
Which Minimizer Does My Neural Network Converge To?
The loss surface of an overparameterized neural network (NN) possesses m...
read it

Adaptive Learning Rates for Support Vector Machines Working on Data with Low Intrinsic Dimension
We derive improved regression and classification rates for support vecto...
read it

SVM Learning Rates for Data with Low Intrinsic Dimension
We derive improved regression and classification rates for support vecto...
read it

Training TwoLayer ReLU Networks with Gradient Descent is Inconsistent
We prove that twolayer (Leaky)ReLU networks initialized by e.g. the wid...
read it

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...
read it

PACBayesian Bounds for Deep Gaussian Processes
Variational approximation techniques and inference for stochastic models...
read it

Bestscored Random Forest Classification
We propose an algorithm named bestscored random forest for binary class...
read it

Global Minima of DNNs: The Plenty Pantry
A common strategy to train deep neural networks (DNNs) is to use very la...
read it

Improved Classification Rates for Localized SVMs
One of the main characteristics of localized support vector machines tha...
read it

A Sober Look at Neural Network Initializations
Initializing the weights and the biases is a key part of the training pr...
read it

Optimal Learning with Anisotropic Gaussian SVMs
This paper investigates the nonparametric regression problem using SVMs ...
read it

Strictly proper kernel scores and characteristic kernels on compact spaces
Strictly proper kernel scores are wellknown tool in probabilistic forec...
read it

Adaptive Clustering Using Kernel Density Estimators
We investigate statistical properties of a clustering algorithm that rec...
read it

Learning Rates for KernelBased Expectile Regression
Conditional expectiles are becoming an increasingly important tool in fi...
read it

Sobolev Norm Learning Rates for Regularized LeastSquares Algorithm
Learning rates for regularized leastsquares algorithms are in most case...
read it

liquidSVM: A Fast and Versatile SVM package
liquidSVM is a package written in C++ that provides SVMtype solvers for...
read it

Kernel Density Estimation for Dynamical Systems
We study the density estimation problem with observations generated by c...
read it

Learning theory estimates with observations from general stationary stochastic processes
This paper investigates the supervised learning problem with observation...
read it

Representation of QuasiMonotone Functionals by Families of Separating Hyperplanes
We characterize when the level sets of a continuous quasimonotone funct...
read it

Towards an Axiomatic Approach to Hierarchical Clustering of Measures
We propose some axioms for hierarchical clustering of probability measur...
read it

Fully adaptive densitybased clustering
The clusters of a distribution are often defined by the connected compon...
read it

Fast rates for support vector machines using Gaussian kernels
For binary classification we establish learning rates up to the order of...
read it

Learning from dependent observations
In most papers establishing consistency for learning algorithms it is as...
read it
Ingo Steinwart
is this you? claim profile
Professor of Department of Mathematics at University of Stuttgart, Professor of Institute of Stochastics and Applications at University of Stuttgart, Professor of Department of Stochastics University of Stuttgart.