Fall 2019

September 16, 2019

Dynamic Monitoring and Decision Systems (DyMonDS) Framework for Data-Enabled Integration in Complex Electric Energy Systems

Speaker: Marija Ilic (MIT)

In this talk, we introduce a unifying Dynamic Monitoring and Decision Systems (DyMonDS) framework that is based on multi-layered modeling for aggregation and minimal coordination of interactions between the layers of complex electric energy...

September 23, 2019

Power of Experimental Design and Active Learning

Speaker: Aarti Singh (Carnegie Mellon University)

Classical supervised machine learning algorithms focus on the setting where the algorithm has access to a fixed labeled dataset obtained prior to any analysis. In most applications, however, we have control over the data collection process...

October 1, 2019

Data-driven Coordination of Distributed Energy Resources

Speaker: Alejandro Dominguez-Garcia (University of Illinois at Urbana-Champaign)

The integration of distributed energy resources (DERs), e.g., rooftop photovoltaics installations, electric energy storage devices, and flexible loads, is becoming prevalent. This integration poses numerous operational challenges on the...

October 21, 2019

Robustness Analysis of Neural Networks via Semidefinite Programming

Speaker: George Pappas (University of Pennsylvania)

Deep neural networks have dramatically impacted machine learning problems in numerous fields. Despite these major advances, neural networks are not robust and hence not suitable for safety-critical applications. In this lecture, we will...

October 28, 2019

The Age of Information in Networks: Moments, Distributions, and Sampling 

Speaker: Roy Yates (Rutgers University)

We examine a source providing status updates to monitors through a network with state defined by a continuous-time finite Markov chain. Using an age of information (AoI) metric, we characterize timeliness by the vector of ages tracked by the...

November 18, 2019

Towards Model Agnostic Robustness

Speaker: Sujay Sanghavi (University of Texas at Austin)

It is now common practice to try and solve machine learning problems by starting with a complex existing model or architecture, and fine-tuning/adapting it to the task at hand. However, outliers, errors or even just sloppiness in training...

November 25, 2019

Finite-Time Performance Bounds and Adaptive Learning Rate Selection for TD Learning

Speaker: Rayadurgam Srikant (University of Illinois at Urbana-Champaign)

Temporal difference learning is a widely-used algorithm to estimate the value function of an MDP under a given policy. Here, we consider TD learning with linear function approximation and a constant learning rate, and obtain bounds on its...