Combining Adversarial Guarantees and Stochastic Fast Rates in Online Learning

Authors: Wouter M. Koolen, Peter Grünwald, Tim van Erven

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We prove that these algorithms attain fast rates in their respective settings both in expectation and with high probability.
Researcher Affiliation Academia Wouter M. Koolen Centrum Wiskunde & Informatica Science Park 123, 1098 XG Amsterdam, the Netherlands wmkoolen@cwi.nl Peter Grünwald CWI and Leiden University pdg@cwi.nl Tim van Erven Leiden University Niels Bohrweg 1, 2333 CA Leiden, the Netherlands tim@timvanerven.nl
Pseudocode No The paper describes algorithms (Squint and Meta Grad) and their properties, but it does not include pseudocode or an algorithm block.
Open Source Code No The paper does not provide any links to open-source code or state that code is available.
Open Datasets No The paper discusses theoretical settings involving data and distributions (e.g., "i.i.d. losses drawn from a distribution"), but it does not specify any particular dataset, nor does it provide information about its public availability or access.
Dataset Splits No The paper does not mention training, validation, or test dataset splits. It focuses on theoretical guarantees.
Hardware Specification No The paper does not mention any specific hardware specifications used for experiments.
Software Dependencies No The paper does not specify any software dependencies or version numbers.
Experiment Setup No The paper does not describe any experimental setup details such as hyperparameters or training configurations, as it is a theoretical work.