Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Fast Rates in Statistical and Online Learning
Authors: Tim van Erven, Peter D. Grünwald, Nishant A. Mehta, Mark D. Reid, Robert C. Williamson
JMLR 2015 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We show that most of these conditions are special cases of a single, unifying condition, that comes in two forms: the central condition for proper learning algorithms that always output a hypothesis in the given model, and stochastic mixability for online algorithms that may make predictions outside of the model. We show that under surprisingly weak assumptions both conditions are, in a certain sense, equivalent. The central condition has a re-interpretation in terms of convexity of a set of pseudoprobabilities, linking it to density estimation under misspecification. For bounded losses, we show how the central condition enables a direct proof of fast rates and we prove its equivalence to the Bernstein condition, itself a generalization of the Tsybakov margin condition, both of which have played a central role in obtaining fast rates in statistical learning. |
| Researcher Affiliation | Academia | Tim van Erven EMAIL Mathematisch Instituut, Universiteit Leiden Leiden, 2300 RA, The Netherlands Peter D. Gr unwald EMAIL Centrum voor Wiskunde en Informatica and MI, Universiteit Leiden Amsterdam, NL-1090 GB, The Netherlands Nishant A. Mehta EMAIL Centrum voor Wiskunde en Informatica Amsterdam, NL-1090 GB, The Netherlands Mark D. Reid EMAIL Robert C. Williamson EMAIL Australian National University and NICTA Canberra, ACT 2601 Australia. |
| Pseudocode | No | The paper does not contain any sections or blocks explicitly labeled as 'Pseudocode' or 'Algorithm'. The description of methods is provided through mathematical formulations and textual explanations. |
| Open Source Code | No | The paper does not contain any explicit statements about the release of source code, nor does it provide any links to code repositories. |
| Open Datasets | No | The paper focuses on theoretical concepts, conditions, and proofs in statistical and online learning. It uses theoretical examples (e.g., 'Regression, Classification', 'Density estimation', 'Bernoulli, 0/1-loss') to illustrate concepts but does not conduct empirical experiments on specific, named public datasets, nor does it provide access information for any datasets. |
| Dataset Splits | No | The paper is theoretical and does not involve empirical experiments with datasets. Therefore, there is no discussion or provision of dataset splits (e.g., training, test, validation splits). |
| Hardware Specification | No | The paper is theoretical and does not describe any experiments that would require specific hardware. Consequently, no hardware specifications are mentioned. |
| Software Dependencies | No | The paper is theoretical and does not describe any experiments that would require specific software or libraries. Therefore, no software dependencies with version numbers are listed. |
| Experiment Setup | No | The paper is purely theoretical, focusing on mathematical conditions and proofs in learning theory. It does not describe any practical experiments, and therefore, no experimental setup details, hyperparameters, or training configurations are provided. |