Speakers

Speaker information will continue to be updated as we get closer to the workshop.

*Invited Speakers*

 
Sanjoy Dasgupta, UC San Diego
Talk title: Some directions in explainable unsupervised learning
Bio: Sanjoy Dasgupta is a professor in the Computer Science department at UC San Diego. He got his PhD at Berkeley in 2000 and then spent two years at AT&T Labs before joining UCSD. He works primarily on unsupervised and minimally-supervised learning. He has a textbook, "Algorithms", with Christos Papadimitriou and Umesh Vazirani.
Badih Ghazi, Google
Talk title: Differentially Private Clustering: Tight Approximation Ratios
Bio: Badih Ghazi has been a research scientist at Google since 2018. Before joining Google, he did his PhD at MIT where he was supervised by Madhu Sudan and Ronitt Rubinfeld. His research interests are around privacy, algorithms, and machine learning.
Vincent Cohen-Addad, Google
Talk title: A New Framework For K-means Coresets
Bio: Vincent Cohen-Addad is a research scientist at Google working on clustering problems and more broadly on unsupervised learning. Vincent has joined Google in 2020 after holding a researcher position at CNRS (France) and a Marie-Curie postdoc at the University of Copenhagen. His doctoral work has been awarded the EATCS distinguished dissertation award.
Jakub "Kuba" Lacki, Google
Talk title: Parallel Graph Algorithms in Constant Adaptive Rounds: Theory meets Practice
Bio: Jakub Łącki is a research scientist working on the Graph Mining team. His research interests include scalable graph algorithms and clustering. He received his PhD from Univeristy of Warsaw in 2015, advised by Piotr Sankowski. Before joining Google he was a postdoctoral researcher at Sapienza University of Rome, working with Stefano Leonardi.
David Woodruff, CMU
Talk title: Optimal Stochastic Trace Estimation
Bio: David Woodruff joined the algorithms and complexity group at IBM Almaden in 2007, after completing his PhD at MIT in Theoretical Computer Science. He is currently an Associate Professor of Computer Science at Carnegie Mellon University. His interests are in compressed sensing, communication, numerical linear algebra, sketching, and streaming. He is the recipient of the Presburger Award and Simons Investigator Award, as well as best paper awards at STOC, 2013, as well as PODS 2010 and PODS 2020. Earlier at IBM he was in the Academy of Technology, was a Master Inventor, and received the Pat Goldberg Best Paper Award in 2010, 2012, and 2013.
Umar Syed, Google
Talk title: Label differential privacy via clustering
Bio: Umar Syed has been a research scientist at Google since 2011. His current interests include privacy-preserving machine learning.
Maria-Florina Balcan, Carnegie Mellon University
Talk title: Data driven algorithm design
Bio: Maria Florina Balcan is the Cadence Design Systems Professor of Computer Science in the School of Computer Science at Carnegie Mellon University. Her main research interests are machine learning, artificial intelligence, theory of computing, and algorithmic game theory. She is a Sloan Fellow, a Simons Investigator, a Microsoft Research New Faculty Fellow, a Kavli Fellow, and a recipient of an NSF CAREER award, the ACM Grace Murray Hopper Award, and several best paper awards. She served as a general chair for the International Conference on Machine Learning 2021, and as a program committee co-chair of the Conference on Learning Theory in 2014 the International Conference on Machine Learning in 2016, and the Neural Information Processing Systems 2020 conference.
Andreas Krause, ETH Zürich
Talk title:Data Summarization via Bilevel Coresets
Bio:Andreas Krause is a Professor of Computer Science at ETH Zurich, where he leads the Learning & Adaptive Systems Group. He also serves as Academic Co-Director of the Swiss Data Science Center and Chair of the ETH AI Center, and co-founded the ETH spin-off LatticeFlow. Before that he was an Assistant Professor of Computer Science at Caltech. He received his Ph.D. in Computer Science from Carnegie Mellon University (2008) and his Diplom in Computer Science and Mathematics from the Technical University of Munich, Germany (2004). He is an ELLIS Fellow, a Microsoft Research Faculty Fellow and a Kavli Frontiers Fellow of the US National Academy of Sciences. He received the Rössler Prize, ERC Starting Investigator and ERC Consolidator grants, the German Pattern Recognition Award, an NSF CAREER award as well as the ETH Golden Owl teaching award. His research has received awards at several premier conferences and journals, including Test of Time Awards at KDD 2019 and ICML 2020. Andreas Krause served as Program Co-Chair for ICML 2018 and as Action Editor for the Journal of Machine Learning Research.
