LIDS Seminar Series

The LIDS seminar series serves as a focal point in the intellectual life of the lab. Seminar videos, when available, can be found on the LIDS YouTube channel.

October 2, 2023

Complexity of Finding Local Minima in Continuous Optimization

Amir Ali Ahmadi (Princeton)

Can we efficiently find a local minimum of a nonconvex continuous optimization problem? We give a rather complete answer to this question for optimization problems defined by polynomial data. In the unconstrained case, the answer remains positive...

October 16, 2023

Beyond Low-Inertia Systems: Grid-Forming Control Foundations for Converter-Dominated Power Systems

Dominic Groß (University of Wisconsin-Madison)

At the heart of the transition to a zero-carbon power system is a technological paradigm shift from conventional generation to renewable generation connected to the grid via power electronics. In this context, the literature and public debate mostly...

October 25, 2023

Inferential Artificial Intelligence (iAI): Cases Studies in Computational Statistics, Machine Learning, and Global Health

Seth Flaxman (Oxford)

Machine learning is the computational beating heart of the modern AI renaissance. Behind the hype, a range of machine learning and computational statistical methods are quietly revolutionizing our approach to difficult statistical and scientific...

October 30, 2023

Formal Methods for Safety-Critical Control

Calin Belta (Boston University)

In control theory, complicated dynamics such as systems of (nonlinear) differential equations are mostly controlled to achieve stability and to optimize a cost. In formal synthesis, simple systems such as finite state transition graphs modeling...

November 13, 2023

Control-Theory Concepts in Systems Biology and Algorithms: Responses to Inputs, Transients, and Asymptotic Behaviors

Eduardo Sontag (Northeastern )

This talk will focus on systems-theoretic and control theory tools that help characterize the responses of nonlinear systems to external inputs, with an emphasis on how network structure constrains finite-time, transient behaviors. Of interest are...

November 27, 2023

Collaborative learning for control

James Anderson (Columbia University )

We begin by studying the problem of learning a linear system model from the observations of M clients. The catch: Each client is observing data from a different dynamical system. This work addresses the question of how multiple clients...

December 4, 2023

Learning from Dynamics

Ankur Moitra (MIT)

Linear dynamical systems are the canonical model for time series data. They have wide-ranging applications and there is a vast literature on learning their parameters from input-output sequences. Moreover they have received renewed interest because...

December 8, 2023

Blockchain in Smart Grids: Steering Sustainable Development Goals Forward

Jesús Rodríguez-Molina (Technical University of Madrid)

In the contemporary era, Sustainable Development Goals (SDGs) serve as the backbone of global efforts to ensure a future that harmonizes environmental conservation, social equity, and economic growth. One of the critical challenges facing these...

February 5, 2024

Digital Cousins: Ensemble/Multi-scale Learning for Markov Decision Processes

Urbashi Mitra (USC)

Many agent-based systems interacting with their environments are well-modeled by Markov Decision Processes (MDPs). MDPs also form the ``model ‘’ framework for many learning strategies such as reinforcement learning. We focus on policy design to...

February 26, 2024

Multi-Agent Dynamical Systems: Equilibria, Learning, and Asymptotics

Tamer Başar (UIUC)

Decision-making in dynamic uncertain environments with multiple agents having possibly misaligned objectives arises in many disciplines and application domains, including control (particularly networked control, such as control and operation of...

March 11, 2024

Entropy and minimal data rates for state estimation and model detection

Daniel Liberzon (UIUC)

In this talk we will discuss estimation entropy for continuous-time nonlinear systems, which is a variant of topological entropy formulated in terms of the number of functions that approximate all system trajectories up to an exponentially decaying...

March 18, 2024

Real-Time Robust Multivariate Estimator for Dynamic Systems with Heavy-Tailed Additive Uncertainties

Jason Speyer (UCLA)

A recursive, analytic, real-time state estimation algorithm for linear and nonlinear systems, referred to as the Multivariate Cauchy Estimator (MCE), is presented. The algorithm enables robust state estimation performance for applications where the...

April 1, 2024

Why is RLHF Data-Efficient in Policy Optimization?

R. Srikant (UIUC)

We consider a version of a policy optimization in reinforcement learning where one has to learn rewards through human feedback. We study the sample complexity of this algorithm and compare it to the sample complexity of an algorithm where the...

April 8, 2024

Safe Learning in Autonomous Systems

Naira Hovakimyan (UIUC)

Learning-based control paradigms have seen many success stories with various robots and co-robots in recent years. However, as these robots prepare to enter the real world, operating safely in the presence of imperfect model knowledge and external...

April 22, 2024

Contraction Theory for Optimization, Control, and Neural Networks

Francesco Bullo (UC Santa Barbara)

I survey recent advances on contraction theory for dynamical systems, as a robust, computationally-friendly and modular stability theory. Starting from basic notions, I will present novel theoretical properties and examples of contracting dynamics,...

April 29, 2024

Representation-based Learning and Control for Dynamical Systems

Na Li (Harvard)

The explosive growth of machine learning and data-driven methodologies have revolutionized numerous fields. Yet, their application to real-world dynamical physical systems remains a significant challenge. Closing the loop from data to actions in...

May 13, 2024

Structural Deep Learning

Sanjog Misra (University of Chicago)

Humans have an amazing ability to describe the structure of the world in ways that allows for constraints, realisms and boundaries to be respected. This structure facilitates the notion of counterfactuals which is a fundamental element of any...