paper-with-me

Papers

Fast Optimizer Benchmark

2024-06-26 · Simon Blauth, Tobias Bürger, Zacharias Häringer, Jörg Franke, Frank Hutter

In this paper, we present the Fast Optimizer Benchmark (FOB), a tool designed for evaluating deep learning optimizers during their development. The benchmark supports tasks from multiple domains such as computer vision, natural language processing, and graph learning. The focus is on convenient usage, featuring human-readable YAML configurations, SLURM integration, and plotting utilities. FOB can be used together with existing hyperparameter optimization (HPO) tools as it handles training and resuming of runs. The modular design enables integration into custom pipelines, using it simply as a collection of tasks. We showcase an optimizer comparison as a usage example of our tool. FOB can be found on GitHub: https://github.com/automl/FOB.

📄 PDF Abstract BibTeX arXiv:2406.18701

Code (1)

automl/fob 공식 구현 pytorch

Tasks

AutoMLGraph LearningHyperparameter Optimization

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Is Scaling Learned Optimizers Worth It? Evaluating The Value of VeLO's 4000 TPU Months

2023-10-27 · Fady Rezk, Antreas Antoniou, Henry Gouk, Timothy Hospedales

We analyze VeLO (versatile learned optimizer), the largest scale attempt to train a general purpose "foundational" optimizer to date. VeLO was trained on thousands of machine learning tasks using over 4000 TPU months wit…

Radiotherapy Dosimetry: A Review on Open-Source Optimizer

2023-05-29 · Paul Dubois

Radiotherapy dosimetry plays a crucial role in optimizing treatment plans for cancer patients. In this study, we investigate the performance of a dozen standard state-of-the-art open-source optimizers for radiotherapy do…

AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization

2026-03-24 · Jiehao Wu, Zixiao Huang, Wenhao Li, Chuyun Shen 외 arxiv

Optimizing AscendC (Ascend C) operators for Ascend NPUs is difficult for two reasons. First, unlike CUDA, the ecosystem offers few public kernels to learn from. Second, performance depends on a coupled two-part implement…

A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes

2021-02-12 · NeurIPS 2021 12 · Zachary Nado, Justin M. Gilmer, Christopher J. Shallue, Rohan Anil 외

Recently the LARS and LAMB optimizers have been proposed for training neural networks faster using large batch sizes. LARS and LAMB add layer-wise normalization to the update rules of Heavy-ball momentum and Adam, respec…

Image ClassificationOpen-Ended Question AnsweringQuestion AnsweringStochastic Optimization

Effective Quantization of Muon Optimizer States

2025-09-27 · Aman Gupta, Rafael Celente, Abhishek Shivanna, D. T. Braithwaite 외 arxiv

The Muon optimizer, based on matrix orthogonalization, has recently shown faster convergence and better computational efficiency over AdamW in LLM pre-training. However, the memory overhead of maintaining high-precision …

Computational EfficiencyInstruction Following