MAS is proposed as a new parameterization for CCIFs in TPPs using distinct interpolation and extrapolation spline components to overcome convexity, saturation, and modeling requirement issues of MNNs.
Fully neural network based model for general temporal point processes,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Efficient Temporal Point Processes via Monotone Alternating Splines
MAS is proposed as a new parameterization for CCIFs in TPPs using distinct interpolation and extrapolation spline components to overcome convexity, saturation, and modeling requirement issues of MNNs.