MLCommons Optimizer Benchmark Suite
收藏arXiv2025-09-30 收录
下载链接:
https://mlcommons.org/en/benchmarks/
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是一个基准测试套件,用于评估包括VeLO在内的各种优化器在训练和验证损失最小化方面的性能表现。该基准测试涵盖了多种机器学习任务,并允许与多种优化器进行比较,以评估它们的表现优劣。该任务的目的是进行优化器性能对比。
This dataset constitutes a benchmark suite for evaluating the performance of various optimizers—including VeLO—in minimizing training and validation losses. This benchmark encompasses a wide range of machine learning tasks and enables comparative assessment across multiple optimizers to gauge their respective performance. The core objective of this benchmark is to conduct optimizer performance comparisons.
提供机构:
MLCommons



