papers

Publications (13)

cs.LG2021

Stable Recovery of Entangled Weights: Towards Robust Identification of Deep Neural Networks from Minimal Samples

Christian Fiedler, Massimo Fornasier, Timo Klock +1

In this paper we approach the problem of unique and stable identifiability of generic deep artificial neural networks with pyramidal shape and smooth activation functions from a fi…

math.NA2024

Convergence of Anisotropic Consensus-Based Optimization in Mean-Field Law

Massimo Fornasier, Timo Klock, Konstantin Riedl

In this paper we study anisotropic consensus-based optimization (CBO), a multi-agent metaheuristic derivative-free optimization method capable of globally minimizing nonconvex and…

cs.LG2026

Gradient is All You Need? How Consensus-Based Optimization can be Interpreted as a Stochastic Relaxation of Gradient Descent

Konstantin Riedl, Timo Klock, Carina Geldhauser +1

In this paper, we provide a novel analytical perspective on the theoretical understanding of gradient-based learning algorithms by interpreting consensus-based optimization (CBO),…

math.NA2024

Consensus-Based Optimization Methods Converge Globally

Massimo Fornasier, Timo Klock, Konstantin Riedl

In this paper, we study consensus-based optimization (CBO), which is a multi-agent metaheuristic derivative-free optimization method that can globally minimize nonconvex nonsmooth…

math.ST2020

Estimating multi-index models with response-conditional least squares

Timo Klock, Alessandro Lanteri, Stefano Vigogna

The multi-index model is a simple yet powerful high-dimensional regression model which circumvents the curse of dimensionality assuming for s…

cs.LG2024

Semi-Supervised Manifold Learning with Complexity Decoupled Chart Autoencoders

Stefan C. Schonsheck, Scott Mahan, Timo Klock +2

Autoencoding is a popular method in representation learning. Conventional autoencoders employ symmetric encoding-decoding procedures and a simple Euclidean latent space to detect h…