Bandits with Switching Costs: T^{2/3} Regret
- 👤 Speaker: Yuval Peres, Microsoft Research Redmond
- 📅 Date & Time: Wednesday 02 April 2014, 14:00 - 15:00
- 📍 Venue: Auditorium, Microsoft Research Ltd, 21 Station Road, Cambridge, CB1 2FB
Abstract
Consider the adversarial two-armed bandit problem in a setting where the player incurs a unit cost each time he switches actions. We prove that the player’s T-round regret in this setting (i.e., his excess loss compared to the better of the two actions) is T (up to a log term). In the corresponding full-information problem, the minimax regret is known to grow at a slower rate of T{1/2} . The difference between these two rates indicates that learning with bandit feedback (i.e. just knowing the loss from the player’s action, not the alternative) can be significantly harder than learning with full-information feedback. It also shows that without switching costs, any regret-minimizing algorithm for the bandit problem must sometimes switch actions very frequently. The proof is based on an information-theoretic analysis of a loss process arising from a multi-scale random walk.
(Joint work with Ofer Dekel, Jian Ding and Tomer Koren, to appear in STOC 2014 available at http://arxiv.org/abs/1310.2997)
Series This talk is part of the Microsoft Research Cambridge, public talks series.
Included in Lists
- All Talks (aka the CURE list)
- Auditorium, Microsoft Research Ltd, 21 Station Road, Cambridge, CB1 2FB
- bld31
- Cambridge Centre for Data-Driven Discovery (C2D3)
- Cambridge talks
- Chris Davis' list
- Guy Emerson's list
- Interested Talks
- Microsoft Research Cambridge, public talks
- ndk22's list
- ob366-ai4er
- Optics for the Cloud
- personal list
- PMRFPS's
- rp587
- School of Technology
- Trust & Technology Initiative - interesting events
- yk449
Note: Ex-directory lists are not shown.
![[Talks.cam]](/static/images/talkslogosmall.gif)

Yuval Peres, Microsoft Research Redmond
Wednesday 02 April 2014, 14:00-15:00