Extra Colloquium Mathematics - Max Welling
Join us for coffee and tea at 15.45 p.m.
Date: Thursday, March 17th 2011
Speaker: Max Welling
Room: 5161.0289 (Bernoulliborg),
Time: 16.15
Title: Herding: Learning with Weakly Chaotic Nonlinear Dynamical Systems
Abstract:
We describe a class of deterministic weakly chaotic dynamical systems with infinite memory. These ``herding systems'' combine learning and inference into one algorithm. They convert moments directly into a sequence of pseudo-samples without learning an explicit model. Using the "perceptron cycling theorem" we can easily show that Monte Carlo estimates based on these pseudo-samples converge at an optimal rate of O(1/T), due to infinite range negative auto-correlations. We show that the information content of these sequences, as measured by sub-extensive entropy, can grow as fast as K log(N), which is faster than the usual 1/2 K log(N) for sequences generated by random posterior sampling from a Bayesian posterior model. In continuous spaces we can control an infinite number of moments
by formulating herding in a Hilbert space. Also in this case sample averages over arbitrary functions in the Hilbert space will converge at an optimal rate of O(1/T).
More generally, we advocate the application of the rich theoretical framework of nonlinear dynamical systems and chaos theory to statistical learning.
Colloquium coordinators are Prof.dr. A.C.D. van Enter (e-mail : A.C.D.van.Enter@rug.nl) and
Dr. M. Dür (e-mail: M.E.Dur@rug.nl)
Last modified: | 10 February 2021 2.28 p.m. |
More news
-
23 April 2024
Nine MSCA Doctoral Network grants for FSE researchers
Nine researchers of the Faculty of Science and Engineering have received a Horizon Europe Marie Sklodowska Curie Doctoral Network grant.
-
22 April 2024
Charissa Roossien secures JTF subsidy to develop Health Tracker
Dr. Charissa Roossien (ENTEG) has successfully secured a Just Transition Fund (JTF) subsidy of 1.8 million euros to develop a Health Tracker for reliable respiratory and metabolic analysis.
-
15 April 2024
Single-molecule engineering niche in Gravitation research
With her expertise in single-molecule techniques, Dr. Kasia Tych (GBB) will contribute to a big Grvitation-research programme