Online Learning with Abstention

Authors: Corinna Cortes, Giulia DeSalvo, Claudio Gentile, Mehryar Mohri, Scott Yang

ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We further report the results of a series of experiments demonstrating that UCB-GT largely outperforms that extension of UCB-N, as well as other standard baselines.
Researcher Affiliation Collaboration 1Google Research, New York, NY. 2INRIA Lille Nord Europe. 3Courant Institute of Mathematical Sciences, New York, NY. 4D. E. Shaw & Co., New York, NY.
Pseudocode Yes ALGORITHM 1: UCB-NT... ALGORITHM 2: UCB-GT
Open Source Code No The paper does not provide any links to open-source code for the methodology described.
Open Datasets Yes We used the following eight datasets from the UCI data repository: HIGGS, phishing, ijcnn, covtype, eye, skin, cod-rna, and guide. We also used the CIFAR dataset from (Krizhevsky et al., 2009)
Dataset Splits No The paper does not explicitly provide training/validation/test dataset splits. It mentions 'averaged over five random draws of the data'.
Hardware Specification No The paper does not provide specific hardware details used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes The predictors h are hyperplanes centered at the origin whose normal vector in Rd is drawn randomly from the Gaussian distribution, N(0, 1)d, where d is the dimension of the feature space of the dataset. The abstention functions r are concentric annuli around the origin with radii in (0, d 20 . . . , d). For each dataset, we generated a total of K = 2,100 experts and all the algorithms were tested for a total of T = 10,000 rounds. We report these results for c 2 {0.1, 0.2, 0.3}.