Amin Karbasi, Yale / Google
Talk title: Batch Active Learning
Bio: Amin Karbasi is currently an associate professor of Electrical Engineering, Computer Science, and Statistics at Yale University. He is also a research scientist at Google NY. He has been the recipient of the National Science Foundation (NSF) Career Award 2019, Office of Naval Research (ONR) Young Investigator Award 2019, Air Force Office of Scientific Research (AFOSR) Young Investigator Award 2018, DARPA Young Faculty Award 2016, National Academy of Engineering Grainger Award 2017, Amazon Research Award 2018, Google Faculty Research Award 2016, Microsoft Azure Research Award 2016, Simons Research Fellowship 2017, and ETH Research Fellowship 2013. His work has also been recognized with a number of paper awards, including Medical Image Computing and Computer Assisted Interventions Conference (MICCAI) 2017, International Conference on Artificial Intelligence and Statistics (AISTAT) 2015, IEEE ComSoc Data Storage 2013, International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2011, ACM SIGMETRICS 2010, and IEEE International Symposium on Information Theory (ISIT) 2010 (runner-up). His Ph.D. thesis received the Patrick Denantes Memorial Prize 2013 from the School of Computer and Communication Sciences at EPFL, Switzerland.
Piotr Indyk, MIT
Talk title: Learning-Based Sampling for Distinct Elements Counting
Bio: Piotr Indyk is a Thomas D. and Virginia W. Cabot Professor in the Department of Electrical Engineering and Computer Science at MIT. He joined MIT in 2000, after earning PhD from Stanford University. Earlier, he received Magister degree from Uniwersytet Warszawski in 1995. Piotr’s research interests lie in the design and analysis of efficient algorithms, including high-dimensional computational geometry, sketching, streaming and sampling algorithms, sparse recovery, fine-grained complexity and learning-based algorithms. He has received Sloan Fellowship (2003), Packard Fellowship (2003), Simons Investigator Award (2013) and ICML Best Paper Award (2015). His work on sparse Fourier sampling has been named to Technology Review TR10 in 2012, while his work on locality-sensitive hashing has received the 2012 ACM Kanellakis Theory and Practice Award. He is a co-director of Foundations of Data Science Institute (fodsi.us), an NSF-funded project focused on foundations of data science.
MohammadHosein Bateni, Google
Talk title: Submodular Optimization for Machine Learning
Bio: MohammadHossein Bateni is a staff research scientist at Google, where he is a member of the NYC Algorithms and Optimization Team. He obtained his Ph.D. and M.A. in Computer Science from Princeton University in 2011 and 2008, respectively, after finishing his undergraduate studies with a B.Sc. in Computer Engineering at Sharif University of Technology in 2006. Hossein is broadly interested in combinatorics and combinatorial optimization. His research focuses on approximation algorithms, distributed computing, and analysis of game-theoretic models.
Nicholas Carlini
Talk title: Data Poisoning in {Semi,Self}-Supervised Learning
Bio: Nicholas Carlini is a research scientist in Brain. He attacks machine learning systems
Ronitt Rubinfield
Talk title: Locality in computation
Bio: Ronitt Rubinfeld is the Edwin Sibley Webster Professor in MIT's Electrical Engineering and Computer Science department, where she has been on the faculty since 2004. She has previously held faculty positions at Cornell University and Tel Aviv University, and has been a member of the research staff at NEC Research Institute. Ronitt's research centers on property testing and sub-linear time algorithms, that provide the foundations for measuring the performance of algorithms that analyze data by looking at only a very small portion of it. Her work has developed the field of sublinear time property testers and approximation algorithms for functions, combinatorial objects and distributions. Ronitt received her PhD from the University of California, Berkeley. Ronitt Rubinfeld was an ONR Young Investigator, a Sloan Fellow, and an invited speaker at the Internal Congress of Mathematics in 2006. She is a fellow of the ACM and of the American Academy of Arts and Sciences.
