Non-Exponentially Weighted Aggregation: Regret Bounds for Unbounded Loss Functions

Authors: Pierre Alquier

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we study a generalized aggregation strategy, where the weights no longer depend exponentially on the losses. Our strategy is based on Follow The Regularized Leader (FTRL): we minimize the expected losses plus a regularizer, that is here a φ-divergence. When the regularizer is the Kullback-Leibler divergence, we obtain EWA as a special case. Using alternative divergences enables unbounded losses, at the cost of a worst regret bound in some cases.
Researcher Affiliation Academia Pierre Alquier 1 RIKEN AIP, Tokyo, Japan. Correspondence to: Pierre Alquier <pierrealain.alquier@riken.jp>.
Pseudocode No No structured pseudocode or algorithm blocks were found in the paper. Algorithms are described mathematically or textually.
Open Source Code No The paper does not contain any statements about releasing open-source code or links to a code repository for the methodology described.
Open Datasets No This paper is theoretical and does not involve experiments on datasets, thus no information regarding dataset availability for training is provided.
Dataset Splits No This paper is theoretical and does not involve experiments on datasets, thus no information regarding validation splits is provided.
Hardware Specification No This paper is theoretical and does not describe any experiments or the specific hardware used.
Software Dependencies No This paper is theoretical and does not mention any specific software dependencies with version numbers.
Experiment Setup No This paper is theoretical and does not describe any experimental setup details, such as hyperparameters or training configurations.