research
∙
05/23/2023
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
The success of over-parameterized neural networks trained to near-zero t...
share
research
∙
03/08/2023
ChatGPT Participates in a Computer Science Exam
We asked ChatGPT to participate in an undergraduate computer science exa...
research
∙
03/07/2023
AI for Science: An Emerging Agenda
This report documents the programme and the outcomes of Dagstuhl Seminar...
research
∙
11/05/2022
Pitfalls of Climate Network Construction: A Statistical Perspective
Network-based analyses of dynamical systems have become increasingly pop...
research
∙
11/03/2022
A Consistent Estimator for Confounding Strength
Regression on observational data can fail to capture a causal relationsh...
research
∙
11/03/2022
Relating graph auto-encoders to linear models
Graph auto-encoders are widely used to construct graph representations i...
research
∙
09/08/2022
From Shapley Values to Generalized Additive Models and back
In explainable machine learning, local post-hoc explanation algorithms a...
research
∙
06/15/2022
The Manifold Hypothesis for Gradient-Based Explanations
When do gradient-based explanation algorithms provide meaningful explana...
research
∙
03/07/2022
Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference
Full Bayesian posteriors are rarely analytically tractable, which is why...
research
∙
02/18/2022
Interpolation and Regularization for Causal Learning
We study the problem of learning causal models from observational data t...
research
∙
01/25/2022
Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts
Existing and planned legislation stipulates various obligations to provi...
research
∙
10/18/2021
Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture Models
Despite the ubiquity of kernel-based clustering, surprisingly few statis...
research
∙
07/09/2021
Specialists Outperform Generalists in Ensemble Classification
Consider an ensemble of k individual classifiers whose accuracies are kn...
research
∙
08/25/2020
Looking deeper into LIME
Interpretability of machine learning algorithm is a pressing need. Numer...
research
∙
07/09/2020
When Humans and Machines Make Joint Decisions: A Non-Symmetric Bandit Model
How can humans and machines learn to make joint decisions? This has beco...
research
∙
06/25/2020
Tangles: From Weak to Strong Clustering
We introduce a new approach to clustering by using tangles, a tool that ...
research
∙
04/30/2020
Group Decisions based on Confidence Weighted Majority Voting
Background: It has repeatedly been reported that when making decisions u...
research
∙
04/30/2020
The unconscious priming fallacy: When can scientists truly claim an indirect task advantage?
Current literature holds that many cognitive functions can be performed ...
research
∙
01/10/2020
Explaining the Explainer: A First Theoretical Analysis of LIME
Machine learning is used more and more often for sensitive applications,...
research
∙
12/03/2019
Large scale representation learning from triplet comparisons
In this paper, we discuss the fundamental problem of representation lear...
research
∙
08/21/2019
Estimation of perceptual scales using ordinal embedding
In this paper, we address the problem of measuring and analysing sensati...
research
∙
06/27/2019
Uncertainty Estimates for Ordinal Embeddings
To investigate objects without a describable notion of distance, one can...
research
∙
05/17/2019
Comparison-Based Framework for Psychophysics: Lab versus Crowdsourcing
Traditionally, psychophysical experiments are conducted by repeated meas...
research
∙
11/30/2018
Practical methods for graph two-sample testing
Hypothesis testing for graphs has been an important tool in applied rese...
research
∙
11/02/2018
Foundations of Comparison-Based Hierarchical Clustering
We address the classical problem of hierarchical clustering, but in a fr...
research
∙
10/31/2018
Boosting for Comparison-Based Learning
We consider the problem of classification in a comparison-based setting:...
research
∙
06/18/2018
Comparison-Based Random Forests
Assume we are given a set of items from a general metric space, but we n...
research
∙
08/31/2017
Design and Analysis of the NIPS 2016 Review Process
Neural Information Processing Systems (NIPS) is a top-tier annual confer...
research
∙
07/04/2017
Two-sample Hypothesis Testing for Inhomogeneous Random Graphs
The study of networks leads to a wide range of high dimensional inferenc...
research
∙
05/17/2017
Two-Sample Tests for Large Random Graphs Using Network Statistics
We consider a two-sample hypothesis testing problem, where the distribut...
research
∙
04/05/2017
Comparison Based Nearest Neighbor Search
We consider machine learning in a comparison-based setting where we are ...
research
∙
07/28/2016
Kernel functions based on triplet comparisons
Given only information in the form of similarity triplets "Object A is m...
research
∙
02/23/2016
Lens depth function and k-relative neighborhood graph: versatile tools for ordinal data analysis
In recent years it has become popular to study machine learning problems...
research
∙
06/02/2015
Peer Grading in a Course on Algorithms and Data Structures: Machine Learning Algorithms do not Improve over Simple Baselines
Peer grading is the process of students reviewing each others' work, suc...
research
∙
06/27/2012
Shortest path distance in random k-nearest neighbor graphs
Consider a weighted or unweighted k-nearest neighbor graph that has been...
research
∙
05/03/2011
Pruning nearest neighbor cluster trees
Nearest neighbor (k-NN) graphs are widely used in machine learning and d...
research
∙
02/10/2011
How the result of graph clustering methods depends on the construction of the graph
We study the scenario of graph-based clustering algorithms such as spect...
research
∙
12/17/2009
Optimal construction of k-nearest neighbor graphs for identifying noisy clusters
We study clustering algorithms based on neighborhood graphs on a random ...
research
∙
10/27/2008