Search Results for author: Bernhard C. Geiger

Found 18 papers, 4 papers with code

Robust Bayesian Target Value Optimization

no code implementations11 Jan 2023 Johannes G. Hoffer, Sascha Ranftl, Bernhard C. Geiger

We consider the problem of finding an input to a stochastic black box function such that the scalar output of the black box function is as close as possible to a target value in the sense of the expected squared error.

Gaussian Processes

FUNCK: Information Funnels and Bottlenecks for Invariant Representation Learning

no code implementations2 Nov 2022 João Machado de Freitas, Bernhard C. Geiger

Learning invariant representations that remain useful for a downstream task is still a key challenge in machine learning.

Representation Learning Variational Inference

Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering

1 code implementation31 May 2022 João Machado de Freitas, Sebastian Berg, Bernhard C. Geiger, Manfred Mücke

In this paper, we frame homogeneous-feature multi-task learning (MTL) as a hierarchical representation learning problem, with one task-agnostic and multiple task-specific latent representations.

Multi-Task Learning Representation Learning

Understanding the Difficulty of Training Physics-Informed Neural Networks on Dynamical Systems

1 code implementation25 Mar 2022 Franz M. Rohrhofer, Stefan Posch, Clemens Gößnitzer, Bernhard C. Geiger

Experiments on a simple dynamical system demonstrate that physics loss residuals are trivially minimized in the vicinity of fixed points.

Knock Detection in Combustion Engine Time Series Using a Theory-Guided 1D Convolutional Neural Network Approach

no code implementations18 Jan 2022 Andreas B. Ofner, Achilles Kefalas, Stefan Posch, Bernhard C. Geiger

In addition, the model proved to classify knocking cycles in unseen engines with increased accuracy of 89% after adapting to their features via training on a small number of exclusively non-knocking cycles.

Time Series

Semi-Supervised Clustering via Information-Theoretic Markov Chain Aggregation

1 code implementation17 Dec 2021 Sophie Steger, Bernhard C. Geiger, Marek Smieja

The introduced Constrained Markov Clustering (CoMaC) is an extension of a recent information-theoretic framework for (unsupervised) Markov aggregation to the semi-supervised case.

On the Pareto Front of Physics-Informed Neural Networks

no code implementations3 May 2021 Franz M. Rohrhofer, Stefan Posch, Bernhard C. Geiger

We use the diffusion equation and Navier-Stokes equations in various test environments to analyze the effects of system parameters on the shape of the Pareto front.

Synwalk -- Community Detection via Random Walk Modelling

2 code implementations21 Jan 2021 Christian Toth, Denis Helic, Bernhard C. Geiger

We thoroughly validate the effectiveness of our approach on synthetic and empirical networks, respectively, and compare Synwalk's performance with the performance of Infomap and Walktrap.

Community Detection

A Formally Robust Time Series Distance Metric

no code implementations18 Aug 2020 Maximilian Toller, Bernhard C. Geiger, Roman Kern

Distance-based classification is among the most competitive classification methods for time series data.

Classification General Classification +1

On Information Plane Analyses of Neural Network Classifiers -- A Review

no code implementations21 Mar 2020 Bernhard C. Geiger

Specifically, we argue that even in feed-forward neural networks the data processing inequality need not hold for estimates of mutual information.

Information Plane Mutual Information Estimation

SeGMA: Semi-Supervised Gaussian Mixture Auto-Encoder

no code implementations21 Jun 2019 Marek Śmieja, Maciej Wołczyk, Jacek Tabor, Bernhard C. Geiger

We propose a semi-supervised generative model, SeGMA, which learns a joint probability distribution of data and their classes and which is implemented in a typical Wasserstein auto-encoder framework.

Style Transfer

Understanding Neural Networks and Individual Neuron Importance via Information-Ordered Cumulative Ablation

no code implementations18 Apr 2018 Rana Ali Amjad, Kairen Liu, Bernhard C. Geiger

In this work, we investigate the use of three information-theoretic quantities -- entropy, mutual information with the class variable, and a class selectivity measure based on Kullback-Leibler divergence -- to understand and study the behavior of already trained fully-connected feed-forward neural networks.

Classification General Classification

Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle

no code implementations27 Feb 2018 Rana Ali Amjad, Bernhard C. Geiger

In this theory paper, we investigate training deep neural networks (DNNs) for classification via minimizing the information bottleneck (IB) functional.

General Classification

Co-Clustering via Information-Theoretic Markov Aggregation

no code implementations2 Jan 2018 Clemens Bloechl, Rana Ali Amjad, Bernhard C. Geiger

We present an information-theoretic cost function for co-clustering, i. e., for simultaneous clustering of two sets based on similarities between their elements.

Semi-supervised cross-entropy clustering with information bottleneck constraint

no code implementations3 May 2017 Marek Śmieja, Bernhard C. Geiger

By combining the ideas from cross-entropy clustering (CEC) with those from the information bottleneck method (IB), our method trades between three conflicting goals: the accuracy with which the data set is modeled, the simplicity of the model, and the consistency of the clustering with side information.

Hard Clusters Maximize Mutual Information

no code implementations17 Aug 2016 Bernhard C. Geiger, Rana Ali Amjad

In this paper, we investigate mutual information as a cost function for clustering, and show in which cases hard, i. e., deterministic, clusters are optimal.

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