1 code implementation • 23 Jun 2022 • Manuel Nonnenmacher, Lukas Oldenburg, Ingo Steinwart, David Reeb
We therefore devise ExpCLR, a novel contrastive learning approach built on an objective that utilizes expert features to encourage both properties for the learned representation.
1 code implementation • NeurIPS 2021 • Manuel Nonnenmacher, Thomas Pfeil, Ingo Steinwart, David Reeb
We validate SOSP-H by comparing it to our second method SOSP-I that uses a well-established Hessian approximation, and to numerous state-of-the-art methods.
no code implementations • 4 Nov 2020 • Manuel Nonnenmacher, David Reeb, Ingo Steinwart
The loss surface of an overparameterized neural network (NN) possesses many global minima of zero training error.
no code implementations • 25 Sep 2019 • Manuel Nonnenmacher, David Reeb, Ingo Steinwart
The recently developed link between strongly overparametrized neural networks (NNs) and kernel methods has opened a new way to understand puzzling features of NNs, such as their convergence and generalization behaviors.