Christian Schulz, Heidelberg University
Talk title: Recent Advances in Scalable Graph Decomposition
Bio: Christian Schulz received his Ph.D. in computer science from Karlsruhe Institute of Technology, Germany in 2013. Afterwards he was leading the graph partitioning & parallel processing subgroup in the group of Peter Sanders and later on leading the algorithm engineering subgroup of the group of Monika Henzinger in Vienna. Christian Schulz obtained a habilitation in computer science in 2019 and returned to Germany as a full professor at Heidelberg University in 2020. He has more than 80 publications, mostly on algorithms in the context of scalable graph algorithms. This includes multilevel algorithms [(hyper)graph partitioning, clustering, etc.], parallel algorithms [sorting, graph generation, etc.], streaming algorithms, support vector machines, data reductions algorithms as well as dynamic graph algorithms. He received various awards for his research, e.g. the Heinz Billing Prize, the KIT doctoral award, as well as a best paper award at IPDPS and at IEEE CLUSTER. His codes won several competitions such as the DIMACS Implementation Challenge on Graph Partitioning and Clustering and the PACE Implementation Challenge on Vertex Cover.
Richard Peng, Georgia Institue of Technology
Talk title: Fully Dynamic Effective Resistance
Bio: Richard Peng is an assistant professor in the School of Computer Science at the Georgia Institute of Technology. His research interests are in the design, analysis, and implementation of efficient algorithms. These interests currently revolve around problems induced by practice that arise at the intersection of discrete, numerical, and randomized algorithms, and his representative results include linear systems solvers, max-flow/min-cut algorithms, and time/space efficient data structures for matchings, resistances, and matrices. Richard received his BMath from Waterloo, PhD from CMU, and was a postdoc at MIT. Awards he received include the NSF Career Award, the 2011 Microsoft Research PhD Fellowship, the 2013 CMU SCS Distinguished Dissertation Award, and the 2021 SODA Best Paper Award.
Piotr Sankowski, IDEAS NCBR / University of Warsaw
Talk title: Walking Randomly, Massively, and Efficiently
Bio: Piotr Sankowski is acting as a CEO of IDEAS NCBR, a new research center created in Warsaw Poland. He is a professor in the Institute of Informatics, University of Warsaw, where he received his habilitation in 2009 and where he received a doctorate in computer science in 2005. His research interest is in algorithmics with the focus on algorithmic analysis of network and data science algorithms. Piotr Sankowski received also a doctorate in physics in solid state theory at the Polish Academy of Sciences in 2009. He is the first Pole to have received three ERC grants: Starting Grant (2010), Proof of Concept Grant (2015), and Consolidator Grant (2017). In 2018 he received the individual Crystal Brussels Sprout Award and the National Science Center award. Since 2016 he has been a member of the Council of the National Center for Research and Development. He is also a co-founder of the spin-off company MIM Solutions.
Laxman Dhulipala, Google
TalkTitle: ParHAC: Single-Machine Parallel Hierarchical Clustering of Billion-Edge Graphs
Bio: Laxman is currently a visiting researcher at Google Research NYC where I work on parallel clustering algorithms as part of the Graph Mining team (I will be joining the Computer Science Dept. at University of Maryland as an assistant professor in Fall'22). Prior to Google, I was a postdoc at MIT, working with Julian Shun. I received my PhD from Carnegie Mellon University where I was advised by Guy Blelloch. My main research interests are scalable parallel, dynamic, and streaming graph algorithms (both theory and practice).
