Search Results for author: Tom Heskes

Found 41 papers, 17 papers with code

Pfeed: Generating near real-time personalized feeds using precomputed embedding similarities

no code implementations25 Feb 2024 Binyam Gebre, Karoliina Ranta, Stef van den Elzen, Ernst Kuiper, Thijs Baars, Tom Heskes

In personalized recommender systems, embeddings are often used to encode customer actions and items, and retrieval is then performed in the embedding space using approximate nearest neighbor search.

Recommendation Systems Retrieval

Graph Isomorphic Networks for Assessing Reliability of the Medium-Voltage Grid

1 code implementation2 Oct 2023 Charlotte Cambier van Nooten, Tom van de Poll, Sonja Füllhase, Jacco Heres, Tom Heskes, Yuliya Shapovalova

Ensuring electricity grid reliability becomes increasingly challenging with the shift towards renewable energy and declining conventional capacities.

Likelihood-ratio-based confidence intervals for neural networks

1 code implementation4 Aug 2023 Laurens Sluijterman, Eric Cator, Tom Heskes

This paper introduces a first implementation of a novel likelihood-ratio-based approach for constructing confidence intervals for neural networks.

Unsupervised anomaly detection algorithms on real-world data: how many do we need?

1 code implementation1 May 2023 Roel Bouman, Zaharah Bukhsh, Tom Heskes

In this study we evaluate 32 unsupervised anomaly detection algorithms on 52 real-world multivariate tabular datasets, performing the largest comparison of unsupervised anomaly detection algorithms to date.

Unsupervised Anomaly Detection

Optimal Training of Mean Variance Estimation Neural Networks

1 code implementation17 Feb 2023 Laurens Sluijterman, Eric Cator, Tom Heskes

We demonstrate, both on toy examples and on a number of benchmark UCI regression data sets, that following the original recommendations and the novel separate regularization can lead to significant improvements.

regression

Machine Learning Meets The Herbrand Universe

1 code implementation7 Oct 2022 Jelle Piepenbrock, Josef Urban, Konstantin Korovin, Miroslav Olšák, Tom Heskes, Mikolaš Janota

In particular, we develop a GNN2RNN architecture based on an invariant graph neural network (GNN) that learns from problems and their solutions independently of symbol names (addressing the abundance of skolems), combined with a recurrent neural network (RNN) that proposes for each clause its instantiations.

Automatic inference of fault tree models via multi-objective evolutionary algorithms

no code implementations6 Apr 2022 Lisandro A. Jimenez-Roa, Tom Heskes, Tiedo Tinga, Marielle Stoelinga

Fault tree analysis is a well-known technique in reliability engineering and risk assessment, which supports decision-making processes and the management of complex systems.

Decision Making Evolutionary Algorithms +1

Confident Neural Network Regression with Bootstrapped Deep Ensembles

1 code implementation22 Feb 2022 Laurens Sluijterman, Eric Cator, Tom Heskes

A classical parametric model has uncertainty in the parameters due to the fact that the data on which the model is build is a random sample.

Prediction Intervals regression

Going Grayscale: The Road to Understanding and Improving Unlearnable Examples

1 code implementation25 Nov 2021 Zhuoran Liu, Zhengyu Zhao, Alex Kolmus, Tijn Berns, Twan van Laarhoven, Tom Heskes, Martha Larson

Recent work has shown that imperceptible perturbations can be applied to craft unlearnable examples (ULEs), i. e. images whose content cannot be used to improve a classifier during training.

Swift sky localization of gravitational waves using deep learning seeded importance sampling

1 code implementation1 Nov 2021 Alex Kolmus, Grégory Baltus, Justin Janquart, Twan van Laarhoven, Sarah Caudill, Tom Heskes

Fast, highly accurate, and reliable inference of the sky origin of gravitational waves would enable real-time multi-messenger astronomy.

