Highly-Smooth Zero-th Order Online Optimization

Add to your list(s) Download to your calendar using vCal

• Vianney Perchet (INRIA & Paris Diderot)
• Friday 30 October 2015, 16:00-17:00
• MR12, Centre for Mathematical Sciences, Wilberforce Road, Cambridge..

If you have a question about this talk, please contact Quentin Berthet.

The minimization of convex functions which are only available through partial and noisy information is a key methodological problem in machine learning. We consider online convex optimization with noisy zero-th order information, that is noisy function evaluations at any desired point. We focus on problems with high degrees of smoothness, such as online logistic regression. We show that as opposed to gradient-based algorithms, high-order smoothness may be used to improve estimation rates, with a precise dependence of our upper-bounds on the degree of smoothness. In particular, we show that for infinitely differentiable functions, we recover essentially the same dependence on sample size as gradient-based algorithms, with an extra dimension-dependent factor. This is done for convex and strongly-convex functions, with finite horizon and anytime algorithms.

This talk is part of the Statistics series.

This talk is included in these lists:

• All CMS events
• All Talks (aka the CURE list)
• CMS Events
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• DPMMS Lists
• DPMMS info aggregator
• DPMMS lists
• Guy Emerson's list
• Hanchen DaDaDash
• Interested Talks
• MR12, Centre for Mathematical Sciences, Wilberforce Road, Cambridge.
• Machine Learning
• School of Physical Sciences
• Statistical Laboratory info aggregator
• Statistics
• Statistics Group
• bld31
• custom
• rp587

Note that ex-directory lists are not shown.