Peilin Zhong, Google
Talk title: Massively Parallel and Dynamic Algorithms for Minimum Size Clustering
Bio: Peilin Zhong is a research scientist at Google NYC in the Algorithms and Optimization team. He received a PhD in computer science from Columbia University, advised by Alex Andoni, Cliff Stein and Mihalis Yannakakis. During his PhD study, he received the Google PhD Fellowship in 2019.
 
He has broad interests in design and analysis of algorithms. Some particular interests include parallel and massively parallel algorithms, sketching, streaming algorithms, graph algorithms, machine learning, high dimensional geometry, metric embedding, numerical linear algebra, clustering and other algorithms related to large-scale data computation.
Julian Shun, MIT
Talk title: Parallel Index-Based Structural Graph Clustering and Its Approximation
Bio: Julian Shun is an Associate Professor in EECS and CSAIL at MIT. Prior to coming to MIT, he was a Miller Research Fellow at UC Berkeley. He received his Ph.D. from Carnegie Mellon University and his B.A. from UC Berkeley. His research focuses on the theory and practice of parallel algorithms and programming frameworks. He has received the NSF CAREER Award, DOE Early Career Award, ACM Doctoral Dissertation Award, CMU School of Computer Science Doctoral Dissertation Award, Facebook Graduate Fellowship, Google Faculty Research Award, Google Research Scholar Award, SoE Ruth and Joel Spira Award for Excellence in Teaching, and best paper awards at PLDI, SPAA, CGO, and DCC.
David Gleich, Purdue University
Talk title: Recent insights from flow and diffusion-based semi-supervised learning problems
Bio: David Gleich is the Jyoti and Aditya Mathur Associate Professor in the Computer Science Department at Purdue University whose research is on novel models and fast large-scale algorithms for data-driven scientific computing including scientific data analysis, bioinformatics, and network analysis. He is committed to making software available based on this research and has written software packages such as MatlabBGL with thousands of users worldwide. Gleich has received a number of awards for his research including a SIAM Outstanding Publication prize (2018), a Sloan Research Fellowship (2016), an NSF CAREER Award (2011), the John von Neumann post-doctoral fellowship at Sandia National Laboratories in Livermore CA (2009). His research is funded by the NSF, DOE, DARPA, and NASA. For more information, see his website: https://www.cs.purdue.edu/homes/dgleich/
Silvio Lattanzi, Google
Talk title: Semi-supervised Clustering
Bio: Silvio is a Research Scientist at Google since April 2011. He is part of the Algorithm & Optimization group. He received his PhD from Sapienza University of Rome under the supervision of Alessandro Panconesi. His research interests are in the areas of algorithms, machine learning and information retrieval.
Ali Sinop, Google
Talk title: Robust Routing Using Electrical Flows
Bio: Ali Kemal Sinop is a research scientist at Google Research. He received his PhD from Carnegie Mellon University. His research interests include computational mobility, algorithms and spectral graph theory.
Aneesh Sharma, Google
Talk title: Graph Embeddings and Graph Structure
Bio: Aneesh is a software engineer/research scientist at Google, working on YouTube Ads brand safety and contextual advertising. Before coming to Google in 2017, he worked at Twitter, where his work powered relevance for a variety of products such as Who to Follow, Home Timeline suggestions/ranking, and email/push recommendations. His research focuses on algorithmic/ML problems arising in social systems.
Jean Pouget-Abadi, Google
Talk title: Graphs and Causal Inference
Bio: Jean Pouget-Abadie is a research scientist at Google Research New York on the Algorithms & Optimization team, led by Vahab Mirrokni. Before joining Google, he was a PhD student in Computer Science at Harvard University, advised by Edoardo Airoldi and Salil Vadhan. Prior to that, he completed an undergraduate at Ecole Polytechnique, Paris. His recent research interests focus on causal inference and experimental design, particularly when network interference is present. For more info, visit his webpage: https://jean.pouget-abadie.com/
Stefanie Jegelka, MIT
Talk title: Extrapolation in Graph Neural Networks
Bio: Stefanie Jegelka is an Associate Professor in the Department of EECS at MIT. She is a member of the Computer Science and AI Lab (CSAIL), the Center for Statistics and an affiliate of IDSS and ORC. Before joining MIT, she was a postdoctoral researcher at UC Berkeley and obtained her PhD from ETH Zurich and the Max Planck Institute for Intelligent Systems. Stefanie has received a Sloan Research Fellowship, an NSF CAREER Award, a DARPA Young Faculty Award, Google research (scholar) awards, a Two Sigma faculty research award, the German Pattern Recognition Award and a Best Paper Award at the International Conference for Machine Learning (ICML). Her research interests span the theory and practice of algorithmic machine learning, with a focus on learning with discrete structures.
