Ulrike von Luxburg is the research group leader for learning theory at the Empirical Inference Department of the Max Planck Institute for Biological Cybernetics, Tubingen; since 2010 hosted at the University of Hamburg. She was previously the head of the Data Mining Group at Fraunhofer IPSI, Darmstadt, Germany.

Statistical Analysis of Learning Algorithms on Graphs
In many machine learning applications, data comes with a natural graph structure: social networks, the internet, biological networks, similarity based data, etc. In most cases, these graphs are the result of some kind of random process. In order to evaluate the results of machine learning algorithms on graphs, it is therefore important to find out whether the learning results on a particular graph reflect ``true structure'' or merely model statistical artefacts of the graph. In my talk I am going to show how the statistical analysis of learning algorithms on graphs can shed light on this question.

Cordelia Schmid holds a M.S. degree in Computer Science from the University of Karlsruhe and a Doctorate, also in Computer Science, from the Institut National Polytechnique de Grenoble (INPG). Her doctoral thesis on "Local Greyvalue Invariants for Image Matching and Retrieval" received the best thesis award from INPG in 1996. She received the Habilitation degree in 2001 for her thesis entitled "From Image Matching to Learning Visual Models". Dr. Schmid was a post-doctoral research assistant in the Robotics Research Group of Oxford University in 1996--1997. Since 1997 she has held a permanent research position at INRIA Rhone-Alpes, where she is a research director and directs the INRIA team called LEAR for LEArning and Recognition in Vision. Dr. Schmid is the author of over eighty technical publications. She has been an Associate Editor for the IEEE Transactions on Pattern Analysis and Machine Intelligence (2001--2005) and for the International Journal of Computer Vision (2004---), and she was program chair of the 2005 IEEE Conference on Computer Vision and Pattern Recognition. In 2006, she was awarded the Longuet-Higgins prize for fundamental contributions in computer vision that have withstood the test of time. She is a senior member of IEEE.

TBA

Alice Zheng is a researcher in the Machine Learning Group at Microsoft Research Redmond. Before joining Microsoft, she was a postdoc at Carnegie Mellon University's Auton Lab with Dr. Andrew Moore, and the Parallel data Lab with Dr. Greg Ganger. She received her B.A. and Ph.D degrees from U.C. Berkeley under Michael Jordan. Her research interests lie in the design of machine learning systems for large-scale data analysis. She is also interested in applications of machine learning to problems in systems, security, and software engineering.

TBA

Claire Monteleoni is an assistant professor of Computer Science at George Washington University, and adjunct research faculty at the Center for Computational Learning Systems at Columbia University, where she was previously research faculty. She did a postdoc in Computer Science and Engineering at the University of California, San Diego, and completed her PhD and Masters in Computer Science, at MIT. Her research focus is on machine learning algorithms and theory for problems including learning from data streams, learning from raw (unlabeled) data, learning from private data, and Climate Informatics: accelerating discovery in Climate Science with machine learning. Her papers have received several awards, and she currently serves on the Senior Program Committee of the International Conference on Machine Learning, and the Editorial Board of the Machine Learning Journal.

Clustering algorithms for streaming and online settings
Clustering techniques are widely used to summarize large quantities of data (e.g. aggregating similar news stories), however their outputs can be hard to evaluate. While a domain expert could judge the quality of a clustering, having a human in the loop is often impractical. Probabilistic assumptions have been used to analyze clustering algorithms, for example i.i.d. data, or even data generated by a well-separated mixture of Gaussians. Without any distributional assumptions, one can analyze clustering algorithms by formulating some objective function, and proving that a clustering algorithm either optimizes or approximates it. The k-means clustering objective, for Euclidean data, is simple, intuitive, and widely-cited, however it is NP-hard to optimize, and few algorithms approximate it, even in the batch setting (the algorithm known as "k-means" does not have an approximation guarantee). Dasgupta (2008) posed open problems for approximating it on data streams. In this talk, I will discuss my ongoing work on designing clustering algorithms to approximate the k-means objective in streaming and online settings. This talk is based on joint works with Nir Ailon, Ragesh Jaiswal, and Anna Choromanska.