200 citations · 675 across the 45 of their papers we have counts for
15 papers · 1 filter
Cluster Purging: Efficient Outlier Detection based on Rate-Distortion Theory
Maximilian B. Toller, Bernhard C. Geiger, Roman Kern
Rate-distortion theory-based outlier detection builds upon the rationale that a good data compression will encode outliers with unique symbols. Based on this rationale, we propose…
A conceptual model for leaving the data-centric approach in machine learning
Sebastian Scher, Bernhard Geiger, Simone Kopeinik +2
For a long time, machine learning (ML) has been seen as the abstract problem of learning relationships from data independent of the surrounding settings. This has recently been cha…
Robust Bayesian Target Value Optimization
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 th…
Trustworthy Representation Learning via Information Funnels and Bottlenecks
João Machado de Freitas, Bernhard C. Geiger
Ensuring trustworthiness in machine learning -- by balancing utility, fairness, and privacy -- remains a critical challenge, particularly in representation learning. In this work,…
Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering
João Machado de Freitas, Sebastian Berg, Bernhard C. Geiger +1
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 re…
Semi-Supervised Clustering via Information-Theoretic Markov Chain Aggregation
Sophie Steger, Bernhard C. Geiger, Marek Smieja
We connect the problem of semi-supervised clustering to constrained Markov aggregation, i.e., the task of partitioning the state space of a Markov chain. We achieve this connection…
Data vs. Physics: The Apparent Pareto Front of Physics-Informed Neural Networks
Franz M. Rohrhofer, Stefan Posch, Clemens Gößnitzer +1
Physics-informed neural networks (PINNs) have emerged as a promising deep learning method, capable of solving forward and inverse problems governed by differential equations. Despi…
A Formally Robust Time Series Distance Metric
Maximilian Toller, Bernhard C. Geiger, Roman Kern
Distance-based classification is among the most competitive classification methods for time series data. The most critical component of distance-based classification is the selecte…
On Information Plane Analyses of Neural Network Classifiers -- A Review
Bernhard C. Geiger
We review the current literature concerned with information plane analyses of neural network classifiers. While the underlying information bottleneck theory and the claim that info…
Class-Conditional Compression and Disentanglement: Bridging the Gap between Neural Networks and Naive Bayes Classifiers
Rana Ali Amjad, Bernhard C. Geiger
In this draft, which reports on work in progress, we 1) adapt the information bottleneck functional by replacing the compression term by class-conditional compression, 2) relax thi…
SeGMA: Semi-Supervised Gaussian Mixture Auto-Encoder
Marek Śmieja, Maciej Wołczyk, Jacek Tabor +1
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…
Understanding Neural Networks and Individual Neuron Importance via Information-Ordered Cumulative Ablation
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 Kull…
Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle
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. We show that the resulting o…
Co-Clustering via Information-Theoretic Markov Aggregation
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. By constructing a s…
Semi-supervised cross-entropy clustering with information bottleneck constraint
Marek Śmieja, Bernhard C. Geiger
In this paper, we propose a semi-supervised clustering method, CEC-IB, that models data with a set of Gaussian distributions and that retrieves clusters based on a partial labeling…