Conference Program

October 5

7:30 – 8:30	Registration
8:30 – 8:40	Prof. Elena Bunina Russia, Yandex, Yandex School of Data Analysis and Moscow State University	Welcome & Keynote Address
	Prof. Ilya Muchnik USA, Rutgers University (NJ), and Russia, Yandex School of Data Analysis

Session I Chair Sc.D. Anatoli Michalski, Russia V. A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences, Moscow
Deep Learning
8:40 – 9:20	Prof. Lior Wolf Israel, Blavatnik School of Computer Science at Tel Aviv University	Image Annotation – The Marriage of Computer Vision and NLP Using Deep Learning
9:20 – 10:00	Dr. Li Deng USA, Microsoft Research	Deep Generative and Discriminative Models for Speech Recognition

10:00 – 10:15	Break

10:15 – 10:55	Prof. John Shawe-Taylor UK, Centre for Computation Statistics and Machine Learning at University College London	Deep-er Kernels
10:55 – 11:35	Prof. Pierre Baldi USA, Department of Computer Science, Center for Machine Learning and Intelligent Systems, and Institute for Genomics and Bioinformatics at University of California, Irvine	Deep Learning Applications in the Natural Sciences

11:35 – 11:50	Break

Sublinearity
11:50 – 12:10	Prof. Artur Czumaj UK, Centre for Discrete Mathematics and its Applications (DIMAP), University of Warwick	Sublinear-time Approximation Algorithms

Generalizations
12:10 – 12:30	Sc.D. Anatoli Michalski Russia, V. A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences, Moscow	Data Properties Estimation as Statistical Inverse Problem
12:30 – 12:50	Dr. Varvara Tsurko Russia, V. A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences, Moscow	Feature Selection by Conditional Distribution Contrasting

12:50 – 13:40	Lunch

Session II Chair Arkady Borkovsky, USA Yandex
Causality
13:40 – 14:00	Vyacheslav Teterin Russia, The Computer Training Center «Specialist», Yandex School of Data Analysis	Approximation of Causal Dependences by Structural Regression Equations
14:00 – 14:40	Prof. Bernhard Schölkopf Germany, Max Planck Institute for Intelligent Systems	Toward Causal Machine Learning
Quantum Learning
14:40 – 15:00	Dr. Dominik Janzing Germany, Max Planck Institute for Intelligent Systems	Inferring Causal Structure from Statistical Dependences among n Variables — Differences between Classical and Quantum Communication Scenarios

15:00 – 15:15	Break

15:15 – 15:35	Dr. Peter Wittek Spain, ICFO-The Institute of Photonic Sciences, Barcelona	What Can We Expect from Quantum Machine Learning?
Submodularity and Learning
15:35 – 16:15	Prof. Francis Bach France, Ecole Normale Supérieure de Paris	Learning with Submodular Functions: A Convex Optimization Perspective
16:15 – 16:35	Prof. Andreas Krause Switzerland, ETH Zürich	Summarizing Massive Data Sets via Large-Scale Submodular Maximization
16:35 – 16:40	Dr. Tomas Werner, Czech Republic, Czech Technical University Prof. Michail Schlesinger, Ukraine, International Research and Training Centre of Information Technologies and Systems, National Academy of Science of Ukraine, Cybernetica Centre	Flash Presentation with slides for the Poster: Minimizing Submodular Discrete Energies by Integer Re-parameterizations

16:40 – 16:50	Break

Clustering and Sparsity
16:50 – 17:10	Prof. Boris Mirkin Russia, National Research University Higher School of Economics in Moscow, UK, Birkbeck University of London	K-means and Anomalous Clustering
17:10 – 17:30	Ilya Trofimov Russia, Yandex Data Factory	Distributed Coordinate Descent for Regularized Logistic Regression
17:30 – 17:35	Zachary Chase Lipton ML scientist, Amazon, University of California, San Diego, USA	Flash Presentation with slides for the Poster: Efficient Elastic Net Regularization for Sparse Linear Models in the Multilabel Setting
17:35 – 17:55	Dr. Mikhail Bilenko USA, Microsoft	Large-Scale Learning

