Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
livellosegreto.it is one of the many independent Mastodon servers you can use to participate in the fediverse.
Livello Segreto è il social etico che ha rispetto di te e del tuo tempo.

Administered by:

Server stats:

1.2K
active users

livellosegreto.it: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

#timeseries

0 posts0 participants0 posts today
Replied in thread
Public
Valeriy M., PhD, MBA, CQF

#TimeSeries #AI #MachineLearning #Innovation #China #Research #Forecasting #SiliconValley #Academia

arxiv.org/abs/2502.03264

arXiv.orgGeneral Time-series Model for Universal Knowledge Representation of Multivariate Time-Series dataUniversal knowledge representation is a central problem for multivariate time series(MTS) foundation models and yet remains open. This paper investigates this problem from the first principle and it makes four folds of contributions. First, a new empirical finding is revealed: time series with different time granularities (or corresponding frequency resolutions) exhibit distinct joint distributions in the frequency domain. This implies a crucial aspect of learning universal knowledge, one that has been overlooked by previous studies. Second, a novel Fourier knowledge attention mechanism is proposed to enable learning time granularity-aware representations from both the temporal and frequency domains. Third, an autoregressive blank infilling pre-training framework is incorporated to time series analysis for the first time, leading to a generative tasks agnostic pre-training strategy. To this end, we develop the General Time-series Model (GTM), a unified MTS foundation model that addresses the limitation of contemporary time series models, which often require token, pre-training, or model-level customizations for downstream tasks adaption. Fourth, extensive experiments show that GTM outperforms state-of-the-art (SOTA) methods across all generative tasks, including long-term forecasting, anomaly detection, and imputation.
SearchLive feeds
About