Mhammedi, Z;
Guedj, B;
Williamson, RC;
(2020)
PAC-Bayesian Bound for the Conditional Value at Risk.
In:
Proceedings of the 34th Conference on Neural Information Processing Systems.
Neural Information Processing Systems Foundation: Vancouver, Canada.
(In press).
![[thumbnail of NeurIPS-2020-pac-bayesian-bound-for-the-conditional-value-at-risk-Paper.pdf]](https://discovery.ucl.ac.uk/style/images/fileicons/text.png) |
Text
NeurIPS-2020-pac-bayesian-bound-for-the-conditional-value-at-risk-Paper.pdf - Published Version Available under License : See the attached licence file. Download (1MB) |
Abstract
Conditional Value at Risk (CVAR) is a family of “coherent risk measures” which generalize the traditional mathematical expectation. Widely used in mathematical finance, it is garnering increasing interest in machine learning, e.g., as an alternate approach to regularization, and as a means for ensuring fairness. This paper presents a generalization bound for learning algorithms that minimize the CVAR of the empirical loss. The bound is of PAC-Bayesian type and is guaranteed to be small when the empirical CVAR is small. We achieve this by reducing the problem of estimating CVAR to that of merely estimating an expectation. This then enables us, as a by-product, to obtain concentration inequalities for CVAR even when the random variable in question is unbounded.
| Type: | Proceedings paper |
|---|---|
| Title: | PAC-Bayesian Bound for the Conditional Value at Risk |
| Event: | 34th Conference on Neural Information Processing Systems |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://proceedings.neurips.cc/paper/2020/hash/d02... |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10104814 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