17:55 – 18:05	Break

18:05 – 20:35	Discussion "Deep Learning". Moderator Dr. Li Deng (expected participants: Pierre Baldi, John Shawe-Taylor, Nathan Intrator, Alexandre Klementiev, Dmitrij Schlesinger and others)

October 6

Session III Chair Dr. Andrey Ustyuzhanin, Russia Yandex, Yandex School of Data Analysis
Particular Problems
9:00 – 9:20	Dr. Timothy Hospedales UK, School of Electronic Engineering & Computer Science, Queen Mary University of London	Zero-Shot Learning
9:20 – 9:40	Prof. Sándor Darányi Sweden, Högskolan i Borås, Swedish School of Library and Information Science	A Potential Surface Underlying Meaning?
9:40 – 10:20	Prof. Nathan Intrator Israel, Blavatnik School of Computer Science, Sagol School of Neuroscience	Can Machine Learning replace Signal Processing?

10:20 – 10:35	Break

Generalizations and Physics
10:35 – 10:55	Boris Belyaev Russia, Yandex	Relationship Graph Filtering Drawing on the Example of the Site Hierarchy Extraction
10:55 – 11:00	Gleb Turkanov Russia, Russian Academy of Sciences, Moscow Institute of Physics and Technology	Flash Presentation with slides for the Poster: Modified Naive Bayes with Hurst Exponent as Quantitative Measure of Data Mutual Dependence
11:00 – 11:05	Dr. Andrey Ustyuzhanin Yandex, Yandex School of Data Analysis	Flash Presentation with slides for the Poster: Yandex + CERN: Three Years of Collaboration of Data Science with Particle Physics
11:05 – 11:10	Tatiana Likhomanenko Russia, National Research University Higher School of Economics, Yandex Data Factory Dr. Andrey Ustyuzhanin Russia, Yandex, Yandex School of Data Analysis	Flash Presentation with slides for the Poster: Machine Learning and Optimization of LHC Real-Time Event Stream Filter for New Physics Discoveries
Applications
11:10 – 11:15	Dr. Pedro J. Ballester France, Cancer Research Centre of Marseille	Flash Presentation with slides for the Poster: The Use of Random Forest to Improve Molecular Docking Tools for Drug Design
11:15 – 11:20	Assoc. Prof. Halil İbrahim Erdal, Dr. Aykut Ekinci Turkey, Turkish Cooperation and Coordination Agency, F. A. Hayek Visiting Scholar, George Mason University	Flash Presentation with slides for the Poster: Bank Failure Prediction Using Hybrid Classifier Ensembles of Random Sub-Spaces and Bagging
11:20 – 11:25	Dr. Andreas Karathanasopoulos Associate Professor: American University of Beirut	Flash Presentation with slides for the Poster: Trading the FTSE100 Index – 'Adaptive' Modeling and Optimisation Techniques
11:25 – 11:30	Prof. Marius Kloft Germany, Humboldt University of Berlin Department of Computer Science	Flash Presentation with slides for the Poster: Kernel-based Machine Learning from Multiple Information Sources: Learning Theory, Algorithms, and Applications in Visual Image Recognition and Computational Biology
11:30 – 11:35	Dr. Andrey Mishchenko Russia, Yandex	Flash Presentation with slides for the Poster: Bots Filtering in Crowd-Sourcing
11:35 – 11:40	Dr. Michael Roizner Russia, Yandex	Flash Presentation with slides for the Poster: Yandex Recommender System
11:40 – 11:45	Denis Elshin, Daria Gubar Russia, Yandex	Flash Presentation with slides for the Poster: Internet Search Trends Extraction: Using Topic Modeling Ideas for Clustering User Queries
11:45 – 11:50	Boris Okun Russia, Yandex	Flash Presentation with slides for the Poster: Expansion of Video Categories Through Link and Users Graphs
11:50 – 11:55	Anton Slesarev Russia, Yandex	Flash Presentation with slides for the Poster: Deep Neural Networks for Fast Object Detection