Leman Akoglu, Heinz College
Talk title: Distributed Outlier Detection at Scale
Bio: Leman Akoglu is the Heinz College Dean's Associate Professor of Information Systems. She holds courtesy appointments in the Computer Science Department (CSD) and the Machine Learning Department (MLD) of School of Computer Science (SCS). She has also received her Ph.D. from CSD/SCS of Carnegie Mellon University in 2012.

Dr. Akoglu’s research interests broadly span machine learning and data mining, and specifically graph mining, pattern discovery and anomaly detection, with applications to fraud and event detection in diverse real-world domains. At Heinz, Dr. Akoglu directs the Data Analytics Techniques Algorithms (DATA) Lab.

Dr. Akoglu is a recipient of the SDM/IBM Early Career Data Mining Research award (2020), National Science Foundation CAREER award (2015) and US Army Research Office Young Investigator award (2013). Her research has won 8 publication awards; The Most Influential Paper (PAKDD 2020), Best Research Paper (SIAM SDM 2019), Best Student Machine Learning Paper Runner-up (ECML PKDD 2018), Best Paper Runner-up (SIAM SDM 2016), Best Research Paper (SIAM SDM 2015), Best Paper (ADC 2014), Best Paper (PAKDD 2010), and Best Knowledge Discovery Paper (ECML PKDD 2009). She also holds 3 U.S. patents filed by IBM T. J. Watson Research Labs. Her research has been supported by the NSF, US ARO, DARPA, Adobe, Facebook, Northrop Grumman, PNC Bank, and PwC.
Danai Koutra, Michigan Institute for Data Science / University of Michigan
Talk title: The Power of Summarization in Graph Mining and Learning: Smaller Data, Faster Methods, More Interpretability
Bio: Danai Koutra is an Associate Director of the Michigan Institute for Data Science (MIDAS) and a Morris Wellman Assistant Professor in Computer Science and Engineering at the University of Michigan, where she leads the Graph Exploration and Mining at Scale (GEMS) Lab. Her research focuses on practical and scalable methods for large-scale real networks, and her interests include graph summarization, knowledge graph mining, graph learning, similarity and alignment, and anomaly detection. She has won an NSF CAREER award, an ARO Young Investigator award, the 2020 SIGKDD Rising Star Award, research faculty awards from Google, Amazon, Facebook and Adobe, a Precision Health Investigator award, the 2016 ACM SIGKDD Dissertation award, and an honorable mention for the SCS Doctoral Dissertation Award (CMU). She holds one "rate-1" patent on bipartite graph alignment, and has multiple papers in top data mining conferences, including 8 award-winning papers. She is the Secretary of the new SIAG on Data Science, an Associate Editor of ACM TKDD, and has served multiple times in the organizing committees of all the major data mining conferences. She has worked at IBM, Microsoft Research, and Technicolor. She earned her Ph.D. and M.S. in Computer Science from CMU in 2015 and her diploma in Electrical and Computer Engineering at the National Technical University of Athens in 2010.
