From Stochastic Mixability to Fast Rates

Authors: Nishant A Mehta, Robert C. Williamson

NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical The present paper presents a direct proof of fast rates for ERM in terms of stochastic mixability of (ℓ, F, P), and in so doing provides new insight into the fast-rates phenomenon. The proof exploits an old result of Kemperman on the solution to the general moment problem.
Researcher Affiliation Academia Nishant A. Mehta Research School of Computer Science Australian National University nishant.mehta@anu.edu.au Robert C. Williamson Research School of Computer Science Australian National University and NICTA bob.williamson@anu.edu.au
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link indicating that source code for the described methodology is publicly available.
Open Datasets No This is a theoretical paper focusing on proofs and mathematical concepts, and as such, it does not involve the use of empirical datasets for training.
Dataset Splits No This is a theoretical paper that does not describe empirical experiments, thus no training/validation/test dataset splits are discussed.
Hardware Specification No This is a theoretical paper and does not involve experimental runs, thus no hardware specifications are provided.
Software Dependencies No This is a theoretical paper and does not involve experimental implementations, thus no software dependencies with version numbers are specified.
Experiment Setup No This is a theoretical paper and does not describe any empirical experiments or their setup, thus no hyperparameter values or training configurations are provided.