On Adaptivity in Information-Constrained Online Learning

Authors: Siddharth Mitra, Aditya Gopalan5199-5206

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We study how to adapt to smoothly-varying ( easy ) environments in well-known online learning problems where acquiring information is expensive. For the problem of label efficient prediction, which is a budgeted version of prediction with expert advice, we present an online algorithm whose regret depends optimally on the number of labels allowed and Q (the quadratic variation of the losses of the best action in hindsight), along with a parameter-free counterpart whose regret depends optimally on Q (the quadratic variation of the losses of all the actions).
Researcher Affiliation Academia Siddharth Mitra,1 Aditya Gopalan2 1Chennai Mathematical Institute, smitra@cmi.ac.in 2Indian Institute of Science, aditya@iisc.ac.in
Pseudocode Yes Algorithm 1 RESERVOIR SAMPLING, Algorithm 2 ADAPTIVE LABEL EFFICIENT PREDICTION, Algorithm 3 PARAMETER FREE ADAPTIVE LABEL EFFICIENT PREDICTION
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository.
Open Datasets No The paper is theoretical and does not conduct experiments on specific datasets. It discusses 'loss vectors' as part of the problem setup, but these are conceptual and not references to publicly available data.
Dataset Splits No The paper is theoretical and does not discuss empirical dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for experiments.
Software Dependencies No The paper is theoretical and does not list any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with hyperparameters or training settings.