Approximation-Generalization Trade-offs under (Approximate) Group Equivariance

Authors: Mircea Petrache, Shubhendu Trivedi

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we conduct a formal unified investigation of these intuitions. To begin, we present general quantitative bounds that demonstrate how models capturing task-specific symmetries lead to improved generalization.
Researcher Affiliation Academia UC Chile, Fac. de Matemáticas, & Inst. de Ingeniería Matematica y Computacional, Av. Vicuña Mackenna 4860, Santiago, 6904441, Chile. mpetrache@mat.uc.cl. shubhendu@csail.mit.edu.
Pseudocode No The paper contains mathematical derivations and proofs but does not include any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper is theoretical and focuses on mathematical derivations; it does not mention releasing any open-source code for the described methodology or provide links to code repositories.
Open Datasets No The paper is theoretical and does not conduct experiments with specific datasets. While it discusses data distributions, it does not refer to any publicly available or open datasets by name, link, or citation.
Dataset Splits No The paper is theoretical and does not involve empirical experiments with dataset splits. Therefore, no information regarding training, validation, or test dataset splits is provided.
Hardware Specification No The paper is purely theoretical and does not describe any computational experiments or specify the hardware used to perform any analyses or derivations.
Software Dependencies No The paper is theoretical and does not describe computational experiments that would require a list of specific software dependencies with version numbers for reproducibility.
Experiment Setup No The paper is theoretical and does not involve empirical experiments. Therefore, it does not provide details about experimental setup, hyperparameters, or system-level training settings.