LGMLDec 16, 2020

Predicting Generalization in Deep Learning via Metric Learning -- PGDL Shared task

arXiv:2012.09117v11 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the problem of understanding and predicting generalization in deep learning models, which is a fundamental challenge for the machine learning community.

This paper describes the 8th place solution for the PGDL competition, which aimed to predict generalization in deep learning models. The solution involved creating simple metrics and finding their optimal combination to predict generalization based on properties of input neural network architectures.

The competition "Predicting Generalization in Deep Learning (PGDL)" aims to provide a platform for rigorous study of generalization of deep learning models and offer insight into the progress of understanding and explaining these models. This report presents the solution that was submitted by the user \emph{smeznar} which achieved the eight place in the competition. In the proposed approach, we create simple metrics and find their best combination with automatic testing on the provided dataset, exploring how combinations of various properties of the input neural network architectures can be used for the prediction of their generalization.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes