We consider a variant of the multiarmed bandit (MAB) problem where jobs or tasks queue for service, and service rates of different servers (agents) may be unknown. Such (queueing+learning) problems are motivated by a vast range of service systems, including supply and demand in online platforms (e.g., Uber, Lyft, Airbnb, Upwork, etc.), order flow in…
Title: Strong data processing inequalities and information percolation Abstract: The data-processing inequality, that is, $I(U;Y) \le I(U;X)$ for a Markov chain $U \to X \to Y$, has been the method of choice for proving impossibility (converse) results in information theory and many other disciplines. A channel-dependent improvement is called the strong data-processing inequality (or SDPI).…
MIT Statistics and Data Science Center host guest lecturers from around the world in this weekly seminar.
We bring the tools from Blackwell’s seminal result on comparing two stochastic experiments from 1953, to shine a new light on a modern application of great interest: Generative Adversarial Networks (GAN). Binary hypothesis testing is at the center of training GANs, where a trained neural network (called a critic) determines whether a given sample is…
Social scientists are increasingly turning to computer-assisted text analysis as a way of understanding the digital footprints left by communities and individuals. Much of the technology that powers these approaches is borrowed from the fields of computer science and statistics; yet, social scientists have substantially different goals. We focus on the development of methods that…
Abstract Concentration of measure refers to a collection of tools and results from analysis and probability theory that have been used in many areas of pure and applied mathematics. Arguably, the first data science application of measure concentration (under the name ‘‘blowing-up lemma’’) is the proof of strong converses in multiuser information theory by Ahlswede,…
Abstract: The Graph Matching problem is a robust version of the Graph Isomorphism problem: given two not-necessarily-isomorphic graphs, the goal is to find a permutation of the vertices which maximizes the number of common edges. We study a popular average-case variant; we deviate from the common heuristic strategy and give the first quasi-polynomial time algorithm,…
Tackle challenges on the future of cities, future of health, and future of work! For this IDSS student-run hackathon, teams will propose creative policy solutions to societal challenges using a combination of robust data analytics and domain knowledge. This event is a part of HUBweek, a leading ideas festival founded by institutions from the greater Boston area (including MIT).
Abstract: Local geometric analysis is a method to define a coordinate system in a small neighborhood in the space of distributions over a given alphabet. It is a powerful technique since the notions of distance, projection, and inner product defined this way are useful in the optimization problems involving distributions, such as regressions. It has…
Abstract: In this talk, we investigate statistical learning and estimation under local privacy constraints, where data providers do not trust the collector of the data and so privatize their data before it is even collected. We identify fundamental tradeoffs between statistical utility and privacy in such local models of privacy, providing instance-specific bounds for private…