Our next event for the Statistics Department Colloquium Series is scheduled for this Monday, March 7th from 12:00 – 1:00pm (ET).
The speakers are Xiao-Li Meng: the Whipple V. N. Jones Professor of Statistics at Harvard University, and the Founding Editor-in-Chief of Harvard Data Science Review and Sham Kakade: a Gordon McKay Professor of Computer Science & Statistics at Harvard University.
Zoom information is posted below.
From Covid Vaccination Surveys to Presidential Election Predictions: How Small are Our Big Data?
Bio: Xiao-Li Meng is the Whipple V. N. Jones Professor of Statistics, and the Founding Editor-in-Chief of Harvard Data Science Review. His interests range from the theoretical foundations of statistical inferences (e.g., the interplay among Bayesian, Fiducial, and frequentist perspectives; frameworks for multi-source, multi-phase and multi- resolution inferences) to statistical methods and computation (e.g., posterior predictive p-value; EM algorithm; Markov chain Monte Carlo; bridge and path sampling) to applications in natural, social, and medical sciences and engineering (e.g., complex statistical modeling in astronomy and astrophysics, assessing disparity in mental health services, and quantifying statistical information in genetic studies). Meng was named the best statistician under the age of 40 by COPSS (Committee of Presidents of Statistical Societies) in 2001.
What Constitutes a Good Representation for Offline and Online Reinforcement Learning?
Abstract: A fundamental question in the theory of reinforcement learning is what representational conditions govern our ability to generalize and avoid the curse of dimensionality. With regards to supervised learning, these questions are well understood theoretically, and, practically speaking, we have overwhelming evidence on the value of representational learning (say through modern deep networks) as a means for sample efficient learning. Providing an analogous theory for reinforcement learning is far more challenging, where even characterizing the representational conditions which support sample efficient generalization is far less well understood.
This talk will highlight recent advances towards characterizing when generalization is possible in both offline and online reinforcement learning, focusing on both necessary and sufficient conditions. With regards to lower bounds with linear representations, we will provide a novel and sharper characterization of the stability of "backup methods" in offline RL, making connections to Lyapunov stability. With regards to online RL, we will provide a broader set of sufficient conditions and discuss progress in obtaining minimax optimal rates.
Bio: Sham Kakade is a Gordon McKay Professor of Computer Science & Statistics at Harvard University. He works on the mathematical foundations of machine learning and AI. Sham's thesis helped in laying the statistical foundations of reinforcement learning. With his collaborators, his additional contributions include: one of the first provably efficient policy search methods, Conservative Policy Iteration, for reinforcement learning; developing the mathematical foundations for the widely used linear bandit models and the Gaussian process bandit models; the tensor and spectral methodologies for provable estimation of latent variable models; the first sharp analysis of the perturbed gradient descent algorithm, along with the design and analysis of numerous other convex and non-convex algorithms. He is the recipient of the ICML Test of Time Award (2020), the IBM Pat Goldberg best paper award (in 2007), INFORMS Revenue Management and Pricing Prize (2014).
Please note: The Spring 2022 Colloquium (Stat 314) series will be held interchangeably virtually on Zoom or in person. Zoom events will be recorded, and retained for a short period, solely for students enrolled in Stat 314 and Harvard Statistics Department members. If you do not wish to have your video recorded, you are welcome to turn off your video feed during the talk.
The Statistics Department is inviting you to a scheduled Zoom meeting.
Time: Mar 7, 2022 11:45 AM Eastern Time (US and Canada)
Join Zoom meeting
Join by telephone (use any number to dial in)
+1 312 626 6799
+1 929 436 2866
+1 301 715 8592
+1 346 248 7799
+1 669 900 6833
+1 253 215 8782
International numbers available: https://harvard.zoom.us/u/ab8cFTVHKB
One tap mobile: +13126266799,,92276154062# US (Chicago)
Join by SIP conference room system
Meeting ID: 922 7615 4062