Braverman Readings in Machine Learning. Key Ideas from Inception to Current State: International Conference Commemorating the 40th Anniversary of Emmanuil Braverman's Decease, Boston, MA, USA, April 28-30, 2017, Invited Talks

Description

This state-of-the-art survey is dedicated to the memory of Emmanuil Markovich Braverman (1931-1977), a pioneer in developing machine learning theory. The 12 revised full papers and 4 short papers included in this volume were presented at the conference "Braverman Readings in Machine Learning: Key Ideas from Inception to Current State" held in Boston, MA, USA, in April 2017, commemorating the 40th anniversary of Emmanuil Braverman's decease. The papers present an overview of some of Braverman's ideas and approaches. The collection is divided in three parts. The first part bridges the past and the present and covers the concept of kernel function and its application to signal and image analysis as well as clustering. The second part presents a set of extensions of Braverman's work to issues of current interest both in theory and applications of machine learning. The third part includes short essays by a friend, a student, and a colleague. Front Matter ....Pages I-XII Front Matter ....Pages 1-1 Potential Functions for Signals and Symbolic Sequences (Valentina Sulimova, Vadim Mottl)....Pages 3-31 Braverman’s Spectrum and Matrix Diagonalization Versus iK-Means: A Unified Framework for Clustering (Boris Mirkin)....Pages 32-51 Compactness Hypothesis, Potential Functions, and Rectifying Linear Space in Machine Learning (Vadim Mottl, Oleg Seredin, Olga Krasotkina)....Pages 52-102 Conformal Predictive Distributions with Kernels (Vladimir Vovk, Ilia Nouretdinov, Valery Manokhin, Alex Gammerman)....Pages 103-121 On the Concept of Compositional Complexity (Lev I. Rozonoer)....Pages 122-127 On the Choice of a Kernel Function in Symmetric Spaces (M. A. Aizerman, E. M. Braverman, Lev I. Rozonoer)....Pages 128-147 Causality Modeling and Statistical Generative Mechanisms (Igor Mandel)....Pages 148-186 Front Matter ....Pages 187-187 One-Class Semi-supervised Learning (Evgeny Bauman, Konstantin Bauman)....Pages 189-200 Prediction of Drug Efficiency by Transferring Gene Expression Data from Cell Lines to Cancer Patients (Nicolas Borisov, Victor Tkachev, Anton Buzdin, Ilya Muchnik)....Pages 201-212 On One Approach to Robot Motion Planning (Vladimir Lumelsky)....Pages 213-228 Geometrical Insights for Implicit Generative Modeling (Leon Bottou, Martin Arjovsky, David Lopez-Paz, Maxime Oquab)....Pages 229-268 Deep Learning in the Natural Sciences: Applications to Physics (Peter Sadowski, Pierre Baldi)....Pages 269-297 From Reinforcement Learning to Deep Reinforcement Learning: An Overview (Forest Agostinelli, Guillaume Hocquet, Sameer Singh, Pierre Baldi)....Pages 298-328 Front Matter ....Pages 329-329 A Man of Unlimited Capabilities (in Memory of E. M. Braverman) (Lev I. Rozonoer)....Pages 331-332 Braverman and His Theory of Disequilibrium Economics (Mark Levin)....Pages 333-340 Misha Braverman: My Mentor and My Model (Boris Mirkin)....Pages 341-348 List of Braverman’s Papers Published in the “Avtomatika i telemekhanika” Journal, Moscow, Russia, and Translated to English as “Automation and Remote Control” Journal (Ilya Muchnik)....Pages 349-351 Correction to: Braverman and His Theory of Disequilibrium Economics (Mark Levin)....Pages E1-E1 Back Matter ....Pages 353-353