University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > Stochastic Analysis & Algorithms: From numerics for SDEs to Langevin algorithms

Stochastic Analysis & Algorithms: From numerics for SDEs to Langevin algorithms

Add to your list(s) Download to your calendar using vCal

  • UserSotirios Sabanis (University of Edinburgh)
  • ClockThursday 27 June 2024, 15:00-16:50
  • HouseExternal.

If you have a question about this talk, please contact nobody.

DMLW02 - Summer school on fundamentals and applications of diffusion models

In recent years, diffusion-based algorithms have gained significant popularity due to their extensive application in sampling and non-convex optimization. These algorithms are frequently conceptualized as numerical schemes for stochastic differential equations (SDEs), a perspective that enables the utilization of advanced tools from modern probability theory and stochastic analysis for their analysis. We will review critical aspects of the analysis of these numerical methods applied to random systems, and will provide important comparisons with stochastic gradient methods commonly employed in machine learning and artificial intelligence.

This talk is part of the Isaac Newton Institute Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity