2024-10-09-seng24a.md

title	openreview	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Bi-Level One-Shot Architecture Search for Probabilistic Time Series Forecasting	AaPhnfFQYn	Time series forecasting is ubiquitous in many disciplines. A recent hybrid architecture named predictive Whittle networks (PWNs) tackles this task by employing two distinct modules, a tractable probabilistic model and a neural forecaster, with the former guiding the latter by providing likelihoods about predictions during training. Although PWNs achieve state-of-the-art accuracy, finding the optimal type of probabilistic model and neural forecaster (macro-architecture search) and the architecture of each module (micro-architecture search) of such hybrid models remains difficult and time-consuming. Current one-shot neural architecture search (NAS) methods approach this challenge by focusing on either the micro or the macro aspect, overlooking mutual impact, and could attain the overall optimization only sequentially. To overcome these limitations, we introduce a bi-level one-shot NAS method that optimizes such hybrid architectures simultaneously, leveraging the relationships between the micro and the macro architectural levels. We empirically demonstrate that the hybrid architectures found by our method outperform human-designed and overparameterized ones on various challenging datasets. Furthermore, we unveil insights about underlying connections between architectural choices and temporal features.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	seng24a	0	Bi-Level One-Shot Architecture Search for Probabilistic Time Series Forecasting	10/1	20	10/1-20	10	false	Seng, Jonas and Kalter, Fabian and Yu, Zhongjie and Ventola, Fabrizio and Kersting, Kristian	given family Jonas Seng given family Fabian Kalter given family Zhongjie Yu given family Fabrizio Ventola given family Kristian Kersting	2024-10-09		Proceedings of the Third International Conference on Automated Machine Learning	256	inproceedings	date-parts 2024 10 9	https://raw.githubusercontent.com/mlresearch/v256/main/assets/seng24a/seng24a.pdf