Hi All,
We will have a talk tomorrow (Friday) by Nicolas Le Roux (work with Andrew Fitzgibbon). Apologies for the short notice.
Place: Pavillon André-Aisenstadt, room 3195 Time 3pm, Friday July 16th
Title: A fast natural Newton method
Abstract: Nowadays, for many tasks such as object recognition or language modeling, data is plentiful. As such, an important challenge has become to find learning algorithms which can make use of all the available data. In this setting, called ``large-scale learning'' by Bottou and Bousquet (2008), learning and optimization become different and powerful optimization algorithms are suboptimal learning algorithms. While most efforts are focused on adapting optimization algorithms for learning by efficiently using the information contained in the Hessian, Le Roux et al. (2008) exploited the special structure of the learning problem to achieve faster convergence. In this paper, we investigate a natural way of combining these two directions to yield fast and robust learning algorithms.
Cheers, Aaron