Ingo Steinwart

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...

0 Moritz Haas, et al. ∙

research

∙ 12/23/2022

Physics-Informed Gaussian Process Regression Generalizes Linear PDE Solvers

Linear partial differential equations (PDEs) are an important, widely ap...

10 Marvin Pförtner, et al. ∙

research

∙ 06/23/2022

Utilizing Expert Features for Contrastive Learning of Time-Series Representations

We present an approach that incorporates expert knowledge for time-serie...

0 Manuel Nonnenmacher, et al. ∙

research

∙ 03/17/2022

A Framework and Benchmark for Deep Batch Active Learning for Regression

We study the performance of different pool-based Batch Mode Deep Active ...

1 David Holzmüller, et al. ∙

research

∙ 10/19/2021

SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning

Pruning neural networks reduces inference time and memory costs. On stan...

0 Manuel Nonnenmacher, et al. ∙

research

∙ 09/20/2021

Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments

Artificial neural networks (NNs) are one of the most frequently used mac...

0 Viktor Zaverkin, et al. ∙

research

∙ 07/16/2021

Intrinsic Dimension Adaptive Partitioning for Kernel Methods

We prove minimax optimal learning rates for kernel ridge regression, res...

0 Thomas Hamm, et al. ∙

research

∙ 11/04/2020

Which Minimizer Does My Neural Network Converge To?

The loss surface of an overparameterized neural network (NN) possesses m...

0 Manuel Nonnenmacher, et al. ∙

research

∙ 03/13/2020

Adaptive Learning Rates for Support Vector Machines Working on Data with Low Intrinsic Dimension

We derive improved regression and classification rates for support vecto...

0 Thomas Hamm, et al. ∙

research

∙ 03/13/2020

SVM Learning Rates for Data with Low Intrinsic Dimension

We derive improved regression and classification rates for support vecto...

0 Thomas Hamm, et al. ∙

research

∙ 02/12/2020

Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent

We prove that two-layer (Leaky)ReLU networks initialized by e.g. the wid...

0 David Holzmüller, et al. ∙

research

∙ 02/08/2020

Reproducing Kernel Hilbert Spaces Cannot Contain all Continuous Functions on a Compact Metric Space

Given an uncountable, compact metric space, we show that there exists no...

0 Ingo Steinwart, et al. ∙

research

∙ 09/22/2019

PAC-Bayesian Bounds for Deep Gaussian Processes

Variational approximation techniques and inference for stochastic models...

0 Roman Föll, et al. ∙

research

∙ 05/27/2019

Best-scored Random Forest Classification

We propose an algorithm named best-scored random forest for binary class...

0 Hanyuan Hang, et al. ∙

research

∙ 05/25/2019

Global Minima of DNNs: The Plenty Pantry

A common strategy to train deep neural networks (DNNs) is to use very la...

0 Nicole Mücke, et al. ∙

research

∙ 05/04/2019

Improved Classification Rates for Localized SVMs

One of the main characteristics of localized support vector machines tha...

0 Ingrid Blaschzyk, et al. ∙

research

∙ 03/27/2019

A Sober Look at Neural Network Initializations

Initializing the weights and the biases is a key part of the training pr...

0 Ingo Steinwart, et al. ∙

research

∙ 10/04/2018

Optimal Learning with Anisotropic Gaussian SVMs

This paper investigates the nonparametric regression problem using SVMs ...

0 Hanyuan Hang, et al. ∙

research

∙ 12/14/2017

Strictly proper kernel scores and characteristic kernels on compact spaces

Strictly proper kernel scores are well-known tool in probabilistic forec...

0 Ingo Steinwart, et al. ∙

research

∙ 08/17/2017

Adaptive Clustering Using Kernel Density Estimators

We investigate statistical properties of a clustering algorithm that rec...

0 Ingo Steinwart, et al. ∙

research

∙ 02/24/2017

Learning Rates for Kernel-Based Expectile Regression

Conditional expectiles are becoming an increasingly important tool in fi...

0 Muhammad Farooq, et al. ∙

research

∙ 02/23/2017

Sobolev Norm Learning Rates for Regularized Least-Squares Algorithm

Learning rates for regularized least-squares algorithms are in most case...

0 Simon Fischer, et al. ∙

research

∙ 02/22/2017

liquidSVM: A Fast and Versatile SVM package

liquidSVM is a package written in C++ that provides SVM-type solvers for...

0 Ingo Steinwart, et al. ∙

research

∙ 07/13/2016

Kernel Density Estimation for Dynamical Systems

We study the density estimation problem with observations generated by c...

0 Hanyuan Hang, et al. ∙

research

∙ 05/10/2016

Learning theory estimates with observations from general stationary stochastic processes

This paper investigates the supervised learning problem with observation...

0 Hanyuan Hang, et al. ∙

research

∙ 08/21/2015

Representation of Quasi-Monotone Functionals by Families of Separating Hyperplanes

We characterize when the level sets of a continuous quasi-monotone funct...

0 Ingo Steinwart, et al. ∙

research

∙ 08/15/2015

Towards an Axiomatic Approach to Hierarchical Clustering of Measures

We propose some axioms for hierarchical clustering of probability measur...

0 Philipp Thomann, et al. ∙

research

∙ 09/30/2014

Fully adaptive density-based clustering

The clusters of a distribution are often defined by the connected compon...

0 Ingo Steinwart, et al. ∙

research

∙ 08/14/2007

Fast rates for support vector machines using Gaussian kernels

For binary classification we establish learning rates up to the order of...

0 Ingo Steinwart, et al. ∙

research

∙ 07/02/2007

Learning from dependent observations

In most papers establishing consistency for learning algorithms it is as...

0 Ingo Steinwart, et al. ∙

Ingo Steinwart

Featured Co-authors