Views Navigation

Event Views Navigation

Calendar of Events

S Sun

M Mon

T Tue

W Wed

T Thu

F Fri

S Sat

0 events,

0 events,

0 events,

0 events,

0 events,

1 event,

Stochastics and Statistics Seminar Series Ashia Wilson

0 events,

0 events,

1 event,

IDSS Distinguished Seminar Series Johan Ugander

0 events,

0 events,

0 events,

1 event,

Stochastics and Statistics Seminar Series Krishna Balasubramanian

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

Two Approaches Towards Adaptive Optimization

Ashia Wilson (MIT)
E18-304

Abstract: This talk will address to recent projects I am excited about. The first describes efficient methodologies for hyper-parameter estimation in optimization algorithms. I will describe two approaches for how to adaptively estimate these parameters that often lead to significant improvement in convergence. The second describes a new method, called Metropolis-Adjusted Preconditioned Langevin Algorithm for sampling from a convex body. Taking an optimization perspective, I focus on the mixing time guarantees of these algorithms — an essential theoretical property for…

Find out more »

Bridging-based Fact-checking Moderates the Diffusion of False Information on Social Media

Johan Ugander (Stanford University)
MIT Building E18, Room 304

Abstract: Social networks scaffold the diffusion of information on social media. Much attention has been given to the spread of true vs. false content on online social platforms, including the structural differences between their diffusion patterns. However, much less is known about how platform interventions on false content alter the engagement with and diffusion of such content. In this work, we estimate the causal effects of Community Notes, a novel fact-checking feature adopted by X (formerly Twitter) to solicit and…

Find out more »

Finite-Particle Convergence Rates for Stein Variational Gradient Descent

Krishna Balasubramanian (University of California - Davis)
E18-304

Abstract: Stein Variational Gradient Descent (SVGD) is a deterministic, interacting particle-based algorithm for nonparametric variational inference, yet its theoretical properties remain challenging to fully understand. This talk presents two complementary perspectives on SVGD. First, we introduce Gaussian-SVGD, a framework that projects SVGD onto the family of Gaussian distributions using a bilinear kernel. We establish rigorous convergence results for both mean-field dynamics and finite-particle systems, proving linear convergence to equilibrium in strongly log-concave settings. This framework also unifies recent algorithms for…

Find out more »


MIT Institute for Data, Systems, and Society
Massachusetts Institute of Technology
77 Massachusetts Avenue
Cambridge, MA 02139-4307
617-253-1764