October 04, 2021
Regina Barzilay, MIT
Regina Barzilay is a School of Engineering Distinguished Professor for AI and Health in the Department of Electrical Engineering and Computer Science and a member of the Computer Science and Artificial Intelligence Laboratory at the Massachusetts Institute of Technology. She is an AI faculty lead for Jameel Clinic, an MIT center for Machine Learning in Health. Her research interests are in natural language processing and applications of deep learning to chemistry and oncology. She is a recipient of various awards including the NSF Career Award, the MIT Technology Review TR-35 Award, Microsoft Faculty Fellowship and several Best Paper Awards at NAACL and ACL. In 2017, she received a MacArthur fellowship, an ACL fellowship and an AAAI fellowship. In 2021, she was awarded the Squirrel AI Award for Artificial Intelligence for the Benefit of Humanity and the UNESCO/Netexplo Award. She received her PhD in Computer Science from Columbia University, and spent a year as a postdoc at Cornell University. Prof. Barzilay received her undergraduate degree from Ben-Gurion University of the Negev, Israel.
Until today, all the available therapeutics have been designed by human experts, with no help from AI tools. This reliance on human knowledge and dependence on large-scale experimentations result in prohibitive development cost and high failure rate. Recent developments in machine learning algorithms for molecular modeling aim to transform this field. In my talk, I will present state-of-the-art approaches for property prediction and de-novo molecular generation, describing their use in drug design. In addition, I will highlight unsolved algorithmic questions in this field, including confidence estimation, pretraining, and deficiencies in learned molecular representations.
October 20, 2021
Koushik Sen, UC Berkeley
Koushik Sen is a professor in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley. His research interest lies in Software Engineering, Programming Languages, and Formal methods. He is interested in developing software tools and methodologies that improve programmer productivity and software quality. He is best known for his work on “DART: Directed Automated Random Testing” and concolic testing. He has received an NSF CAREER Award in 2008, a Haifa Verification Conference (HVC) Award in 2009, an IFIP TC2 Manfred Paul Award for Excellence in Software: Theory and Practice in 2010, a Sloan Foundation Fellowship in 2011, a Professor R. Narasimhan Lecture Award in 2014, an Okawa Foundation Research Grant in 2015, and an ACM SIGSOFT Impact Paper Award in 2019. He has won several ACM SIGSOFT Distinguished Paper Awards. He received the C.L. and Jane W-S. Liu Award in 2004, the C. W. Gear Outstanding Graduate Award in 2005, and the David J. Kuck Outstanding Ph.D. Thesis Award in 2007, and a Distinguished Alumni Educator Award in 2014 from the UIUC Department of Computer Science. He holds a B.Tech from the Indian Institute of Technology, Kanpur, and an MS and PhD in CS from the University of Illinois at Urbana-Champaign.
In the last two decades, automation has had a significant impact on software testing and analysis. Automated testing techniques, such as symbolic execution, concolic testing, and feedback-directed fuzzing, have found numerous critical faults, security vulnerabilities, and performance bottlenecks in mature and well-tested software systems. The key strength of automated techniques is their ability to quickly search state spaces by performing repetitive and expensive computational tasks at a rate far beyond the human attention span and computation speed. In this talk, I will give a brief overview of our past and recent research contributions in automated test generation using symbolic execution, program analysis, constraint solving, fuzzing, and machine learning.
October 27, 2021
Oded Regev, Courant Institute, New York University
Oded Regev is a professor in the Courant Institute of Mathematical Sciences of New York University. Prior to joining NYU, he was affiliated with Tel Aviv University and the École Normale Supérieure, Paris under the French National Centre for Scientific Research (CNRS). He received his Ph.D. in computer science from Tel Aviv University in 2001 under the supervision of Yossi Azar. He is a recipient of the 2019 Simons Investigator Award, the 2018 Gödel Prize, several best paper awards, and is a speaker at the 2022 International Congress of Mathematicians. His main research areas include theoretical computer science, machine learning, cryptography, quantum computation, and complexity theory. One focus of his research is in the area of lattice-based cryptography, where he introduced the Learning with Errors (LWE) problem.
