paper-with-me

Papers

Tabular Benchmarks for Joint Architecture and Hyperparameter Optimization

2019-05-13 · Aaron Klein, Frank Hutter

Due to the high computational demands executing a rigorous comparison between hyperparameter optimization (HPO) methods is often cumbersome. The goal of this paper is to facilitate a better empirical evaluation of HPO methods by providing benchmarks that are cheap to evaluate, but still represent realistic use cases. We believe these benchmarks provide an easy and efficient way to conduct reproducible experiments for neural hyperparameter search. Our benchmarks consist of a large grid of configurations of a feed forward neural network on four different regression datasets including architectural hyperparameters and hyperparameters concerning the training pipeline. Based on this data, we performed an in-depth analysis to gain a better understanding of the properties of the optimization problem, as well as of the importance of different types of hyperparameters. Second, we exhaustively compared various different state-of-the-art methods from the hyperparameter optimization literature on these benchmarks in terms of performance and robustness.

📄 PDF Abstract BibTeX arXiv:1905.04970

Code (1)

automl/nas_benchmarks 공식 구현

Tasks

Hyperparameter Optimization

Methods 이 논문이 사용한 방법론

HPO In machine learning, a hyperparameter is a parameter whose value is used to control learning process, and HPO is the problem of choosing a set of optimal hyperparameters for a…

Similar Papers 제목 키워드 기반

Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL

2020-06-24 · Lucas Zimmer, Marius Lindauer, Frank Hutter

While early AutoML frameworks focused on optimizing traditional ML pipelines and their hyperparameters, a recent trend in AutoML is to focus on neural architecture search. In this paper, we introduce Auto-PyTorch, which …

AutoMLNeural Architecture Search

Fairer and More Accurate Tabular Models Through NAS

2023-10-18 · Richeek Das, Samuel Dooley

Making models algorithmically fairer in tabular data has been long studied, with techniques typically oriented towards fixes which usually take a neural model with an undesirable outcome and make changes to how the data …

FairnessHyperparameter OptimizationNeural Architecture Search

NAS-HPO-Bench-II: A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameters

2021-10-19 · Yoichi Hirose, Nozomu Yoshinari, Shinichi Shirakawa

The benchmark datasets for neural architecture search (NAS) have been developed to alleviate the computationally expensive evaluation process and ensure a fair comparison. Recent NAS benchmarks only focus on architecture…

4kBenchmarkingNeural Architecture Search

Well-tuned Simple Nets Excel on Tabular Datasets

2021-06-21 · NeurIPS 2021 12 · Arlind Kadra, Marius Lindauer, Frank Hutter, Josif Grabocka

Tabular datasets are the last "unconquered castle" for deep learning, with traditional ML methods like Gradient-Boosted Decision Trees still performing strongly even against recent specialized neural architectures. In th…

Model-based Asynchronous Hyperparameter and Neural Architecture Search

2020-03-24 · Aaron Klein, Louis C. Tiao, Thibaut Lienart, Cedric Archambeau 외

We introduce a model-based asynchronous multi-fidelity method for hyperparameter and neural architecture search that combines the strengths of asynchronous Hyperband and Gaussian process-based Bayesian optimization. At t…

AutoMLBayesian OptimizationHyperparameter Optimizationimage-classification+2