# Self-supervised learning for fast and scalable time series hyper-parameter tuning

arXiv: https://arxiv.org/abs/2102.05740 · HTML: https://mlsanity.com/paper/2102.05740/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 21 references that are in the map.
- First posted on arXiv 10 Feb 2021.

## Builds on (most cited first, 5 of 5)

- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [S4L: Self-Supervised Semi-Supervised Learning](https://mlsanity.com/paper/1905.03670/) (2019)
- [LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection](https://mlsanity.com/paper/1607.00148/) (2016)

## Built on by (most cited first, 3 of 3)

- [Unsupervised Model Selection for Time-series Anomaly Detection](https://mlsanity.com/paper/2210.01078/) (2022)
- [MOSPAT: AutoML based Model Selection and Parameter Tuning for Time Series Anomaly Detection](https://mlsanity.com/paper/2205.11755/) (2022)
- [Refining the Optimization Target for Automatic Univariate Time Series Anomaly Detection in Monitoring Services](https://mlsanity.com/paper/2307.10653/) (2023)

## Abstract (arXiv)

Hyper-parameters of time series models play an important role in time series analysis. Slight differences in hyper-parameters might lead to very different forecast results for a given model, and therefore, selecting good hyper-parameter values is indispensable. Most of the existing generic hyper-parameter tuning methods, such as Grid Search, Random Search, Bayesian Optimal Search, are based on one key component - search, and thus they are computationally expensive and cannot be applied to fast and scalable time-series hyper-parameter tuning (HPT). We propose a self-supervised learning framework for HPT (SSL-HPT), which uses time series features as inputs and produces optimal hyper-parameters. SSL-HPT algorithm is 6-20x faster at getting hyper-parameters compared to other search based algorithms while producing comparable accurate forecasting results in various applications.