Online Learning Meets Optimization in the Dual

  title={Online Learning Meets Optimization in the Dual},
  author={Shai Shalev-Shwartz and Yoram Singer},
We describe a novel framework for the design and analysis of o nline learning algorithms. Our framework is based on a new perspec tive on relative mistake bounds by viewing the number of mistakes of an online learning algorithm as a lower bound for an optimization problem. This inte rpr tation of a mistake bound draws a connection between online learning and op timization through the theory of duality. In particular, we show that any proced ur which incrementally increases a dual objective… CONTINUE READING
Highly Cited
This paper has 56 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.
40 Citations
16 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 40 extracted citations

57 Citations

Citations per Year
Semantic Scholar estimates that this publication has 57 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 16 references

Convex Optimization

  • S. Boyd, L. Vandenberghe
  • 2004
Highly Influential
4 Excerpts

On the generalization abilityof on - line learning algorithms

  • A. Conconi N. Cesa-Bianchi, C. Gentile
  • Convex Optimization
  • 2004

Online learn ing with kernels.IEEE Transactions on Signal Processing

  • J. Kivinen, A. J. Smola, R. C. Williamson
  • 2002
1 Excerpt

Similar Papers

Loading similar papers…