11:55 – 12:10	Break

12:10 – 12:30	Michael Levin Russia, Yandex Data Factory, Yandex	MatrixNet Applications at Yandex
A New View on Fundamental Problems
12:30 – 12:50	Dr. Dmitrij Schlesinger Germany, Dresden University of Technology	Implicit Modeling — A Generalization of Discriminative and Generative Approaches
12:50 – 13:10	Andrey Gulin Russia, Yandex	Online Learning or Don’t Look Ahead

13:10 – 14:00	Lunch

Session IV Chair Prof. Alexander Gammerman, UK Royal Holloway, University of London
14:00 – 15:20	Prof. Vladimir Vapnik USA, Columbia University, Facebook	Intelligent Learning: Similarity Control and Knowledge Transfer

15:20 – 15:35	Break

15:35 – 19:00	Social program

19:00	Banquet

October 7

Session V Chair Dr. Evgeny Burnaev, Russia Institute for Information Transmission Problems of Russian Academy of Sciences
Machine Learning Foundations
9:00 – 9:40	Prof. Vladimir Vovk UK, Royal Holloway, University of London	Large-Scale Probabilistic Prediction With and Without Validity Guarantees
9:40 – 10:20	Prof. Michail Schlesinger, Evgeniy Vodolazskiy Ukraine, International Research and Training Centre of Information Technologies and Systems, National Academy of Science of Ukraine, Cybernetica Centre	Minimax Deviation Strategies for Machine Learning and Recognition with Short Learning Samples

10:20 – 10:35	Break

10:35 – 10:40	Ilya Tolstikhin Germany, Max Planck Institute for Intelligent Systems, Department of Empirical Inference	Flash Presentation with slides for the Poster: Global and Local Complexity Measures for Transductive Learning
10:40 – 10:45	Prof. Igor Kononenko Slovenia, Laboratory for Cognitive Modeling University of Ljubljana	Flash Presentation with slides for the Poster: Explaining Predictions of Arbitrary Model with Feature Contributions
10:45 – 11:05	Dr. Rauf Izmailov USA, Vencore Labs Prof. Vladimir Vapnik USA, Columbia University, Facebook	Multidimensional Conditional Probability Estimation Using the V-Matrix Method
Combinatorics
11:05 – 11:25	Prof. Vadim E. Levit Israel, Department of Computer Science and Mathematics, Ariel University	Is It Really NP-Hard to Survive in Big-Data?
11:25 – 11:45	Prof. Michael Khachay Russia, Krasovsky Institute of Mathematics and Mechanics, Ural Federal University, Ekaterinburg	Committee Polyhedral Separability: Complexity and Polynomial Approximation
Text Analysis and Understanding
11:45 – 11:50	Dmytro Prylipko Germany, Yandex	Flash Presentation with slides for the Poster: Functional Analysis of F0 Contours for Recognition of Paralinguistics from Speech
11:50 – 11:55	Anton Bakhtin Russia, Yandex	Flash Presentation with slides for the Poster: Faster Recurrent Neural Network Language Modeling Toolkit with Logarithmic and Sub-logarithmic Cost Function Approximation Algorithms
11:55 – 12:00	Anna Potapenko Russia, Yandex School of Data Analysys Prof. Konstantin Vorontsov Russia, Yandex	Flash Presentation with slides for the Poster: Linguistic Regularization of Topic Models

