speakers & topics
My research focus is on using kernel methods to reveal properties and relations in data. A first application is in measuring distances between probability distributions. These distances can be used to determine strength of dependence, for example in measuring how strongly two bodies of text in different languages are related; testing for similarities in two datasets, which can be used in attribute matching for databases (that is, automatically finding which fields of two databases correspond); and testing for conditional dependence, which is useful in detecting redundant variables that carry no additional predictive information, given the variables already observed. I am also working on applications of kernel methods to inference in graphical models, where the relations between variables are learned directly from training data.
I am currently leading the Probabilistic Learning Group in the Department of Empirical Inference at the Max Planck Institute for Intelligent Systems in Tübingen. Prior to this I was a post-doctoral researcher at the University of Cambridge working with Zoubin Ghahramani, and previously, I was a Humboldt post-doctoral fellowship holder at Max Planck Institute for Software Systems, where I work with Manuel Gomez Rodriguez. I obtained my PhD in 2014 and my Master degree in 2012 from the University Carlos III in Madrid. During my PhD I worked under the supervision of Fernando Perez-Cruz
Joris M. Mooij studied mathematics and physics and received his PhD degree with honors from the Radboud University Nijmegen (the Netherlands) in 2007. His PhD research concerned approximate inference in graphical models. During the next three years, he worked on causal discovery as a postdoc at the Max Planck Institute for Biological Cybernetics in Tübingen (Germany). In 2011 he obtained an NWO VENI grant, which allowed him to do a second postdoc, this time at the Radboud University Nijmegen. In 2013 he became Assistant Professor at the Informatics Institute of the University of Amsterdam (the Netherlands). In the next years, he obtained an NWO VIDI grant and an ERC Starting Grant, allowing him to start his own research group, consisting of 3 PhD students and 3 postdocs, focussing entirely on causal discovery. The research topics addressed by his group span the entire spectrum from causal modeling, discovery, prediction, validation and application and combine mathematical, algorithmic, statistical and modeling aspects. In 2017 he was promoted to Associate Professor. He has won several awards for his work.
Justin Solomon is an assistant professor in the MIT Department of Electrical Engineering and Computer Science. He leads the MIT Geometric Data Processing Group, which studies problems at the intersection of geometry and applications in graphics, learning, and other disciplines.
Marco Cuturi joined Google Brain, in Paris, in October 2018. He graduated from ENSAE (2001), ENS Cachan (Master MVA, 2002) and holds a PhD in applied maths obtained in 2005 at Ecole des Mines de Paris. He worked as a post-doctoral researcher at the Institute of Statistical Mathematics, Tokyo, between 11/2005 and 03/2007. He worked in the financial industry between 04/2007 and 09/2008. After working at the ORFE department of Princeton University between 02/2009 and 08/2010 as a lecturer, he was at the Graduate School of Informatics of Kyoto University between 09/2010 and 09/2016 as a tenured associate professor. He then joined ENSAE, the french national school for statistics and economics, in 9/2016, where he still teaches. His recent proposal to solve optimal transport using an entropic regularization has re-ignited interest in optimal transport and Wasserstein distances in the machine learning community. His work has recently focused on applying that loss function to problems involving probability distributions, e.g. topic models / dictionary learning for text and images, parametric inference for generative models, regression with a Wasserstein loss and probabilistic embeddings for words.
Mark Girolami is an EPSRC Established Career Research Fellow (2012 - 2018) and previously an EPSRC Advanced Research Fellow (2007 - 2012). He is the Director of the £10M Lloyds Register Foundation - Turing Programme on Data Centric Engineering and previously led the EPSRC funded Research Network on Computational Statistics and Machine Learning. His research and that of his group covers the investigation and development of advanced novel statistical methodology driven by applications in the life, clinical, physical, chemical, engineering and ecological sciences. He also works closely with industry where he has several patents leading from his work on e.g. activity profiling in telecommunications networks and developing statistical techniques for the machine based identification of counterfeit currency which is now an established technology used in current Automated Teller Machines. He has worked as a consultant for the Global Forecasting Team at Amazon in Seattle
Michael Bronstein (PhD 2007, Technion, Israel) is a professor at Imperial College London, where he holds the Chair in Machine Learning and Pattern Recognition and Royal Society Wolfson Merit Award. He holds/has held visiting appointments at Stanford, Harvard, MIT, and TUM. Michael's main research interest is in theoretical and computational methods for geometric data analysis. He is a Fellow of IEEE and IAPR, ACM Distinguished Speaker, and World Economic Forum Young Scientist. He is the recipient of multiple prestigious awards, including four ERC grants, two Google Faculty awards, and the 2018 Facebook Computational Social Science award. Besides academic work, Michael was a co-founder and technology executive at Novafora (2005-2009) developing large-scale video analysis methods, and one of the chief technologists at Invision (2009-2012) developing low-cost 3D sensors. Following the multi-million acquisition of Invision by Intel in 2012, Michael has been one of the key developers of the Intel RealSense technology in the role of Principal Engineer. His most recent venture is Fabula AI, a startup dedicated to algorithmic detection of fake news using geometric deep learning.
