paper-with-me

Papers

Mining Robust Default Configurations for Resource-constrained AutoML

2022-02-20 · Moe Kayali, Chi Wang

Automatic machine learning (AutoML) is a key enabler of the mass deployment of the next generation of machine learning systems. A key desideratum for future ML systems is the automatic selection of models and hyperparameters. We present a novel method of selecting performant configurations for a given task by performing offline autoML and mining over a diverse set of tasks. By mining the training tasks, we can select a compact portfolio of configurations that perform well over a wide variety of tasks, as well as learn a strategy to select portfolio configurations for yet-unseen tasks. The algorithm runs in a zero-shot manner, that is without training any models online except the chosen one. In a compute- or time-constrained setting, this virtually instant selection is highly performant. Further, we show that our approach is effective for warm-starting existing autoML platforms. In both settings, we demonstrate an improvement on the state-of-the-art by testing over 62 classification and regression datasets. We also demonstrate the utility of recommending data-dependent default configurations that outperform widely used hand-crafted defaults.

📄 PDF Abstract BibTeX arXiv:2202.09927

Code (0)

등록된 구현이 없습니다.

Tasks

AutoMLBIG-bench Machine Learning

Similar Papers 제목 키워드 기반

AutoSlim: Towards One-Shot Architecture Search for Channel Numbers

2019-03-27 · ICLR 2020 1 · Jiahui Yu, Thomas Huang

We study how to set channel numbers in a neural network to achieve better accuracy under constrained resources (e.g., FLOPs, latency, memory footprint or model size). A simple and one-shot solution, named AutoSlim, is pr…

Neural Architecture SearchReinforcement Learning

The Potential of AutoML for Recommender Systems

2024-02-06 · Tobias Vente, Joeran Beel

Automated Machine Learning (AutoML) has greatly advanced applications of Machine Learning (ML) including model compression, machine translation, and computer vision. Recommender Systems (RecSys) can be seen as an applica…

AutoMLMachine TranslationModel CompressionRecommendation Systems

FLAML: A Fast and Lightweight AutoML Library

2019-11-12 · Chi Wang, Qingyun Wu, Markus Weimer, Erkang Zhu

We study the problem of using low computational cost to automate the choices of learners and hyperparameters for an ad-hoc training dataset and error metric, by conducting trials of different configurations on the given …

AutoMLHyperparameter Optimization

Leveraging AutoML for Sustainable Deep Learning: A Multi-Objective HPO Approach on Deep Shift Neural Networks

2026-06-22 · Leona Hennig, Marius Lindauer arxiv

Deep Learning (DL) has advanced various fields by extracting complex patterns from large datasets. However, the computational demands of DL models pose environmental and resource challenges. Deep Shift Neural Networks (D…

Hyperparameter OptimizationImage Classification

Predicting Mortgage Default with Machine Learning: AutoML, Class Imbalance, and Leakage Control

2026-01-27 · Xianghong Hu, Tianning Xu, Ying Chen, Shuai Wang arxiv

Mortgage default prediction is a core task in financial risk management, and machine learning models are increasingly used to estimate default probabilities and provide interpretable signals for downstream decisions. In …