@article{PokuttaSpiegelZimmer, author = {Pokutta, Sebastian and Spiegel, Christoph and Zimmer, Max}, title = {Deep Neural Network Training with Frank-Wolfe}, abstract = {This paper studies the empirical efficacy and benefits of using projection-free first-order methods in the form of Conditional Gradients, a.k.a. Frank-Wolfe methods, for training Neural Networks with constrained parameters. We draw comparisons both to current state-of-the-art stochastic Gradient Descent methods as well as across different variants of stochastic Conditional Gradients. In particular, we show the general feasibility of training Neural Networks whose parameters are constrained by a convex feasible region using Frank-Wolfe algorithms and compare different stochastic variants. We then show that, by choosing an appropriate region, one can achieve performance exceeding that of unconstrained stochastic Gradient Descent and matching state-of-the-art results relying on L2-regularization. Lastly, we also demonstrate that, besides impacting performance, the particular choice of constraints can have a drastic impact on the learned representations.}, language = {en} } @inproceedings{ZimmerSpiegelPokutta, author = {Zimmer, Max and Spiegel, Christoph and Pokutta, Sebastian}, title = {How I Learned to Stop Worrying and Love Retraining}, series = {Proceedings of International Conference on Learning Representations}, booktitle = {Proceedings of International Conference on Learning Representations}, language = {en} } @inproceedings{ZimmerSpiegelPokutta, author = {Zimmer, Max and Spiegel, Christoph and Pokutta, Sebastian}, title = {Sparse Model Soups}, series = {Proceedings of International Conference on Learning Representations}, booktitle = {Proceedings of International Conference on Learning Representations}, language = {en} } @inproceedings{WaeldchenSharmaTuranetal., author = {W{\"a}ldchen, Stephan and Sharma, Kartikey and Turan, Berkant and Zimmer, Max and Pokutta, Sebastian}, title = {Interpretability Guarantees with Merlin-Arthur Classifiers}, series = {Proceedings of International Conference on Artificial Intelligence and Statistics}, booktitle = {Proceedings of International Conference on Artificial Intelligence and Statistics}, abstract = {We propose an interactive multi-agent classifier that provides provable interpretability guarantees even for complex agents such as neural networks. These guarantees consist of lower bounds on the mutual information between selected features and the classification decision. Our results are inspired by the Merlin-Arthur protocol from Interactive Proof Systems and express these bounds in terms of measurable metrics such as soundness and completeness. Compared to existing interactive setups, we rely neither on optimal agents nor on the assumption that features are distributed independently. Instead, we use the relative strength of the agents as well as the new concept of Asymmetric Feature Correlation which captures the precise kind of correlations that make interpretability guarantees difficult. We evaluate our results on two small-scale datasets where high mutual information can be verified explicitly.}, language = {en} } @inproceedings{MundingerPokuttaSpiegeletal., author = {Mundinger, Konrad and Pokutta, Sebastian and Spiegel, Christoph and Zimmer, Max}, title = {Extending the Continuum of Six-Colorings}, series = {Proceedings of Discrete Mathematics Days}, booktitle = {Proceedings of Discrete Mathematics Days}, language = {en} } @article{MundingerPokuttaSpiegeletal., author = {Mundinger, Konrad and Pokutta, Sebastian and Spiegel, Christoph and Zimmer, Max}, title = {Extending the Continuum of Six-Colorings}, series = {Geombinatorics Quarterly}, journal = {Geombinatorics Quarterly}, language = {en} } @inproceedings{PaulsZimmerKellyetal., author = {Pauls, Jan and Zimmer, Max and Kelly, Una M and Schwartz, Martin and Saatchi, Sassan and Ciais, Philippe and Pokutta, Sebastian and Brandt, Martin and Gieseke, Fabian}, title = {Estimating canopy height at scale}, series = {Proceedings of International Conference on Machine Learning}, booktitle = {Proceedings of International Conference on Machine Learning}, language = {en} }