JSAI2024

Presentation information

General Session

General Session » GS-2 Machine learning

[4D1-GS-2] Machine learning: Uncertainty / Information visualization

Fri. May 31, 2024 9:00 AM - 10:40 AM Room D (Temporary room 2)

座長:山田 聡(NEC)

10:20 AM - 10:40 AM

[4D1-GS-2-05] Enhanced Accuracy Estimation Method of Models in Production to Accelerate MLOps

〇Ryuta Matsuno1, Keita Sakuma1, Masakazu Hirokawa1, Yoshio Kameda1 (1. NEC Corporation)

Keywords:MLOps, Accuracy Estimation, Machine Learning

In MLOps, it is essential to estimate the performance of prediction models in production, especially when the target labels are not immediately available.
Existing methods utilize ``check'' models, which check the predictions of the prediction model, trained with the conventional cross-entropy loss.
This study presents a novel method to estimate accuracy using a check model based on our proposed GBCE loss, which strictly upper bounds the accuracy estimation error.
We analyze the generalization error bounds of both the proposed and the cross-entropy-based methods, thereby demonstrating the theoretical superiority of our method.
Through numerical experiments with multiple real-world data sets, we confirm the effectiveness of our proposed method, showing up to 56.3% reduction in accuracy estimation error.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password