Search Results for author: Maren Mahsereci

Found 9 papers, 4 papers with code

Invariant Priors for Bayesian Quadrature

no code implementations2 Dec 2021 Masha Naslidnyk, Javier Gonzalez, Maren Mahsereci

Bayesian quadrature (BQ) is a model-based numerical integration method that is able to increase sample efficiency by encoding and leveraging known structure of the integration task at hand.

Numerical Integration

Dynamic Pruning of a Neural Network via Gradient Signal-to-Noise Ratio

no code implementations ICML Workshop AutoML 2021 Julien Niklas Siems, Aaron Klein, Cedric Archambeau, Maren Mahsereci

Dynamic sparsity pruning undoes this limitation and allows to adapt the structure of the sparse neural network during training.

A Fourier State Space Model for Bayesian ODE Filters

no code implementations17 Jul 2020 Hans Kersting, Maren Mahsereci

Gaussian ODE filtering is a probabilistic numerical method to solve ordinary differential equations (ODEs).

Active Multi-Information Source Bayesian Quadrature

no code implementations27 Mar 2019 Alexandra Gessner, Javier Gonzalez, Maren Mahsereci

Bayesian quadrature (BQ) is a sample-efficient probabilistic numerical method to solve integrals of expensive-to-evaluate black-box functions, yet so far, active BQ learning schemes focus merely on the integrand itself as information source, and do not allow for information transfer from cheaper, related functions.

Active Learning

Early Stopping without a Validation Set

no code implementations28 Mar 2017 Maren Mahsereci, Lukas Balles, Christoph Lassner, Philipp Hennig

Early stopping is a widely used technique to prevent poor generalization performance when training an over-expressive model by means of gradient-based optimization.

regression

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