A Stochastic View of Optimal Regret through Minimax Duality

  title={A Stochastic View of Optimal Regret through Minimax Duality},
  author={Jacob D. Abernethy and Alekh Agarwal and Peter L. Bartlett and Alexander Rakhlin},
We study the regret of optimal strategies for online convex optimization games. Using von Neumann’s minimax theorem, we show that the optimal regret in this adversarial setting is closely related to the behavior of the empirical minimization algorithm in a stochastic process setting: it is equal to the maximum, over joint distributions of the adversary’s action sequence, of the difference between a sum of minimal expected losses and the minimal empirical loss. We show that the optimal regret… CONTINUE READING
Highly Cited
This paper has 89 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 1 time over the past 90 days. VIEW TWEETS
62 Citations
18 References
Similar Papers


Publications citing this paper.

90 Citations

Citations per Year
Semantic Scholar estimates that this publication has 90 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 18 references

A stochastic view of optimal regret through minimax duality

  • A. Agarwal J. Abernethy, P. L. Bartlett, A. Rakhlin
  • 2009

Convex games in banach spaces (working title)

  • K. Sridharan, A. Tewari
  • 2009
1 Excerpt

Similar Papers

Loading similar papers…