papers

Publications (6)

cs.CV2017

Associative Domain Adaptation

Philip Haeusser, Thomas Frerix, Alexander Mordvintsev +1

We propose associative domain adaptation, a novel technique for end-to-end domain adaptation with neural networks, the task of inferring class labels for an unlabeled target domain…

q-bio.BM2024

De novo design of high-affinity protein binders with AlphaProteo

Vinicius Zambaldi, David La, Alexander E. Chu +29

Computational design of protein-binding proteins is a fundamental capability with broad utility in biomedical research and biotechnology. Recent methods have made strides against s…

cs.LG2018

Proximal Backpropagation

Thomas Frerix, Thomas Möllenhoff, Michael Moeller +1

We propose proximal backpropagation (ProxProp) as a novel algorithm that takes implicit instead of explicit gradient steps to update the network parameters during neural network tr…

cs.LG2021

Variational Data Assimilation with a Learned Inverse Observation Operator

Thomas Frerix, Dmitrii Kochkov, Jamie A. Smith +3

Variational data assimilation optimizes for an initial state of a dynamical system such that its evolution fits observational data. The physical model can subsequently be evolved i…

math.OC2019

Approximating Orthogonal Matrices with Effective Givens Factorization

Thomas Frerix, Joan Bruna

We analyze effective approximation of unitary matrices. In our formulation, a unitary matrix is represented as a product of rotations in two-dimensional subspaces, so-called Givens…

cs.LG2020

Homogeneous Linear Inequality Constraints for Neural Network Activations

Thomas Frerix, Matthias Nießner, Daniel Cremers

We propose a method to impose homogeneous linear inequality constraints of the form on neural network activations. The proposed method allows a data-driven training appr…