Search Results for author: Martin Jørgensen

Found 12 papers, 8 papers with code

Bayesian Quadrature for Neural Ensemble Search

1 code implementation15 Mar 2023 Saad Hamid, Xingchen Wan, Martin Jørgensen, Binxin Ru, Michael Osborne

Ensembling can improve the performance of Neural Networks, but existing approaches struggle when the architecture likelihood surface has dispersed, narrow peaks.

SOBER: Highly Parallel Bayesian Optimization and Bayesian Quadrature over Discrete and Mixed Spaces

1 code implementation27 Jan 2023 Masaki Adachi, Satoshi Hayakawa, Saad Hamid, Martin Jørgensen, Harald Oberhauser, Micheal A. Osborne

Batch Bayesian optimisation and Bayesian quadrature have been shown to be sample-efficient methods of performing optimisation and quadrature where expensive-to-evaluate objective functions can be queried in parallel.

Drug Discovery

Bézier Gaussian Processes for Tall and Wide Data

no code implementations1 Sep 2022 Martin Jørgensen, Michael A. Osborne

We introduce a kernel that allows the number of summarising variables to grow exponentially with the number of input features, but requires only linear cost in both number of observations and input features.

Gaussian Processes

Fast Bayesian Inference with Batch Bayesian Quadrature via Kernel Recombination

2 code implementations9 Jun 2022 Masaki Adachi, Satoshi Hayakawa, Martin Jørgensen, Harald Oberhauser, Michael A. Osborne

Empirically, we find that our approach significantly outperforms the sampling efficiency of both state-of-the-art BQ techniques and Nested Sampling in various real-world datasets, including lithium-ion battery analytics.

Bayesian Inference Numerical Integration

Last Layer Marginal Likelihood for Invariance Learning

1 code implementation14 Jun 2021 Pola Schwöbel, Martin Jørgensen, Sebastian W. Ober, Mark van der Wilk

Computing the marginal likelihood is hard for neural networks, but success with tractable approaches that compute the marginal likelihood for the last layer only raises the question of whether this convenient approach might be employed for learning invariances.

Data Augmentation Gaussian Processes +1

Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval

no code implementations ICCV 2021 Frederik Warburg, Martin Jørgensen, Javier Civera, Søren Hauberg

Uncertainty quantification in image retrieval is crucial for downstream decisions, yet it remains a challenging and largely unexplored problem.

Computational Efficiency Image Retrieval +2

Reparametrization Invariance in non-parametric Causal Discovery

no code implementations12 Aug 2020 Martin Jørgensen, Søren Hauberg

This study investigates one such invariant: the causal relationship between X and Y is invariant to the marginal distributions of X and Y.

Causal Discovery

Stochastic Differential Equations with Variational Wishart Diffusions

1 code implementation ICML 2020 Martin Jørgensen, Marc Peter Deisenroth, Hugh Salimbeni

We present a Bayesian non-parametric way of inferring stochastic differential equations for both regression tasks and continuous-time dynamical modelling.

regression

Isometric Gaussian Process Latent Variable Model for Dissimilarity Data

no code implementations21 Jun 2020 Martin Jørgensen, Søren Hauberg

We present a probabilistic model where the latent variable respects both the distances and the topology of the modeled data.

Variational Inference

Probabilistic Spatial Transformer Networks

1 code implementation7 Apr 2020 Pola Schwöbel, Frederik Warburg, Martin Jørgensen, Kristoffer H. Madsen, Søren Hauberg

Spatial Transformer Networks (STNs) estimate image transformations that can improve downstream tasks by `zooming in' on relevant regions in an image.

Data Augmentation Time Series +2

Reliable training and estimation of variance networks

2 code implementations NeurIPS 2019 Nicki S. Detlefsen, Martin Jørgensen, Søren Hauberg

We propose and investigate new complementary methodologies for estimating predictive variance networks in regression neural networks.

Active Learning Gaussian Processes +1

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