|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
Large-scale convex optimization for machine learning
If you have a question about this talk, please contact Richard Samworth.
Many machine learning and signal processing problems are traditionally cast as convex optimization problems. A common difficulty in solving these problems is the size of the data, where there are many observations (“large n”) and each of these is large (“large p”). In this setting, online algorithms which pass over the data only once, are usually preferred over batch algorithms, which require multiple passes over the data. In this talk, I will present several recent results, showing that in the ideal infinite-data setting, online learning algorithms based on stochastic approximation should be preferred (both in terms of running speed and generalization performance), but that in the practical finite-data setting, an appropriate combination of batch and online algorithms leads to unexpected behaviors, such as a linear convergence rate with an iteration cost similar to stochastic gradient descent.
This is joint work with Nicolas Le Roux, Eric Moulines and Mark Schmidt.
This talk is part of the Statistics series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsEMBL-EBI Science & Society Silicon Valley comes to the UK 2011 National Centre for Statistical Ecology (NCSE) Seminars
Other talksNovel Conjugated Materials for Fission, Fusion and Reverse Intersystem Crossing Mesembryanthemums A Very Fine Swan Indeed: Art, science and the unfeathered bird Three stories of money in the Age of Discovery *Please note that this talk has been cancelled* How unsteady winds can fuel phytoplankton blooms at fronts in the upper ocean