Abstract
We study the problem of actively learning a multi-index function of the form f(x) = g0(A0x) from its point evaluations, where A0 ∈ k×d with k 蠑 d. We build on the assumptions and techniques of an existing approach based on low-rank matrix recovery (Tyagi and Cevher, 2012). Specifically, by introducing an additional self-concordant like assumption on g0 and adapting the sampling scheme and its analysis accordingly, we provide a bound on the sampling complexity with a weaker dependence on d in the presence of additive Gaussian sampling noise. For example, under natural assumptions on certain other parameters, the dependence decreases from O(d3/2) to O(d).
Original language | English (US) |
---|---|
Title of host publication | 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 2189-2193 |
Number of pages | 5 |
ISBN (Electronic) | 9781467369978 |
DOIs | |
State | Published - Aug 4 2015 |
Event | 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Brisbane, Australia Duration: Apr 19 2014 → Apr 24 2014 |
Publication series
Name | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
---|---|
Volume | 2015-August |
ISSN (Print) | 1520-6149 |
Other
Other | 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 |
---|---|
Country/Territory | Australia |
City | Brisbane |
Period | 4/19/14 → 4/24/14 |
Bibliographical note
Publisher Copyright:© 2015 IEEE.
Keywords
- Dantzig selector
- Function learning
- low-rank matrix recovery
- multi-index functions