March 2020
[POSTPONED] Large-Scale Cyber-Physical Systems: From Control Theory to Deep Learning
Navid Azizan (California Institute of Technology)
online
Abstract: The expansion of large-scale cyber-physical systems such as electrical grids, transportation networks, IoT, and other societal networks has created enormous challenges for controlling them and, at the same time, tremendous opportunities for utilizing the massive amounts of data generated by them. At the core of these data-driven control problems are distributed and stochastic optimization algorithms, such as the widely used stochastic gradient descent (SGD). While easy to use, these algorithms are not so easy to analyze, and in many…
Find out more »Safe Deep Learning in the Loop: Challenges, Methods, and Future Directions
Mahyar Fazlyab (University of Pennsylvania)
E18-304
Abstract: Despite high-profile advances in various decision-making and classification tasks, Deep Neural Networks (DNNs) have found limited application in safety-critical domains such as self-driving cars and automated healthcare. In particular, DNNs can be vulnerable to adversarial attacks and input uncertainties. This issue becomes even more complicated when DNNs are used in closed-loop systems, where a small perturbation (caused by noisy measurements, uncertain initial conditions, disturbances, etc.) can substantially impact the system being controlled. Therefore, it is of utmost importance…
Find out more »Women in Data Science (WiDS) – Cambridge, MA
Microsoft NERD Center, Cambridge
This one-day technical conference brings together local academic leaders, industrial professionals and students to hear about the latest data science-related research in a number of domains, to learn how leading-edge companies are leveraging data science for success, and to connect with potential mentors, collaborators, and others in the field.
Find out more »Foundations of Resilient Collaborative Autonomy: From Combinatorial Optimization to Control and Learning
Vasileios Tzoumas (MIT)
E18-304
Abstract: Collaborative autonomous robots promise to revolutionize transportation, disaster response, and environmental monitoring. Already, micro-aerial vehicles have become a multi-billion-dollar industry; and in this new decade, teams of semi-autonomous ships, cars, and underwater exploration vehicles are being launched. A future of ubiquitous autonomy is becoming a reality, where robots can autonomously split into teams, and navigate and learn the world. However, this future is threatened by attacks and failures that can compromise the robots’ teams, control, and learning capabilities,…
Find out more »Does Revolution Work? Evidence from Nepal
Rohini Pande (Yale University)
E18-304
The last half century has seen the adoption of democratic institutions in much of the developing world. However, the conditions under which de jure democratization leads to the representation of historically disadvantaged groups remains debated as do the implications of descriptive representation for policy inclusion. Using detailed administrative and survey data from Nepal, we examine political selection in a new democracy, the implications for policy inclusion and the role of conflict in affecting political transformation. I situate these findings in the context of…
Find out more »February 2020
Tales of Random Projections
Kavita Ramanan (Brown University)
E18-304
Abstract: Properties of random projections of high-dimensional probability measures are of interest in a variety of fields, including asymptotic convex geometry, and potential applications to high-dimensional statistics and data analysis. A particular question of interest is to identify what properties of the high-dimensional measure are captured by its lower-dimensional projections. While fluctuations of these projections have been well studied over the past decade, we describe more recent work on the tail behavior of such projections, and various implications. This talk…
Find out more »Predictive Inference with the Jackknife+
Rina Foygel Barber (University of Chicago)
E18-304
Abstract: We introduce the jackknife+, a novel method for constructing predictive confidence intervals that is robust to the distribution of the data. The jackknife+ modifies the well-known jackknife (leaveoneout cross-validation) to account for the variability in the fitted regression function when we subsample the training data. Assuming exchangeable training samples, we prove that the jackknife+ permits rigorous coverage guarantees regardless of the distribution of the data points, for any algorithm that treats the training points symmetrically (in contrast, such guarantees…
Find out more »Diffusion K-means Clustering on Manifolds: provable exact recovery via semidefinite relaxations
Xiaohui Chen (University of Illinois at Urbana-Champaign)
E18-304
Abstract: We introduce the diffusion K-means clustering method on Riemannian submanifolds, which maximizes the within-cluster connectedness based on the diffusion distance. The diffusion K-means constructs a random walk on the similarity graph with vertices as data points randomly sampled on the manifolds and edges as similarities given by a kernel that captures the local geometry of manifolds. Thus the diffusion K-means is a multi-scale clustering tool that is suitable for data with non-linear and non-Euclidean geometric features in mixed dimensions. Given…
Find out more »Risk-Sensitive Safety Analysis and Control for Trustworthy Autonomy
Margaret Chapman (UC Berkeley)
E18-304
Abstract: Methods for managing dynamic systems typically invoke one of two perspectives. In the worst-case perspective, the system is assumed to behave in the worst possible way; this perspective is used to provide formal safety guarantees. In the risk-neutral perspective, the system is assumed to behave as expected; this perspective is invoked in reinforcement learning and stochastic optimal control. While the worst-case perspective is useful for safety analysis, it can lead to unnecessarily conservative decisions, especially in settings where uncertainties…
Find out more »Webinar: Inside the MITx MicroMasters Program in Statistics and Data Science
Devavrat Shah, Karene Chu
online
Interested in starting your data science journey? Register for this special free virtual event. You'll receive a confirmation e-mail with further details about the webinar. Demand for professionals skilled in data, analytics, and machine learning is exploding. A recent report by IBM and Burning Glass states that there will be 364K new job openings in data-driven professions this year in the US alone. Data scientists bring value to organizations across industries because they are able to solve complex challenges with…
Find out more »