Function graph transformers use graph measures to provide a measure-theoretic framework where standard transformer components universally approximate operators between function spaces while preserving single-valued function outputs.
(2020).Probability Theory
4 Pith papers cite this work, alongside 68 external citations. Polarity classification is still indexing.
4
Pith papers citing it
68
external citations · OpenAlex
verdicts
UNVERDICTED 4representative citing papers
Products of finite-dimensional quantum channels asymptotically forget input states under decay of the centered trace-Dobrushin coefficient, yielding unique replacement channels and convergence for deterministic and random inhomogeneous MPS.
A spectral generalized covariance measure enables conditional independence testing on non-Euclidean data with uniform bootstrap validity and power guarantees under doubly robust conditions.
Boosting trees test necessary conditions for calibration and auto-calibration of regression models, shown powerful on a large insurance dataset.
citing papers explorer
-
Function graph transformers universally approximate operators between function spaces
Function graph transformers use graph measures to provide a measure-theoretic framework where standard transformer components universally approximate operators between function spaces while preserving single-valued function outputs.
-
Asymptotic Replacement for Quantum Channel Products with Applications to Inhomogeneous Matrix Product States
Products of finite-dimensional quantum channels asymptotically forget input states under decay of the centered trace-Dobrushin coefficient, yielding unique replacement channels and convergence for deterministic and random inhomogeneous MPS.
-
Testing Conditional Independence via the Spectral Generalized Covariance Measure: Beyond Euclidean Data
A spectral generalized covariance measure enables conditional independence testing on non-Euclidean data with uniform bootstrap validity and power guarantees under doubly robust conditions.
-
Assessing model calibration with boosting trees
Boosting trees test necessary conditions for calibration and auto-calibration of regression models, shown powerful on a large insurance dataset.