# Conjugate-gradient-based Adam for stochastic optimization and its application to deep learning

Source: [Conjugate-gradient-based Adam for stochastic optimization and its application to deep learning](<https://www.sota2.com/research/paper/68fa56bf1e209131ce99f331>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T14:19:43.402Z

Authors: Yu Kobayashi, Hideaki Iiduka

Published: 2020-02-29T10:34:30.000Z

## Abstract

This paper proposes a conjugate-gradient-based Adam algorithm blending Adam with nonlinear conjugate gradient methods and shows its convergence analysis. Numerical experiments on text classification and image classification show that the proposed algorithm can train deep neural network models in fewer epochs than the existing adaptive stochastic optimization algorithms can.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2003.00231>)

[PDF](<https://arxiv.org/pdf/2003.00231.pdf>)