Spring 2019 – Page 2

Human-Interpretable Concept Learning via Information Lattices

Is it possible to learn the laws of music theory directly from raw sheet music in the same human-interpretable form as a music theory textbook? How little prior knowledge needs to be encoded to do so? We consider these and similar questions in other topical domains, in developing a general …

Data-Driven Discovery and Control of Complex Systems: Uncovering Interpretable and Generalizable Nonlinear Models

Accurate and efficient reduced-order models are essential to understand, predict, estimate, and control complex, multiscale, and nonlinear dynamical systems. These models should ideally be generalizable, interpretable, and based on limited training data. This work develops a general framework to discover the governing equations underlying a dynamical system simply from data …

Learning Representations for Information Obfuscation and Inference

Data collection and sharing are pervasive aspects of modern society. This process can either be voluntary, as in the case of a person taking a facial image to unlock his/her phone, or inciden-tal, such as traf?c cameras collecting videos on pedestrians. An undesirable side effect of these processes is that …

Multistage Distributionally Robust Optimization with Total Variation Distance: Modeling and Effective Scenarios

Traditional multistage stochastic optimization assumes the underlying probability distribution is known. However, in practice, the probability distribution is often not known or cannot be accurately approximated. One way to address such distributional ambiguity is to use distributionally robust optimization (DRO), which minimizes the worst-case expected cost with respect to a …

Information-theoretic Privacy: Leakage measures, robust privacy guarantees, and generative adversarial mechanism design

Privacy is the problem of ensuring limited leakage of information about sensitive features while sharing information (utility) about non-private features to legitimate data users. Even as differential privacy has emerged as a strong desideratum for privacy, there is also an equally strong need for context-aware utility-guaranteeing approaches in many data …

Billion-degree of freedom Computational Dynamics: from granular flows to 3D printing and on to river fording simulation

This talk will focus on how a Lagrangian perspective on dynamics is used to capture the time evolution of complex systems, e.g., granular flows, fluid-solid interaction problems, etc. In this context, the aspects that turn out to be more challenging are tied to the handling of friction, contact, geometry, large …