Return to Colloquia & Seminar listing
Avoiding the curse of dimensionality: Computational efficiency in high dimensional inference
Special EventsSpeaker: | Luis Rademacher, Ohio State University |
Related Webpage: | http://www.cse.ohio-state.edu/~lrademac/ |
Location: | 1147 MSB |
Start time: | Mon, Jan 25 2016, 3:10PM |
The goal of inference is to extract information from data. A basic building block in high dimensional inference is feature extraction, that is, to compute functionals of given data that represent it in a way that highlights some underlying structure. For example, Principal Component Analysis is an algorithm that finds a basis to represent data that highlights the property of data being close to a low-dimensional subspace. A fundamental challenge in high dimensional inference is the design of algorithms that are provably efficient and accurate as the dimension grows. I will discuss this challenge and recent work on feature extraction.
There will be a reception following the talk in honor of the speaker.