Optimizer Benchmarks
Comprehensive benchmark results from our research paper on backbone-optimizer coupling bias in visual representation learning.
Research Citation Required
All benchmark results are derived from our research paper. Please cite our work when using these results:
"Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning"
arXiv:2410.06373v1Benchmark Suites
CIFAR-100 Benchmark
Top-1 accuracy (%) across 20 backbone architectures with 20 optimizers
Setup: Representative vision backbones with 20 mainstream optimizers. Blue highlights denote top-4 results.
ImageNet Benchmark
Top-1 accuracy (%) across 10 backbone architectures with 20 optimizers
Setup: Representative vision backbones with 20 mainstream optimizers. Blue highlights denote top-4 results.
COCO Benchmark
Object detection and 2D pose estimation on COCO dataset
Setup: Transfer learning to object detection with RetinaNet and 2D pose estimation with TopDown on COCO. Different pre-training settings: 100-epoch (SGD, LARS), 300-epoch (RSB A2, Adan), and 600-epoch (RSB A1).
C4 Benchmark
LLaMA pre-training comparison on C4 dataset (60M-1B parameters)
Setup: LLaMA pre-training on C4 dataset with model sizes from 60M to 1B parameters. Validation perplexity (PPL)↓, GPU memory (Mem.)↓, and optimizer step time (s)↓ are reported. Lower is better for all metrics.
Our Methods (SAC): Purple background indicates our proposed methods.
Want to Contribute Benchmarks?
Help us expand our benchmark suite! Submit your optimization results and contribute to the community knowledge base.