arXiv Open Access 2022

Time Series Prediction under Distribution Shift using Differentiable Forgetting

Stefanos Bennett Jase Clarkson

Lihat Sumber

Abstrak

Time series prediction is often complicated by distribution shift which demands adaptive models to accommodate time-varying distributions. We frame time series prediction under distribution shift as a weighted empirical risk minimisation problem. The weighting of previous observations in the empirical risk is determined by a forgetting mechanism which controls the trade-off between the relevancy and effective sample size that is used for the estimation of the predictive model. In contrast to previous work, we propose a gradient-based learning method for the parameters of the forgetting mechanism. This speeds up optimisation and therefore allows more expressive forgetting mechanisms.

Topik & Kata Kunci

cs.LG q-fin.ST

Penulis (2)

Stefanos Bennett

Jase Clarkson

Format Sitasi

APA MLA BibTeX

Bennett, S., Clarkson, J. (2022). Time Series Prediction under Distribution Shift using Differentiable Forgetting. https://arxiv.org/abs/2207.11486

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2022
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