IDSS Special Seminar

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). In this talk we will: a) review SDPIs; b) show how point-to-point SDPIs can be combined into an SDPI for a network; c) show recent…

Title: Graphical models under total positivity Abstract: We discuss properties of distributions that are multivariate totally positive of order two (MTP2). Such distributions appear in the context of positive dependence, ferromagnetism in the Ising model, and various latent models. While such distributions have a long history in probability theory and statistical physics, in this talk I will discuss such distributions in the context of high dimensional statistics and graphical models. In particular, I will show that MTP2 in the Gaussian…

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 been used in many places in the literature such as correlation analysis, correspondence analysis. In this talk, we will go through some of the basic…

This seminar consists of a series of lectures each followed by a period of informal discussion and social. The topics are at the nexus of information theory, inference, causality, estimation, and non-convex optimization. The lectures are intended to be tutorial in nature with the goal of learning about interesting and exciting topics rather than merely hearing about the most recent results. The topics are driven by the interests of the speakers, and with the exception of the two lectures on…

This seminar consists of a series of lectures each followed by a period of informal discussion and social. The topics are at the nexus of information theory, inference, causality, estimation, and non-convex optimization. The lectures are intended to be tutorial in nature with the goal of learning about interesting and exciting topics rather than merely hearing about the most recent results. The topics are driven by the interests of the speakers, and with the exception of the two lectures on…

*This lecture is the second of two. The first lecture was given Thursday, October 25th. Title: Randomness and Information I and II Abstract: Exact or approximate generation of random variables with prescribed statistics from a given randomness source has many important applications, including random number generation from physical sources, Monte Carlo simulations, and randomized algorithms, e.g., for cryptography, optimization, and machine learning. It is also closely related to several fundamental questions in information theory, CS theory, and quantum information. The…

This seminar consists of a series of lectures each followed by a period of informal discussion and social. The topics are at the nexus of information theory, inference, causality, estimation, and non-convex optimization. The lectures are intended to be tutorial in nature with the goal of learning about interesting and exciting topics rather than merely hearing about the most recent results. The topics are driven by the interests of the speakers, and with the exception of the two lectures on…

This seminar consists of a series of lectures each followed by a period of informal discussion and social. The topics are at the nexus of information theory, inference, causality, estimation, and non-convex optimization. The lectures are intended to be tutorial in nature with the goal of learning about interesting and exciting topics rather than merely hearing about the most recent results. The topics are driven by the interests of the speakers, and with the exception of the two lectures on…

Abstract: Targeted socio-economic policies require an accurate understanding of a country's demographic makeup. To that end, the United States spends more than 1 billion dollars a year gathering census data such as race, gender, education, occupation and unemployment rates. Compared to the traditional method of collecting surveys across many years which is costly and labor intensive, data-driven, machine learning driven approaches are cheaper and faster--with the potential ability to detect trends in close to real time. In this work, we…