Transformers can implement autoregressive least-squares regression in-context on time series, and pretraining on weakly dependent data gives test error decaying as 1 divided by the square root of the number of pretraining series.
Learning from weakly dependent data under dobrushin’s condition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Transformers and Their Roles as Time Series Foundation Models
Transformers can implement autoregressive least-squares regression in-context on time series, and pretraining on weakly dependent data gives test error decaying as 1 divided by the square root of the number of pretraining series.