Publications (13)
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…
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…
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),…
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…
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…
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…