Braverman Readings in Machine Learning. Key Ideas from Inception to Current State

1. Front Matter

   Pages I-XII

   PDF

2. Bridging Past and Future

   1. Front Matter

      Pages 1-1

      PDF

   2. Potential Functions for Signals and Symbolic Sequences

      • Valentina Sulimova, Vadim Mottl

      Pages 3-31

   3. Braverman’s Spectrum and Matrix Diagonalization Versus iK-Means: A Unified Framework for Clustering

      • Boris Mirkin

      Pages 32-51

   4. Compactness Hypothesis, Potential Functions, and Rectifying Linear Space in Machine Learning

      • Vadim Mottl, Oleg Seredin, Olga Krasotkina

      Pages 52-102

   5. Conformal Predictive Distributions with Kernels

      • Vladimir Vovk, Ilia Nouretdinov, Valery Manokhin, Alex Gammerman

      Pages 103-121

   6. On the Concept of Compositional Complexity

      • Lev I. Rozonoer

      Pages 122-127

   7. On the Choice of a Kernel Function in Symmetric Spaces

      • M. A. Aizerman, E. M. Braverman, Lev I. Rozonoer

      Pages 128-147

   8. Causality Modeling and Statistical Generative Mechanisms

      • Igor Mandel

      Pages 148-186

3. Novel Developments

   1. Front Matter

      Pages 187-187

      PDF

   2. One-Class Semi-supervised Learning

      • Evgeny Bauman, Konstantin Bauman

      Pages 189-200

   3. 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

   4. On One Approach to Robot Motion Planning

      • Vladimir Lumelsky

      Pages 213-228

   5. Geometrical Insights for Implicit Generative Modeling

      • Leon Bottou, Martin Arjovsky, David Lopez-Paz, Maxime Oquab

      Pages 229-268

   6. Deep Learning in the Natural Sciences: Applications to Physics

      • Peter Sadowski, Pierre Baldi

      Pages 269-297

   7. From Reinforcement Learning to Deep Reinforcement Learning: An Overview

      • Forest Agostinelli, Guillaume Hocquet, Sameer Singh, Pierre Baldi

      Pages 298-328

4. Personal and Beyond

   1. Front Matter

      Pages 329-329

      PDF

   2. A Man of Unlimited Capabilities (in Memory of E. M. Braverman)

      • Lev I. Rozonoer

      Pages 331-332

   3. Braverman and His Theory of Disequilibrium Economics

      • Mark Levin

      Pages 333-340

   4. Misha Braverman: My Mentor and My Model

      • Boris Mirkin

      Pages 341-348

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 essaysby a friend, a student, and a colleague.

• artificial intelligence
• classification accuracy
• cluster analysis
• clustering algorithms
• data mining
• kernel function
• learning algorithms
• machine learning
• mixture modeling
• models of learning
• multivariate statistics
• probability
• robotics
• semi-supervised learning
• supervised learning
• Support Vector Machines (SVM)
• algorithm analysis and problem complexity

• West Newton, USA

  Lev Rozonoer

• National Research University Higher School of Economics, Moscow, Russia

  Boris Mirkin

• Rutgers University, Piscataway, USA

  Ilya Muchnik

Lev Rozonoer, West Newton, MA, USA;Boris Mirkin, National Research University Higher School of Economics, Moscow, Russian Federation;
Ilya Muchnik, Rutgers University, Piscataway, NJ, USA.

Policies and ethics