DeepAI AI Chat
Log In Sign Up

Non-exponentially weighted aggregation: regret bounds for unbounded loss functions

by   Pierre Alquier, et al.

We tackle the problem of online optimization with a general, possibly unbounded, loss function. It is well known that the exponentially weighted aggregation strategy (EWA) leads to a regret in √(T) after T steps, under the assumption that the loss is bounded. The online gradient algorithm (OGA) has a regret in √(T) when the loss is convex and Lipschitz. In this paper, we study a generalized aggregation strategy, where the weights do no longer necessarily depend exponentially on the losses. Our strategy can be interpreted as the minimization of the expected losses plus a penalty term. When the penalty term is the Kullback-Leibler divergence, we obtain EWA as a special case, but using alternative divergences lead to a regret bounds for unbounded, not necessarily convex losses. However, the cost is a worst regret bound in some cases.


page 1

page 2

page 3

page 4


Unconstrained Online Learning with Unbounded Losses

Algorithms for online learning typically require one or more boundedness...

Improved Regret Bounds for Online Kernel Selection under Bandit Feedback

In this paper, we improve the regret bound for online kernel selection u...

A Second-order Bound with Excess Losses

We study online aggregation of the predictions of experts, and first sho...

Optimal learning with Bernstein Online Aggregation

We introduce a new recursive aggregation procedure called Bernstein Onli...

Regret Bounds for Lifelong Learning

We consider the problem of transfer learning in an online setting. Diffe...

Data-Dependent Bounds for Online Portfolio Selection Without Lipschitzness and Smoothness

This work introduces the first small-loss and gradual-variation regret b...

On loss functions and regret bounds for multi-category classification

We develop new approaches in multi-class settings for constructing prope...