The Power of Adaptivity in Identifying Statistical Alternatives

Authors: Kevin G. Jamieson, Daniel Haas, Benjamin Recht

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

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper studies the trade-off between two different kinds of pure exploration: breadth versus depth. We focus on the most biased coin problem, asking how many total coin flips are required to identify a heavy coin from an infinite bag containing both heavy coins with mean µ1 ∈ (0, 1), and light" coins with mean µ0 ∈ (0, 1), where heavy coins are drawn from the bag with proportion λ ∈ (0, 1/2).
Researcher Affiliation Academia Kevin Jamieson, Daniel Haas, Ben Recht University of California, Berkeley Berkeley, CA 94720 {kjamieson,dhaas,brecht}@eecs.berkeley.edu
Pseudocode Yes Algorithm 1 The most biased coin problem definition. Algorithm 2 Adaptive strategy for heavy distribution identification with inputs µ0, 0, δ Algorithm 3 Adaptive strategy for heavy distribution identification with unknown parameters
Open Source Code No The paper does not contain any statement or link indicating that source code for the described methodology is publicly available.
Open Datasets No The paper is theoretical and does not describe experiments run on datasets, thus it does not mention publicly available training datasets.
Dataset Splits No The paper is theoretical and does not describe experiments run on datasets, thus it does not provide details on training, validation, or test splits.
Hardware Specification No The paper is theoretical and does not describe any experiments that would require specific hardware specifications.
Software Dependencies No The paper is theoretical and does not describe any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with hyperparameters or system-level training settings.