GOOGLE Research India (For Faulty and Ph.D. Students)

  • Remote Access - Google Meet
  • Virtual Presentations - ET
  • with PRATEEK JAIN, PARTHA TALUKAR, MILIND TAMBE
  • Google Research India
Career Presentation

NOTE: CMU ⇔ Google Research India  →  1:1 and Group discussions with researchers are possible after the talks.  Please SIGN-UP to schedule a time.

Guest Speakers

►  Prateek Jain, Senior Staff Research Scientist and Lead, Machine Learning Foundations and Optimization, Google AI
      —  Online Learning with Markovian Data via Reverse Experience Replay

Learning with Markovian data is a challenging problem with several applications in critical domains like reinforcement learning, control theory, time series analysis etc.  Techniques like SGD are the workhorse of large-scale learning, with rigorous analysis for streaming i.i.d. data in several regimes. But their applicability to non i.i.d. Markovian data is unclear due to dependency between points.

In this talk, we will present results showing that SGD in general can be significantly sub-optimal for Markovian data. In contrast, through three critical problems: a) linear regression, b) dynamical system identification aka vector auto-regressive model estimation, c) policy learning with Linear MDPs, we demonstrate that SGD enhanced with "experience replay"--a popular heuristic used in RL literature--leads to nearly optimal solutions. To the best of our knowledge, we provide the first rigorous analysis of the practically popular experience replay technique. Similarly, our result provides the first provably efficient Q-learning style method for finding optimal policy for linear MDPs.

Based on joint works with Naman Agarwal, Syomantak Chaudhuri, Suhas Kowshik, Dheeraj Nagaraj, Praneeth Netrapalli, Carrie Wu.

   —   Prateek Jain leads the Machine Learning Foundations and Optimization team at Google AI, Bangalore, India. His research interests are in machine learning, non-convex optimization, high-dimensional statistics, and optimization algorithms in general. He is also interested in applications of machine learning to privacy, computer vision, text mining and natural language processing. Earlier, Prateek was a Sr. Principal Research Scientist at Microsoft Research India and completed his PhD at the University of Texas at Austin under Prof. Inderjit S. Dhillon.

►  Partha Talukdar, Staff Research Scientist, Google Research India, and Associate Professor, Department of CDS and CSA, Indian Institute of Science, Bangalore (LOA)
      —  Scaling Natural Language Processing for the Next Billion Users

     Even though there are more than 7000 languages in the world, language technologies are available only for a handful of these languages. Lack of training data poses a significant challenge in developing language technologies for these languages. Recent advances in Multilingual Representation Learning presents an opportunity to transfer knowledge and supervision from high web-resource languages to languages with lower web-resources. In this talk, I shall present an overview of research in this exciting and emerging area in the NLU group at Google Research India. I shall also present an overview of other research activities at Google Research India.

   —   Partha Talukdar is a Staff Research Scientist at Google Research, Bangalore where he leads a group focused on Natural Language Understanding. He is also an Associate Professor (on leave) at IISc Bangalore. Partha founded KENOME, an enterprise Knowledge graph company with the mission to help enterprises make sense of unstructured data. Previously, Partha was a Postdoctoral Fellow in the Machine Learning Department at Carnegie Mellon University, working with Tom Mitchell on the NELL project. He received his PhD (2010) in CIS from the University of Pennsylvania. Partha is broadly interested in Natural Language Processing, Machine Learning, and Knowledge Graphs. Partha is a recipient of several awards, including an Outstanding Paper Award at ACL 2019. He is a co-author of a book on Graph-based Semi-Supervised Learning.

►  Milind Tambe, Director, AI for Social Good, Google Research India, and Gordon McKay Professor of Computer Science and Director, Center for Research in Computation and Society,  Harvard University
     AI for social impact: Results from deployments in public health and conservation

With the maturing of AI and multiagent systems research, we have a tremendous opportunity to direct these advances towards addressing complex societal problems. I  focus on our efforts in "AI for social impact" in our group at Google Research India, specifically focusing on public health and conservation. I will present results from work on Maternal and Child care interventions, as well as for preventing human-wildlife conflicts. Achieving social impact in these domains often requires methodological advances. To that end, I will highlight key research challenges in multiagent reasoning and learning, in particular in topics such as restless bandits.

In pushing this research agenda, our ultimate goal is to facilitate local communities and non-profits to directly benefit from advances in AI tools and techniques.

   —   Milind Tambe is  Director "AI for Social Good" at Google Research India; simultaneously, he is also Gordon McKay Professor of Computer Science and Director of Center for Research in Computation and Society at Harvard University. He is a recipient of the IJCAI John McCarthy Award, ACM/SIGAI Autonomous Agents Research Award from AAMAS, AAAI Robert S Engelmore Memorial Lecture award,  INFORMS Wagner prize, Rist Prize of the Military Operations Research Society, Columbus Fellowship Foundation Homeland security award, over 25 best papers or honorable mentions at conferences such as AAMAS, AAAI, IJCAI and meritorious commendations from agencies such as the US Coast Guard and the Los Angeles Airport.  Prof. Tambe is a fellow of AAAI and ACM. He received his PhD from School of Computer Science at Carnegie Mellon University.

See announcement for video coordinates.