Abstract
In this work we introduce a new optimisation method called SAGA in the spirit of SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient algorithms with fast linear convergence rates. SAGA improves on the theory behind SAG and SVRG, with better theoretical convergence rates, and has support for composite objectives where a proximal operator is used on the regulariser. Unlike SDCA, SAGA supports non-strongly convex problems directly, and is adaptive to any inherent strong convexity of the problem. We give experimental results showing the effectiveness of our method.
| Original language | English |
|---|---|
| Pages (from-to) | 1646-1654 |
| Number of pages | 9 |
| Journal | Advances in Neural Information Processing Systems |
| Volume | 2 |
| Issue number | January |
| Publication status | Published - 2014 |
| Event | 28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014 - Montreal, Canada Duration: 8 Dec 2014 → 13 Dec 2014 |
Fingerprint
Dive into the research topics of 'SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver