamin Guedj +5

Recent works have investigated deep learning models trained by optimising PAC-Bayes bounds, with priors that are learnt on subsets of the data. This combination has been shown to l…

cs.LG20213 cited

On the Role of Optimization in Double Descent: A Least Squares Study

Ilja Kuzborskij, Csaba Szepesvári, Omar Rivasplata +2

Empirically it has been observed that the performance of deep neural networks steadily improves as we increase model size, contradicting the classical view on overfitting and gener…

math.PR2021

A note on a confidence bound of Kuzborskij and Szepesvári

Omar Rivasplata

In an interesting recent work, Kuzborskij and Szepesvári derived a confidence bound for functions of independent random variables, which is based on an inequality that relates conc…

stat.ML2020

PAC-Bayes Analysis Beyond the Usual Bounds

Omar Rivasplata, Ilja Kuzborskij, Csaba Szepesvari +1

We focus on a stochastic learning model where the learner observes a finite set of training examples and the output of the learning process is a data-dependent distribution over a…

cs.LG2020

Logarithmic Pruning is All You Need

Laurent Orseau, Marcus Hutter, Omar Rivasplata

The Lottery Ticket Hypothesis is a conjecture that every large neural network contains a subnetwork that, when trained in isolation, achieves comparable performance to the large ne…

cs.LG2019

PAC-Bayes with Backprop

Omar Rivasplata, Vikram M Tankasali, Csaba Szepesvari

We explore the family of methods "PAC-Bayes with Backprop" (PBB) to train probabilistic neural networks by minimizing PAC-Bayes bounds. We present two training objectives, one deri…