|
Online Learning for Global Cost Functions| old_uid | 7352 |
|---|
| title | Online Learning for Global Cost Functions |
|---|
| start_date | 2009/09/21 |
|---|
| schedule | 13h30 |
|---|
| online | no |
|---|
| summary | We consider an online learning setting where at each time step the decision maker has to choose how to distribute the future loss between k alternatives, and then observes the loss of each alternative. Motivated by load balancing and job scheduling, we consider a global cost function (over the losses incurred by each alternative), rather than a summation of the instantaneous losses as done traditionally in online learning. Such global cost functions include the makespan (the maximum over the |
|---|
| responsibles | Biau, Stoltz, Massart |
|---|
| |
|