Astronomy Bayesian Inference

Learning Equational Theorem Proving

no code implementations10 Feb 2021 Jelle Piepenbrock, Tom Heskes, Mikoláš Janota, Josef Urban

On these tasks, 3SIL is shown to significantly outperform several established RL and imitation learning methods.

Automated Theorem Proving Imitation Learning +1

Spectral Ranking of Causal Influence in Complex Systems

no code implementations24 Dec 2020 Errol Zalmijn, Tom Heskes, Tom Claassen

Like natural complex systems such as the Earth's climate or a living cell, semiconductor lithography systems are characterized by nonlinear dynamics across more than a dozen orders of magnitude in space and time.

Time Series Analysis Information Theory Information Theory Adaptation and Self-Organizing Systems Physics and Society

MASSIVE: Tractable and Robust Bayesian Learning of Many-Dimensional Instrumental Variable Models

no code implementations18 Dec 2020 Ioan Gabriel Bucur, Tom Claassen, Tom Heskes

Unfortunately, searching for proper instruments in a many-dimensional set of candidates is a daunting task due to the intractable model space and the fact that we cannot directly test which of these candidates are valid, so most existing search methods either rely on overly stringent modeling assumptions or fail to capture the inherent model uncertainty in the selection process.

Causal Inference valid

Inferring the Direction of a Causal Link and Estimating Its Effect via a Bayesian Mendelian Randomization Approach

1 code implementation18 Dec 2020 Ioan Gabriel Bucur, Tom Claassen, Tom Heskes

In this paper, we propose a Bayesian approach called BayesMR that is a generalization of the Mendelian randomization technique in which we allow for pleiotropic effects and, crucially, for the possibility of reverse causation.

Large-Scale Local Causal Inference of Gene Regulatory Relationships

1 code implementation3 Sep 2019 Ioan Gabriel Bucur, Tom Claassen, Tom Heskes

Many of these computational methods are designed to infer individual regulatory relationships among genes from data on gene expression.

Causal Inference

Constraining the Parameters of High-Dimensional Models with Active Learning

1 code implementation19 May 2019 Sascha Caron, Tom Heskes, Sydney Otten, Bob Stienen

Constraining the parameters of physical models with $>5-10$ parameters is a widespread problem in fields like particle physics and astronomy.

Active Learning Astronomy +1

A Bayesian Approach for Inferring Local Causal Structure in Gene Regulatory Networks

1 code implementation18 Sep 2018 Ioan Gabriel Bucur, Tom van Bussel, Tom Claassen, Tom Heskes

Gene regulatory networks play a crucial role in controlling an organism's biological processes, which is why there is significant interest in developing computational methods that are able to extract their structure from high-throughput genetic data.

A Novel Bayesian Approach for Latent Variable Modeling from Mixed Data with Missing Values

1 code implementation12 Jun 2018 Ruifei Cui, Ioan Gabriel Bucur, Perry Groot, Tom Heskes

We consider the problem of learning parameters of latent variable models from mixed (continuous and ordinal) data with missing values.

Stable specification search in structural equation model with latent variables

no code implementations24 May 2018 Ridho Rahmadi, Perry Groot, Tom Heskes

In our previous study, we introduced stable specification search for cross-sectional data (S3C).

Causal Discovery

Robust Causal Estimation in the Large-Sample Limit without Strict Faithfulness

1 code implementation6 Apr 2017 Ioan Gabriel Bucur, Tom Claassen, Tom Heskes

Causal effect estimation from observational data is an important and much studied research topic.

Causal Discovery

Causality on Longitudinal Data: Stable Specification Search in Constrained Structural Equation Modeling

no code implementations22 May 2016 Ridho Rahmadi, Perry Groot, Marieke HC van Rijn, Jan AJG van den Brand, Marianne Heins, Hans Knoop, Tom Heskes

The present work introduces a novel causal modeling algorithm for longitudinal data, that is robust for finite samples based on recent advances in stability selection using subsampling and selection algorithms.

