TY - CONF AB - In classical machine learning, regression is treated as a black box process of identifying a suitable function from a hypothesis set without attempting to gain insight into the mechanism connecting inputs and outputs. In the natural sciences, however, finding an interpretable function for a phenomenon is the prime goal as it allows to understand and generalize results. This paper proposes a novel type of function learning network, called equation learner (EQL), that can learn analytical expressions and is able to extrapolate to unseen domains. It is implemented as an end-to-end differentiable feed-forward network and allows for efficient gradient based training. Due to sparsity regularization concise interpretable expressions can be obtained. Often the true underlying source expression is identified. AU - Martius, Georg S AU - Lampert, Christoph ID - 6841 T2 - 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings TI - Extrapolation and learning equations ER - TY - JOUR AB - We generalize winning conditions in two-player games by adding a structural acceptance condition called obligations. Obligations are orthogonal to the linear winning conditions that define whether a play is winning. Obligations are a declaration that player 0 can achieve a certain value from a configuration. If the obligation is met, the value of that configuration for player 0 is 1. We define the value in such games and show that obligation games are determined. For Markov chains with Borel objectives and obligations, and finite turn-based stochastic parity games with obligations we give an alternative and simpler characterization of the value function. Based on this simpler definition we show that the decision problem of winning finite turn-based stochastic parity games with obligations is in NP∩co-NP. We also show that obligation games provide a game framework for reasoning about p-automata. © 2017 The Association for Symbolic Logic. AU - Chatterjee, Krishnendu AU - Piterman, Nir ID - 684 IS - 2 JF - Journal of Symbolic Logic SN - 0022-4812 TI - Obligation blackwell games and p-automata VL - 82 ER - TY - JOUR AB - By applying methods and principles from the physical sciences to biological problems, D'Arcy Thompson's On Growth and Form demonstrated how mathematical reasoning reveals elegant, simple explanations for seemingly complex processes. This has had a profound influence on subsequent generations of developmental biologists. We discuss how this influence can be traced through twentieth century morphologists, embryologists and theoreticians to current research that explores the molecular and cellular mechanisms of tissue growth and patterning, including our own studies of the vertebrate neural tube. AU - Briscoe, James AU - Kicheva, Anna ID - 685 JF - Mechanisms of Development SN - 09254773 TI - The physics of development 100 years after D'Arcy Thompson's “on growth and form” VL - 145 ER - TY - CONF AB - We show that the framework of topological data analysis can be extended from metrics to general Bregman divergences, widening the scope of possible applications. Examples are the Kullback - Leibler divergence, which is commonly used for comparing text and images, and the Itakura - Saito divergence, popular for speech and sound. In particular, we prove that appropriately generalized čech and Delaunay (alpha) complexes capture the correct homotopy type, namely that of the corresponding union of Bregman balls. Consequently, their filtrations give the correct persistence diagram, namely the one generated by the uniformly growing Bregman balls. Moreover, we show that unlike the metric setting, the filtration of Vietoris-Rips complexes may fail to approximate the persistence diagram. We propose algorithms to compute the thus generalized čech, Vietoris-Rips and Delaunay complexes and experimentally test their efficiency. Lastly, we explain their surprisingly good performance by making a connection with discrete Morse theory. AU - Edelsbrunner, Herbert AU - Wagner, Hubert ID - 688 SN - 18688969 TI - Topological data analysis with Bregman divergences VL - 77 ER - TY - JOUR AB - Pursuing the similarity between the Kontsevich-Soibelman construction of the cohomological Hall algebra (CoHA) of BPS states and Lusztig's construction of canonical bases for quantum enveloping algebras, and the similarity between the integrality conjecture for motivic Donaldson-Thomas invariants and the PBW theorem for quantum enveloping algebras, we build a coproduct on the CoHA associated to a quiver with potential. We also prove a cohomological dimensional reduction theorem, further linking a special class of CoHAs with Yangians, and explaining how to connect the study of character varieties with the study of CoHAs. AU - Davison, Ben ID - 687 IS - 2 JF - Quarterly Journal of Mathematics SN - 00335606 TI - The critical CoHA of a quiver with potential VL - 68 ER -