267 citations · 813 across the 34 of their papers we have counts for
14 papers · 1 filter
Which Minimizer Does My Neural Network Converge To?
Manuel Nonnenmacher, David Reeb, Ingo Steinwart
The loss surface of an overparameterized neural network (NN) possesses many global minima of zero training error. We explain how common variants of the standard NN training procedu…
Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent
David Holzmüller, Ingo Steinwart
We prove that two-layer (Leaky)ReLU networks initialized by e.g. the widely used method proposed by He et al. (2015) and trained using gradient descent on a least-squares loss are…
Best-scored Random Forest Classification
Hanyuan Hang, Xiaoyu Liu, Ingo Steinwart
We propose an algorithm named best-scored random forest for binary classification problems. The terminology "best-scored" means to select the one with the best empirical performanc…
Optimal Learning with Anisotropic Gaussian SVMs
Hanyuan Hang, Ingo Steinwart
This paper investigates the nonparametric regression problem using SVMs with anisotropic Gaussian RBF kernels. Under the assumption that the target functions are resided in certain…
Adaptive Clustering Using Kernel Density Estimators
Ingo Steinwart, Bharath K. Sriperumbudur, Philipp Thomann
We derive and analyze a generic, recursive algorithm for estimating all splits in a finite cluster tree as well as the corresponding clusters. We further investigate statistical pr…
Learning Rates for Kernel-Based Expectile Regression
Muhammad Farooq, Ingo Steinwart
Conditional expectiles are becoming an increasingly important tool in finance as well as in other areas of applications. We analyse a support vector machine type approach for estim…
liquidSVM: A Fast and Versatile SVM package
Ingo Steinwart, Philipp Thomann
liquidSVM is a package written in C++ that provides SVM-type solvers for various classification and regression tasks. Because of a fully integrated hyper-parameter selection, very…
Sobolev Norm Learning Rates for Regularized Least-Squares Algorithm
Simon Fischer, Ingo Steinwart
Learning rates for least-squares regression are typically expressed in terms of -norms. In this paper we extend these rates to norms stronger than the -norm without requi…
Learning with Hierarchical Gaussian Kernels
Ingo Steinwart, Philipp Thomann, Nico Schmid
We investigate iterated compositions of weighted sums of Gaussian kernels and provide an interpretation of the construction that shows some similarities with the architectures of d…
Spatial Decompositions for Large Scale SVMs
Philipp Thomann, Ingrid Blaschzyk, Mona Meister +1
Although support vector machines (SVMs) are theoretically well understood, their underlying optimization problem becomes very expensive, if, for example, hundreds of thousands of s…
Kernel Density Estimation for Dynamical Systems
Hanyuan Hang, Ingo Steinwart, Yunlong Feng +1
We study the density estimation problem with observations generated by certain dynamical systems that admit a unique underlying invariant Lebesgue density. Observations drawn from…
Learning theory estimates with observations from general stationary stochastic processes
Hanyuan Hang, Yunlong Feng, Ingo Steinwart +1
This paper investigates the supervised learning problem with observations drawn from certain general stationary stochastic processes. Here by \emph{general}, we mean that many stat…
Towards an Axiomatic Approach to Hierarchical Clustering of Measures
Philipp Thomann, Ingo Steinwart, Nico Schmid
We propose some axioms for hierarchical clustering of probability measures and investigate their ramifications. The basic idea is to let the user stipulate the clusters for some el…
Learning from dependent observations
Ingo Steinwart, Don Hush, Clint Scovel
In most papers establishing consistency for learning algorithms it is assumed that the observations used for training are realizations of an i.i.d. process. In this paper we go far…