I am a Senior Research Scientist at the Max Planck Institute for Intelligent Systems in the department of Empirical Inference and project leader in the department of Physiology of Cognitive Processes at the Max Planck Institute for Biological Cybernetics. Neural networks are characterized by dense connectivity at multiple scales that makes challenging to assess their organization and function. We develop machine learning and statistical tools to study the functional organization of these systems at multiple scales. In parallel, the current intensive development of new artificial deep neural networks has lead to impressive successes, but the functioning of these architectures remains largely elusive due to their high dimensional connectivity. This provides us an opportunity to use our network analysis tools to uncover fundamental principles for such systems, and possibly relate them to biology. We are currently investigating causality and invariance principles to understand the structure of deep generative models and in particular assess their modularity.
Nicolò Cesa-Bianchi is professor of Computer Science at the University of Milan, Italy. His main research areas include the design and analysis of machine learning algorithms, particularly in the online learning model, the study of algorithms for multiarmed bandit problems with applications to personalized recommendations and online auctions, and graph analytics with applications to social networks and bioinformatics. He is co-author of the monographs "Prediction, Learning, and Games" and "Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems".
I am a Professor of Computer Science at the University of Oxford, a tutorial fellow at St. Catherine's College, and the Chief Scientist and co-founder of Latent Logic Ltd. My research focuses on artificial intelligence. My goal is to design, analyse, and evaluate the algorithms that enable computational systems to acquire and execute intelligent behaviour. I'm particularly interested in machine learning, with which computers can learn from experience, and decision-theoretic planning, with which they can reason about their goals and deduce behavioural strategies that maximise their utility. In addition to theoretical work on these topics, I have in recent years also focused on applying them to practical problems in robotics and search engine optimisation.
I am an assistant professor in the Geometry & Visualization group at TUM. I did my PhD with Max Wardetzky in the research group Discrete Differential Geometry at the University of Göttingen, and a postdoc in Herbert Edelsbrunner's research group at IST Austria.
I am an Associate Professor of Machine Learning at the University of Oxford Computer Science department, and head of the Oxford Applied and Theoretical Machine Learning Group (OATML). I am also the Tutorial Fellow in Computer Science at Christ Church, Oxford, and Fellow at the Alan Turing Institute, the UK's national institute for data science. Prior to my move to Oxford I was a Research Fellow in Computer Science at St Catharine's College at the University of Cambridge. I obtained my PhD from the Cambridge machine learning group, working with Prof Zoubin Ghahramani and funded by the Google Europe Doctoral Fellowship. Prior to that I studied at Oxford Computer Science department for a Master's degree under the supervision of Prof Phil Blunsom. Before my MSc I worked as a software engineer for 3 years at IDesia Biometrics developing code and UI for mobile platforms, and did my undergraduate in mathematics and computer science at the Open University in Israel.
Since September 2015, I am an associate professor («maître de conférences ») in statistics at the Toulouse Mathematics Institute and at the University Paul Sabatier.
I am also a member of the AOC project and defended my habilitation (HDR) at the University Paul Sabatier in 2018. My research interests are in the areas of Gaussian
process modeling, Covariance function estimation, Uncertainty quantification for computer experiments, Confidence intervals post-model-selection.
I am an assistant professor at UIUC and my area of focus is studying mathematical aspects of machine learning. At the moment I am interested in the approximation and representation power of deep networks. I proved there exist deep networks which can only be approximated by shallower networks if they have exponentially as many nodes. I am also interested in generalization of deep networks, where the empirically-observed excess risk correlates with the Lipschitz constant of networks, and yields a generalization bound.
the event
The Machine Learning Summer School is an event series started at the Max Planck Institute for Intelligent Systems in Tübingen, Germany, in 2002. Its organizers noticed that while many students are keen to learn about machine learning only few machine learning courses are taught at universities. By now, more than 30 editions have taken place in Europe, Asia and the Americas. For the first time, the Machine Learning Summer School is coming to Eastern Europe.
MLSS will take place at the heart of Moscow's Skolkovo Innovation Center – Skoltech Institute of Science and Technology. Skoltech was created during 2011 in collaboration with the Massachusetts Institute of Technology (MIT). Central to the campus are its multi-story laboratories that accommodate lab space, work and teaching areas, as well as the associated offices, which include 12 laboratory buildings within the insitute.
Moscow is the capital of Russia and one of the largest cities in Europe. A historic center with modern infrastructure easily reachable from all major cities of Russia by air or train travel. Located on the river Moskva, in the west of the country, Moscow's landmarks include the Red Square, the Bolshoi Theatre, the Gorky Park, VDNH and the Tretyakov gallery. Moscow is an excellent destination to visit regardless whether you are on business or holiday travel.
For application, you will need the items listed below.
The application deadline is the 31st of May 2019
Skolkovo Institute of Science & Technology
Center for Computational and Data-Intensive Science and Engineering


Do not hesitate to drop by:
143026, 3 Nobel str., Moscow, Russia
For directions on how to reach us, please see here