12:00 – 12:15	Break

12:15 – 12:55	Prof. Jordan Boyd-Graber USA, University of Colorado	Thinking on your Feet: Reinforcement Learning for Incremental Language Tasks
12:55 – 13:15	Dr. Alexandre Klementiev Germany, Amazon	Inducing Crosslingual Distributed Representations of Words
13:15 – 14:05	Lunch
Session VI Chair Dr. Uri Degen, Israеl TSG IT Advanced Systems Ltd.
14:05 – 14:45	Prof. Konstantin Vorontsov Russia, Yandex	Additive Regularization of Topic Models: Towards Exploratory Search and Other Multi-Criteria Applications
Applications
14:45 – 15:25	Dr. Uri Degen, Dr. Leonid Shvartser, Prof. Igor Korotayev, Dr. Rima Gandlin, Alexander Knafel Israеl, TSG IT Advanced Systems Ltd.	Detecting of hidden patterns in air/maritime/human situation picture
15:25 – 15:45	Dr. Uri Degen, Dr. Leonid Shvartser, Shmuel Teppler Israеl, TSG IT Advanced Systems Ltd.	Identification of Activity Patterns in Communication Data without Content
15:45 – 16:25	Prof. Alexander Gammerman UK, Royal Holloway, University of London	Reliable Diagnostics by Conformal Predictors

16:25 – 16:40	Break

16:40 – 17:00	Dr. Leonid Shvartser Israеl, TSG Advanced Systems Ltd Michael Markov USA, MPI International Inc Dr. Olga Krasotkina Russia, Moscow State University Prof. Vadim Mottl' Russia, Computing Center of the Russian Academy of Sciences	Dynamic Style Analysis of Hedge Funds and Kalman Smoother
17:00 – 17:05	Maxim Ryabinskiy, Dr. Dmitriy Finikov Russia, Yandex.Terra	Flash Presentation with slides for the Poster: The Machine Learning Techniques in Seismic Data Processing and Interpretation Problems
17:05 – 17:25	Maxim Ryabinskiy, Dr. Dmitriy Finikov, Dr. Nikita Zelinsky Russia, Yandex.Terra	Sparse Regression and Data Preparation for Machine Learning in Seismic Data Processing
17:25 – 17:30	Artem Babenko Russia, Yandex	Flash Presentation with slides for the Poster: Deep Learning for Image Retrieval
17:30 – 17:35	Dmitry Krivokon, Alexey Gorodilov Russia, Yandex	Flash Presentation with slides for the Poster: Query Model for Image Search based on User Clicks and NN Features
Current Methodological Progress
17:35 – 17:40	Dr. Evgeny Burnaev Russia, Institute for Information Transmission Problems of Russian Academy of Sciences Prof. Vladimir Vovk UK, Royal Holloway, University of London	Flash Presentation with slides for the Poster: Conformalized Kernel Ridge Regression and Its Efficiency
17:40 – 17:45	Prof. Alex Bernshtein, A.P. Kuleshov, Yu.A. Yanovich Russia, National Research University Higher School of Economics	Flash Presentation with slides for the Poster: Locally Isometric and Conformal Low-dimensional Data Representation in Data Analysis
17:45 – 17:50	Prof. Dmitry Vetrov National Research University Higher School of Economics, Yandex School of Data Analysis, Skoltech Alexander Novikov, Dmitry Podoprikhin Skoltech Anton Osokin INRIA - SIERRA project-team	Flash Presentation with slides for the Poster: Tensor perspective of deep neural networks

17:50 – 18:00	Break

18:00 – 20:00	Discussion "What Learning Problem is About: Brute Force and Intelligent Paradigms of Learning". Moderator: Vladimir Vapnik (expected participants: Konstantin Vorontsov, Anatoli Michalski, Vladimir Vovk, Bernhard Schölkopf, Varvara Tsurko, Andrey Ustyuzhanin and others).
20:00 – 20:30	Arkady Volozh Russia, Yandex Prof. Elena Bunina Russia, Yandex, Yandex School of Data Analysis and Moscow State University	Closing Remarks

October 8

9:00 – 15:00	Business session «Machine Learning and Big Data: Business Challenges»
15:00	Conference closes. Networking

Conference Program

October 5

Session I

Deep Learning

Sublinearity

Generalizations

Session II

Causality

Quantum Learning

Submodularity and Learning

Clustering and Sparsity

October 6

Session III

Particular Problems

Generalizations and Physics

Applications

A New View on Fundamental Problems

Session IV

October 7

Session V

Machine Learning Foundations

Combinatorics

Text Analysis and Understanding

Session VI

Applications

Current Methodological Progress

October 8