On Empirical Risk Minimization with Dependent and Heavy-Tailed Data

Authors: Abhishek Roy, Krishnakumar Balasubramanian, Murat A. Erdogdu

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this work, we establish risk bounds for the Empirical Risk Minimization (ERM) with both dependent and heavy-tailed data-generating processes. We do so by extending the seminal works [Men15, Men18] on the analysis of ERM with heavy-tailed but independent and identically distributed observations, to the strictly stationary exponentially β-mixing case. Our analysis is based on explicitly controlling the multiplier process arising from the interaction between the noise and the function evaluations on inputs.
Researcher Affiliation Academia Department of Statistics, University of California, Davis.abroy@ucdavis.edu. Research of this author was supported in part by NSF TRIPODS grant CCF-1934568 Department of Statistics, University of California, Davis. kbala@ucdavis.edu. Research of this author was supported in part by UC Davis Ce DAR (Center for Data Science and Artificial Intelligence Research) Innovative Data Science Seed Funding Program. Department of Computer Science and Department of Statistical Sciences at the University of Toronto, and Vector Institute. erdogdu@cs.toronto.edu.
Pseudocode No The paper does not contain any pseudocode or explicitly labeled algorithm blocks. It focuses on mathematical proofs and theoretical derivations.
Open Source Code No The paper does not provide any statements about releasing open-source code or links to a code repository for the methodology described.
Open Datasets No The paper is theoretical and does not involve empirical experiments with datasets. It does not mention using any publicly available or open datasets for training, nor does it provide any access information for datasets.
Dataset Splits No The paper is theoretical and does not describe empirical experiments involving dataset splits (training, validation, or test).
Hardware Specification No The paper is theoretical and does not describe empirical experiments, thus no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not describe empirical experiments, thus no software dependencies with version numbers are mentioned.
Experiment Setup No The paper is theoretical and does not describe empirical experiments, thus no specific experimental setup details or hyperparameters are provided.