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.
Title resolution pending
9 Pith papers cite this work, alongside 1,592 external citations. Polarity classification is still indexing.
representative citing papers
The GROW value for bounded e-variables equals the minimal relative entropy between weak-* closed convex hulls of arbitrary composite null and alternative sets.
Nonsmooth extension of the Brezzi-Rappaz-Raviart approximation theorem via metric regularity, applied to quasi-optimal finite-element error estimates for viscous Hamilton-Jacobi equations and second-order mean field games.
Defines resilience evaluation D^ρ π as the L1-limit of scaled dynamic risk measure applied to process increments, and derives its dual representation as worst-case conditional expectation of an effective drift when ρ arises from BSDEs with Lipschitz or quadratic drivers.
Spectral asymptotics for negative fractional powers of hypoelliptic operators on graded Lie groups generalize Birman-Solomyak and imply a version of Connes' integration formula.
Probabilistic programs of thought let LLMs produce many program variants from one generation by building a compact probabilistic representation of the token distribution.
Establishes root-n consistency and asymptotic normality for the plug-in estimator of E[F_Y^{-1} ∘ F_Z(X)] under weaker conditions allowing unbounded support, plus a consistent variance estimator.
Equivalences are proven for diam-mean and mean equicontinuity between a system and its measure-induced version, while hyperspace versions require separate conditions with explicit counterexamples.
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.
-
Strong duality for the GROW criterion
The GROW value for bounded e-variables equals the minimal relative entropy between weak-* closed convex hulls of arbitrary composite null and alternative sets.
-
A nonsmooth extension of the Brezzi-Rappaz-Raviart approximation theorem via metric regularity techniques and applications to nonlinear PDEs
Nonsmooth extension of the Brezzi-Rappaz-Raviart approximation theorem via metric regularity, applied to quasi-optimal finite-element error estimates for viscous Hamilton-Jacobi equations and second-order mean field games.
-
Financial Resilience Evaluation: From Conditional Expectations to Dynamic Convex Risk Measures
Defines resilience evaluation D^ρ π as the L1-limit of scaled dynamic risk measure applied to process increments, and derives its dual representation as worst-case conditional expectation of an effective drift when ρ arises from BSDEs with Lipschitz or quadratic drivers.
-
Weyl asymptotic formulas in the nilpotent Lie group setting
Spectral asymptotics for negative fractional powers of hypoelliptic operators on graded Lie groups generalize Birman-Solomyak and imply a version of Connes' integration formula.
-
Probabilistic Programs of Thought
Probabilistic programs of thought let LLMs produce many program variants from one generation by building a compact probabilistic representation of the token distribution.
-
Asymptotic Properties of Empirical Quantile-Based Estimators
Establishes root-n consistency and asymptotic normality for the plug-in estimator of E[F_Y^{-1} ∘ F_Z(X)] under weaker conditions allowing unbounded support, plus a consistent variance estimator.
-
Mean Equicontinuity and Related Properties in Hyperspace and Measure Dynamics
Equivalences are proven for diam-mean and mean equicontinuity between a system and its measure-induced version, while hyperspace versions require separate conditions with explicit counterexamples.
- Conditional entropy realization and approximation by uniquely ergodic measures