Views Navigation

Event Views Navigation

SES Dissertation Defense

Hussein Mozannar (IDSS)

Training Human-AI Teams ABSTRACT AI systems are augmenting humans' capabilities in settings such as healthcare and programming, forming human-AI teams. To enable more accurate and timely decisions, we need to optimize the performance of the human-AI team directly. In this thesis, we utilize a mathematical framing of the human-AI team and propose a set of methods that optimize the AI, the human, and the interface in which they communicate to enable better team performance. We first show how to provably…

Find out more »

Emergent outlier subspaces in high-dimensional stochastic gradient descent

Reza Gheissari (Northwestern University)

Abstract:  It has been empirically observed that the spectrum of neural network Hessians after training have a bulk concentrated near zero, and a few outlier eigenvalues. Moreover, the eigenspaces associated to these outliers have been associated to a low-dimensional subspace in which most of the training occurs, and this implicit low-dimensional structure has been used as a heuristic for the success of high-dimensional classification. We will describe recent rigorous results in this direction for the Hessian spectrum over the course…

Find out more »

Clean Electricity and the Path to Net Zero: Methods and Insights

Jesse Jenkins (Princeton University )

Abstract: The electricity sector is the linchpin in any path to net-zero greenhouse gas emissions. Electricity sector emissions must fall faster and deeper than any other sector, while simultaneously expanding to power greater shares of energy consumption in transportation, heating, industry and the production of clean fuels. How do we build the grid we need to decarbonize the economy? Prof. Jenkins will share insights from a decade of research on low-carbon electricity systems and pathways to a net-zero America and discuss novel methods…

Find out more »

Matrix displacement convexity and intrinsic dimensionality

Yair Shenfeld (Brown University)

Abstract: The space of probability measures endowed with the optimal transport metric has a rich structure with applications in probability, analysis, and geometry. The notion of (displacement) convexity in this space was discovered by McCann, and forms the backbone of this theory.  I will introduce a new, and stronger, notion of displacement convexity which operates on the matrix level. The motivation behind this definition is to capture the intrinsic dimensionality of probability measures which could have very different behaviors along…

Find out more »

MIT Institute for Data, Systems, and Society
Massachusetts Institute of Technology
77 Massachusetts Avenue
Cambridge, MA 02139-4307