8 citations · 8 across the 4 of their papers we have counts for
4 papers · 1 filter
Efficient and Robust Mixed-Integer Optimization Methods for Training Binarized Deep Neural Networks
Jannis Kurtz, Bubacarr Bah
Compared to classical deep neural networks its binarized versions can be useful for applications on resource-limited devices due to their reduction in memory consumption and comput…
An Integer Programming Approach to Deep Neural Networks with Binary Activation Functions
Bubacarr Bah, Jannis Kurtz
We study deep neural networks with binary activation functions (BDNN), i.e. the activation function only has two states. We show that the BDNN can be reformulated as a mixed-intege…
Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers
Bubacarr Bah, Holger Rauhut, Ulrich Terstiege +1
We study the convergence of gradient flows related to learning deep linear neural networks (where the activation function is the identity map) from data. In this case, the composit…
Discrete Optimization Methods for Group Model Selection in Compressed Sensing
Bubacarr Bah, Jannis Kurtz, Oliver Schaudt
In this article we study the problem of signal recovery for group models. More precisely for a given set of groups, each containing a small subset of indices, and for given linear…