Aug 14, 2020 · We show that this new method significantly reduces out-of-sample error when applied to hyperparameter optimization problems known to be prone to overfitting.

This repository contains scripts accompanying our manuscript 'Efficient Hyperparameter Optimization By Way of PAC-Bayes Bound Minimization.

Aug 14, 2020 · To choose these weights, they derive a quasiconvex PAC-Bayes bound on the expected risk and an algorithm for bound minimization that provably ...

Here we present an alternative objective that is equivalent to a Probably Approximately Correct-Bayes (PAC-Bayes) bound on the expected out-of-sample error. We ...

Aug 14, 2020 · It is shown that this new method significantly reduces out-of-sample error when applied to hyperparameter optimization problems known to be ...

2020. Efficient hyperparameter optimization by way of PAC-Bayes bound minimization. John J Cherian , Andrew G Taube , Robert T McGibbon , and 6 more authors.

Efficient hyperparameter optimization by way of pac-bayes bound minimization JJ Cherian, AG Taube, RT McGibbon, P Angelikopoulos, G Blanc, ...

Efficient hyperparameter optimization by way of PAC-Bayes bound minimization ... Identifying optimal values for a high-dimensional set of hyperparameters is a ...

Efficient hyperparameter optimization by way of PAC-Bayes bound minimization ... Identifying optimal values for a high-dimensional set of hyperparameters is a ...