Exploring the Complexity of Deep Neural Networks through Functional Equivalence

Authors: Guohao Shen

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Leveraging the equivalence property, we present a novel bound on the covering number for deep neural networks, which reveals that the complexity of neural networks can be reduced. Additionally, we demonstrate that functional equivalence benefits optimization, as overparameterized networks tend to be easier to train since increasing network width leads to a diminishing volume of the effective parameter space. These findings can offer valuable insights into the phenomenon of overparameterization and have implications for understanding generalization and optimization in deep learning.
Researcher Affiliation Academia 1Department of Applied Mathematics, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China. Correspondence to: Guohao Shen <guohao.shen@polyu.edu.hk>.
Pseudocode No The paper focuses on theoretical analysis and mathematical proofs, and does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described. It is a theoretical paper primarily focused on mathematical derivations and analysis.
Open Datasets No The paper is theoretical and does not involve empirical evaluation on datasets, so no dataset information or access is provided.
Dataset Splits No The paper is theoretical and does not involve empirical evaluation or dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not report on experimental hardware specifications.
Software Dependencies No The paper is theoretical and does not specify any software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe specific experimental setup details, hyperparameters, or training configurations.