Join us for coffee and tea at 15.45 p.m.
Date: Thursday, March 17th 2011
Speaker: Max Welling
Room: 5161.0289 (Bernoulliborg),
Herding: Learning with Weakly Chaotic Nonlinear Dynamical Systems
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 momentsby 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.
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)
Two promising UG academics, Dr Michael Lerch and Sanne van Dijk, will be able to conduct research at top institutes abroad for two years thanks to the Rubicon programme organized by the Netherlands Organisation for Scientific Research (NWO).
His opponent was fourfold world champion Alexander Schwarzman. Boomstra, who studies Physics at the University of Groningen, also won the title in 2016.
Galaxies grow by giving birth to new stars, but Amina Helmi found evidence to support the theory that parts of the Milky Way have also grown by merging with other galaxies. She had to wait for the Gaia space mission to produce data before she was able...