1 code implementation • 3 Dec 2021 • Jonathan Wenger, Nicholas Krämer, Marvin Pförtner, Jonathan Schmidt, Nathanael Bosch, Nina Effenberger, Johannes Zenn, Alexandra Gessner, Toni Karvonen, François-Xavier Briol, Maren Mahsereci, Philipp Hennig
Probabilistic numerical methods (PNMs) solve numerical problems via probabilistic inference.
no code implementations • 2 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.
2 code implementations • 25 Oct 2021 • Andrei Paleyes, Mark Pullin, Maren Mahsereci, Cliff McCollum, Neil D. Lawrence, Javier Gonzalez
Decision making in uncertain scenarios is an ubiquitous challenge in real world systems.
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.
no code implementations • 17 Jul 2020 • Hans Kersting, Maren Mahsereci
Gaussian ODE filtering is a probabilistic numerical method to solve ordinary differential equations (ODEs).
no code implementations • 27 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.
1 code implementation • NeurIPS 2015 • Maren Mahsereci, Philipp Hennig
In deterministic optimization, line searches are a standard tool ensuring stability and efficiency.
no code implementations • 28 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.
1 code implementation • NeurIPS 2015 • Maren Mahsereci, Philipp Hennig
In deterministic optimization, line searches are a standard tool ensuring stability and efficiency.