Recent advances in machine learning such as deep learning have led to powerful tools and techniques for modeling complex data with high predictive accuracy. However, the resulting models are typically black box, limiting their usefulness in advancing science. Here we will describe how machine learning can be used to model in an interpretable way a certain fundamental cellular process known as RNA splicing. The model provides insights into molecular mechanisms which we are currently validating in the lab.
Based on joint work with Susan E. Liao, Mukund Sudarshan, Mauricio A Arias, Jiacheng Zhang, Lawrence A Chasin, and Jingyi Fei.
November 08, 2021
Shivani Agarwal, University of Pennsylvania
Shivani Agarwal is Rachleff Family Associate Professor of Computer and Information Science at the University of Pennsylvania, where she also directs the NSF-sponsored Penn Institute for Foundations of Data Science (PIFODS) and co-directs the Penn Research in Machine Learning (PRiML) center. She has previously been a Radcliffe Fellow at Harvard and has taught as a Ramanujan Fellow at the Indian Institute of Science and as a postdoctoral lecturer at MIT. She serves as an Action Editor for the Journal of Machine Learning Research and an Associate Editor for the Harvard Data Science Review, and served as Program Co-chair for COLT 2020. Her research interests include computational, mathematical, and statistical foundations of machine learning and data science; applications of machine learning in the life sciences and beyond; and connections between machine learning and other disciplines such as economics, operations research, and psychology. Her group's research has been selected four times for spotlight presentations at the NeurIPS conference.
Surrogate loss functions are widely used in machine learning. In particular, for many machine learning problems, the ideal objective or loss function is computationally hard to optimize, and therefore one instead works with a (usually convex) surrogate loss that can be optimized efficiently. What are the fundamental design principles for such surrogate losses, and what are the associated statistical behaviors of the resulting algorithms?
This talk will provide answers to some of these questions. In particular, we will discuss the theory of convex calibrated surrogate losses, which yield statistically consistent learning algorithms for the true learning objective, and will provide fundamental principles and tools for designing such surrogate losses for a wide variety of machine learning problems. Our surrogate losses effectively decompose complex multiclass and multi-label learning problems into simpler binary learning problems, and come with corresponding decoding schemes that make the overall learning approach statistically consistent. We will also discuss the tool of strongly proper losses, which act as a fundamental primitive in deriving statistical guarantees for various learning problems, and connections with the field of property elicitation and with PAC learning. We will conclude with some open questions.
November 17, 2021
Seny Kamara, Brown University
Seny Kamara is an Associate Professor of Computer Science at Brown University. Before joining Brown, he was a researcher at Microsoft Research. His research is in cryptography and is driven by real-world problems from privacy, security and surveillance. He has worked extensively on the design and cryptanalysis of encrypted search algorithms, which are efficient algorithms to search on end-to-end encrypted data. He maintains interests in various aspects of theory and systems, including applied and theoretical cryptography, data structures and algorithms, databases, networking, game theory and technology policy. At Brown, he co-directs the Encrypted Systems Lab and the Computing for the People project and is affiliated with the Center for Human Rights and Humanitarian Studies, the Policy Lab and the Data Science Initiative.
Algorithms have transformed every aspect of society, including communication, transportation, commerce, finance, and health. The revolution enabled by computing has been extraordinarily valuable. The largest tech companies generate a trillion dollars a year and employ 1 million people. But technology does not affect everyone in the same way. In this talk, we will examine how new technologies affect marginalized communities and think about what technology, academic research and teaching would look like if its goal was to serve the disenfranchised.
- Distinguished Lectures 2022-2023
- Distinguished Lectures 2021-2022
- Distinguished Lectures 2020-2021
- Distinguished Lectures 2019-2020
- Distinguished Lectures 2018-2019
- Distinguished Lectures 2017-2018
- Distinguished Lectures 2016-2017
- Distinguished Lectures 2015-2016
- Distinguished Lectures 2014-2015
- Distinguished Lectures 2013-2014
- Distinguished Lectures 2012-2013
- Distinguished Lectures 2011-2012