A flow-matching model with a neural-operator velocity field is proposed to forecast time series by transporting distributions over continuous functions, reporting top average rank on eight benchmarks.
Absolute continuity of Brownian bridges under certain gauge transformations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We prove absolute continuity of Gaussian measures associated to complex Brownian bridges under certain gauge transformations. As an application we prove that the invariant measure for the periodic derivative nonlinear Schr\"odinger equation obtained by Nahmod, Oh, Rey-Bellet and Staffilani in [20], and with respect to which they proved almost surely global well-posedness, coincides with the weighted Wiener measure constructed by Thomann and Tzvetkov [24]. Thus, in particular we prove the invariance of the measure constructed in [24].
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
NeuTSFlow: Modeling Continuous Functions Behind Time Series Forecasting
A flow-matching model with a neural-operator velocity field is proposed to forecast time series by transporting distributions over continuous functions, reporting top average rank on eight benchmarks.