News & EventsDepartment Events
Events
-
Feb18
EVENT DETAILS
lessPierre Nyquist
KTH Royal Institute of Technology
Title: Piecewise deterministic Markov processes for MCMC - A large deviations analysis of the zig-zag sampler
Abstract:
Over the last decade piecewise deterministic Markov processes (PDMPs) have emerged as a new tool for MCMC simulation, potentially mitigating the problems of slow convergence and heavy computational cost exhibited by many other methods. The two main examples of such processes are the bouncy particle sampler and the zig-zag sampler. The idea of using PDMPs extends the ubiquitous discrete time MCMC methodology towards a new continuous time approach, having several advantageous aspects, for example non-reversibility and the possibility to reduce the computational effort per iteration by using subsampling techniques.
In order to employ this new PDMP methodology a solid understanding of mathematical properties of these methods is necessary. Whereas the theoretical
properties of PDMPs have been an active research area in recent years, our understanding of the performance of the corresponding MCMC methods is still incomplete. In particular knowledge of the speed of convergence of time averages is essential in choosing the most suitable sampling technology for a particular problem and in tuning the parameters of the chosen method.In this talk I will discuss recent work on using large deviation results for empirical measures to study and compare the performance of PDMPs. We will start with a general discussion of non-reversible MCMC methods and the use of empirical measure large deviations in the simulation setting. We then focus on PDMPs, in particular the zig-zag sampler, and a large deviations analysis based on the Feng-Krutz approach; no previous knowledge of either PDMPs or large deviations will be necessary. This is based on joint work with Joris Bierkens and Mikola Schlottke.
Bio:
Pierre Nyquist is associate professor in the Department of Mathematics at KTH Royal Institute of Technology in Stockholm. He received his PhD in Applied and Computational Mathematics from the same institution in 2014. Before moving back to KTH in 2018 he spent time as a postdoc in the Division of Applied Mathematics at Brown University and as assistant professor at Eindhoven University of Technology. His research interests lie broadly at the intersection of analysis and probability and include large deviations, stochastic control, interacting particle systems and design and analysis of Monte Carlo methods. Recent work has focused on the mathematical foundation of methods in machine learning.
Title: Piecewise deterministic Markov processes for MCMC - A large deviations analysis of the zig-zag sampler
Abstract:
Over the last decade piecewise deterministic Markov processes (PDMPs) have emerged as a new tool for MCMC simulation, potentially mitigating the problems of slow convergence and heavy computational cost exhibited by many other methods. The two main examples of such processes are the bouncy particle sampler and the zig-zag sampler. The idea of using PDMPs extends the ubiquitous discrete time MCMC methodology towards a new continuous time approach, having several advantageous aspects, for example non-reversibility and the possibility to reduce the computational effort per iteration by using subsampling techniques.
In order to employ this new PDMP methodology a solid understanding of mathematical properties of these methods is necessary. Whereas the theoretical
properties of PDMPs have been an active research area in recent years, our understanding of the performance of the corresponding MCMC methods is still incomplete. In particular knowledge of the speed of convergence of time averages is essential in choosing the most suitable sampling technology for a particular problem and in tuning the parameters of the chosen method.In this talk I will discuss recent work on using large deviation results for empirical measures to study and compare the performance of PDMPs. We will start with a general discussion of non-reversible MCMC methods and the use of empirical measure large deviations in the simulation setting. We then focus on PDMPs, in particular the zig-zag sampler, and a large deviations analysis based on the Feng-Krutz approach; no previous knowledge of either PDMPs or large deviations will be necessary. This is based on joint work with Joris Bierkens and Mikola Schlottke.
—
Bio:
Pierre Nyquist is associate professor in the Department of Mathematics at KTH Royal Institute of Technology in Stockholm. He received his PhD in Applied and Computational Mathematics from the same institution in 2014. Before moving back to KTH in 2018 he spent time as a postdoc in the Division of Applied Mathematics at Brown University and as assistant professor at Eindhoven University of Technology. His research interests lie broadly at the intersection of analysis and probability and include large deviations, stochastic control, interacting particle systems and design and analysis of Monte Carlo methods. Recent work has focused on the mathematical foundation of methods in machine learning.
TIME Tuesday, February 18, 2020 at 11:00 AM - 12:00 PM
LOCATION M228, Technological Institute map it
CONTACT Agnes Kaminski a-kaminski@northwestern.edu EMAIL
CALENDAR Department of Industrial Engineering and Management Sciences
-
Mar14
EVENT DETAILS
lessWinter Classes End
TIME Saturday, March 14, 2020
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Mar21
EVENT DETAILS
lessSpring Break Begins
TIME Saturday, March 21, 2020
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Mar30
EVENT DETAILS
lessSpring Break Ends
TIME Monday, March 30, 2020
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Mar31
EVENT DETAILS
lessSpring Classes begin 8 a.m.
Northwestern Monday: In the fall of 2019, President Schapiro and Provost Holloway announced changes to commencement, spring break and the start of the spring quarter: spring quarters will now routinely start on Tuesday, rather than Monday, to afford two full weekends of break.
Though spring quarters will begin on a Tuesday, the Monday class schedule will be in effect, a practice referred to as “Northwestern Monday.” Classes that usually meet only on Tuesdays will not meet during the first week of the term. This calendar applies to all quarter classes except those offered in the evening programs in the Kellogg School of Management and the School of Professional Studies (SPS).
TIME Tuesday, March 31, 2020
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
May25
EVENT DETAILS
lessMemorial Day (no classes)
TIME Monday, May 25, 2020
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar