Lower Bounds for Smooth Nonconvex Finite-Sum Optimization

Authors: Dongruo Zhou, Quanquan Gu

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we study the lower bounds for smooth nonconvex finite-sum optimization, where the objective function is the average of n nonconvex component functions. We prove tight lower bounds for the complexity of finding -suboptimal point and -approximate stationary point in different settings, for a wide regime of the smallest eigenvalue of the Hessian of the objective function (or each component function).
Researcher Affiliation Academia Department of Computer Science, University of California, Los Angeles. Correspondence to: Quanquan Gu <qgu@cs.ucla.edu>.
Pseudocode No The paper is theoretical and focuses on mathematical proofs and lower bounds. It does not include any pseudocode or algorithm blocks.
Open Source Code No The paper is theoretical and does not present a new method with associated source code. Therefore, no information about open-source code for a new methodology is provided.
Open Datasets No The paper is theoretical and does not involve the use of datasets for training or evaluation. Therefore, no information about datasets is provided.
Dataset Splits No The paper is theoretical and does not involve the use of datasets or their splits for experimental validation. Therefore, no information about validation splits is provided.
Hardware Specification No The paper is theoretical and does not involve running experiments that would require specific hardware. Therefore, no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not involve running experiments that would require specific software dependencies with version numbers. Therefore, no software dependencies are mentioned.
Experiment Setup No The paper is theoretical and does not describe experiments with specific setups, hyperparameters, or training configurations. Therefore, no experiment setup details are provided.