1 code implementation • 3 Feb 2022 • Philipp Pilar, Carl Jidling, Thomas B. Schön, Niklas Wahlström
Machine learning models can be improved by adapting them to respect existing background knowledge.
no code implementations • 22 Feb 2021 • Filip de Roos, Carl Jidling, Adrian Wills, Thomas Schön, Philipp Hennig
Machine learning practitioners invest significant manual and computational resources in finding suitable learning rates for optimization algorithms.
1 code implementation • 5 Feb 2020 • Johannes Hendriks, Carl Jidling, Adrian Wills, Thomas Schön
We present a novel approach to modelling and learning vector fields from physical systems using neural networks that explicitly satisfy known linear operator constraints.
no code implementations • 4 Sep 2019 • Carl Jidling, Johannes Hendriks, Thomas B. Schön, Adrian Wills
Deep kernel learning refers to a Gaussian process that incorporates neural networks to improve the modelling of complex functions.
no code implementations • ICLR 2019 • Adrian Wills, Carl Jidling, Thomas Schon
During recent years there has been an increased interest in stochastic adaptations of limited memory quasi-Newton methods, which compared to pure gradient-based routines can improve the convergence by incorporating second order information.
no code implementations • 11 Sep 2018 • Zenith Purisha, Carl Jidling, Niklas Wahlström, Simo Särkkä, Thomas B. Schön
The approach also allows for reformulation of come classical regularization methods as Laplacian and Tikhonov regularization as Gaussian process regression, and hence provides an efficient algorithm and principled means for their parameter tuning.
no code implementations • NeurIPS 2017 • Carl Jidling, Niklas Wahlström, Adrian Wills, Thomas B. Schön
We consider a modification of the covariance function in Gaussian processes to correctly account for known linear constraints.