3 papers
cs.LG2022
A Derivation of Feedforward Neural Network Gradients Using Fréchet Calculus
Thomas Hamm
We present a derivation of the gradients of feedforward neural networks using Fréchet calculus which is arguably more compact than the ones usually presented in the literature. We…
math.ST2021
Intrinsic Dimension Adaptive Partitioning for Kernel Methods
Thomas Hamm, Ingo Steinwart
We prove minimax optimal learning rates for kernel ridge regression, resp.~support vector machines based on a data dependent partition of the input space, where the dependence of t…
math.ST2020
Adaptive Learning Rates for Support Vector Machines Working on Data with Low Intrinsic Dimension
Thomas Hamm, Ingo Steinwart
We derive improved regression and classification rates for support vector machines using Gaussian kernels under the assumption that the data has some low-dimensional intrinsic stru…