Andreas Loukas, Swiss Federal Institute of Technology Lausanne
Talk title: Erdős goes neural: solving combinatorial optimization problems with neural networks and no supervision
Bio: I am a computer scientist focusing on the foundations and applications of graph methods in machine learning and data science. In my work, I aim to find elegant explanations for phenomena associated with learning and to exploit them in order to design specialized learning machines. I am also interested in graph problems in signal processing and theoretical computer science, as well as in the theoretical analysis of neural networks. You can read more about my work on andreasloukas.blog or by following me at twitter.com/loukasa_tweet
Rina Panigrahy, Google
Talk title: Sketch based Nerual Memory for Deep Networks
Bio: Rina Panigrahy is a research scientist at Google specializing in applied and theoretical algorithms in areas such as deep learning, high dimensional search, hashing, sketching, streaming, prediction and graph analysis with engineering and research impact covering over 75 publications and 50 patents. His Masters thesis work at MIT was used in founding Akamai Technologies. He has held research and engineering positions at Microsoft(principal researcher) and Cisco Systems. He obtained his Ph.D. in Algorithms from Stanford, and did his undergrad from IIT Mumbai after securing the top rank at the IIT-JEE entrance examination all over India. He is a recipient of a Gold medal at the International Math Olympiad and a winner of several best paper awards.
Marinka Zitnik, Harvard
Talk title: Few-Shot Learning for Network Biomedicine
Bio: Marinka Zitnik is an Assistant Professor at Harvard University with appointments in the Department of Biomedical Informatics, Broad Institute of MIT and Harvard, and Harvard Data Science, where she leads the Machine learning for Medicine and Science Lab. Her research focuses on methods for learning representations of complex interconnected data that produce actionable hypotheses and trustworthy predictions. Areas of impact include the design of therapeutics, precision medicine, and AI for science. She published extensively in top ML venues and leading interdisciplinary journals (e.g., Nature Methods, Nature Communications, PNAS). Her algorithms have had a tangible impact and are used by major institutions, including Baylor College of Medicine, Karolinska Institute, Stanford Medical School, Massachusetts General Hospital, and the pharmaceutical industry. This research won best paper and research awards from the International Society for Computational Biology, Bayer Early Excellence in Science Award, Amazon Faculty Research Award, Rising Star Award in EECS, and Next Generation Recognition in Biomedicine, being the only young scientist who received such recognition in both EECS and Biomedicine.
Zoubin Ghahramani
Talk title: TBD
Bio: TBD
Bryan Perozzi, Google
Talk title: Graph Neural Networks at Google
Bio: Bryan Perozzi is a researcher in Google Research’s Algorithms and Optimization group, where he routinely analyzes some of the world’s largest (and perhaps most interesting) graphs. Bryan’s research focuses on developing techniques for learning expressive representations of relational data with neural networks. These scalable algorithms are useful for prediction tasks (classification/regression), pattern discovery, and anomaly detection in large networked data sets. Bryan is an author of 30+ peer-reviewed papers at leading conferences in machine learning and data mining (such as NeurIPS, ICML, KDD, and WWW). His doctoral work on learning network representations was awarded the prestigious SIGKDD Dissertation Award. Bryan received his Ph.D. in Computer Science from Stony Brook University in 2016, and his M.S. from the Johns Hopkins University in 2011.
Prateek Jain, Google
Talk title: TBD
Bio: TBD
Dilip Krishnan, Google
Talk title: Contrastive Representation Learning
Bio: Dilip Krishnan is a Staff Research Scientist at Google’s Cambridge office (Massachusetts). I work at the intersection of machine perception and machine learning. From August 2013 to November 2014, I was a Postdoctoral Associate with Bill Freeman at MIT’s CSAIL Lab. In June 2013, I received my PhD from the Computer Science department at New York University , under the supervision of Rob Fergus. I was awarded a Microsoft Research PhD Fellowship for 2010-2011, a Dean’s Dissertation Fellowship for 2012-2013 from the Graduate School of Arts and Sciences and the Janet Fabri prize (2013-2014) for outstanding dissertation in Computer Science.
Srinadh Bhojanapalli‎, Google
Talk title: Efficient transformers with less redundancy in attention computation
Bio: Srinadh Bhojanapalli is a senior research scientist in Google research NY. Srinadh has worked on developing rigorous foundations for understanding and improving Transformer models. He is also interested in non convex optimization and distillation. Earlier he was a research assistant professor at TTIC. He did his PhD at the University of Texas Austin.