Regularizing Solutions to the MEG Inverse Problem Using Space-Time Separable Covariance Functions

no code implementations17 Apr 2016 Arno Solin, Pasi Jylänki, Jaakko Kauramäki, Tom Heskes, Marcel A. J. van Gerven, Simo Särkkä

We apply the method to both simulated and empirical data, and demonstrate the efficiency and generality of our Bayesian source reconstruction approach which subsumes various classical approaches in the literature.

The Artificial Mind's Eye: Resisting Adversarials for Convolutional Neural Networks using Internal Projection

1 code implementation15 Apr 2016 Harm Berntsen, Wouter Kuijper, Tom Heskes

We introduce a novel artificial neural network architecture that integrates robustness to adversarial input in the network structure.

Bigger Buffer k-d Trees on Multi-Many-Core Systems

1 code implementation9 Dec 2015 Fabian Gieseke, Cosmin Eugen Oancea, Ashish Mahabal, Christian Igel, Tom Heskes

A buffer k-d tree is a k-d tree variant for massively-parallel nearest neighbor search.

Astronomy

Proof Supplement - Learning Sparse Causal Models is not NP-hard (UAI2013)

no code implementations6 Nov 2014 Tom Claassen, Joris M. Mooij, Tom Heskes

The algorithm is an adaptation of the well-known FCI algorithm by (Spirtes et al., 2000) that is also sound and complete, but has worst case complexity exponential in $N$.

Model Discovery Selection bias

Properties of Bethe Free Energies and Message Passing in Gaussian Models

no code implementations16 Jan 2014 Botond Cseke, Tom Heskes

We define the Gaussian fractional Bethe free energy in terms of the moment parameters of the approximate marginals, derive a lower and an upper bound on the fractional Bethe free energy and establish a necessary condition for the lower bound to be bounded from below.

Learning Sparse Causal Models is not NP-hard

no code implementations26 Sep 2013 Tom Claassen, Joris Mooij, Tom Heskes

This paper shows that causal model discovery is not an NP-hard problem, in the sense that for sparse graphs bounded by node degree k the sound and complete causal model can be obtained in worst case order N^{2(k+2)} independence tests, even when latent variables and selection bias may be present.

Causal Discovery Model Discovery +1

Cyclic Causal Discovery from Continuous Equilibrium Data

no code implementations26 Sep 2013 Joris Mooij, Tom Heskes

We propose a method for learning cyclic causal models from a combination of observational and interventional equilibrium data.

Causal Discovery

Semi-supervised Ranking Pursuit

no code implementations2 Jul 2013 Evgeni Tsivtsivadze, Tom Heskes

We propose a novel sparse preference learning/ranking algorithm.

regression

Sparse Approximate Inference for Spatio-Temporal Point Process Models

no code implementations17 May 2013 Botond Cseke, Andrew Zammit Mangion, Tom Heskes, Guido Sanguinetti

Spatio-temporal point process models play a central role in the analysis of spatially distributed systems in several disciplines.

On Causal Discovery with Cyclic Additive Noise Models

no code implementations NeurIPS 2011 Joris M. Mooij, Dominik Janzing, Tom Heskes, Bernhard Schölkopf

We study a particular class of cyclic causal models, where each variable is a (possibly nonlinear) function of its parents and additive noise.

Causal Discovery regression

Causal discovery in multiple models from different experiments

no code implementations NeurIPS 2010 Tom Claassen, Tom Heskes

We present the MCI-algorithm as the first method that can infer provably valid causal relations in the large sample limit from different experiments.

Causal Discovery valid

Bayesian Source Localization with the Multivariate Laplace Prior

no code implementations NeurIPS 2009 Marcel V. Gerven, Botond Cseke, Robert Oostenveld, Tom Heskes

We introduce a novel multivariate Laplace (MVL) distribution as a sparsity promoting prior for Bayesian source localization that allows the specification of constraints between and within sources.

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