Newton's recursive mixture estimator is a discrete gradient flow on the Fisher-Rao manifold of probability measures.
Reflected solutions of backward SDE's, and related obstacle problems for PDE's
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
Proves sharp Gaussian isoperimetric inequality for conjugate heat-kernel measures along Ricci flow via monotonicity formula, with consequences for concentration estimates, log-Sobolev inequalities, and related results.
Uniform analyticity of local observables is proved in FK-percolation under mixing conditions, yielding analyticity of Potts/Ising magnetization in the supercritical regime and susceptibility in the subcritical regime.
Constructs canonical p-energy measures for strongly local p-energy forms, proves chain/Leibniz rules and uniqueness, and shows coincidence with Korevaar-Schoen-type measures via a p-analogue of Le Jan's domination principle.
The paper establishes existence and uniqueness for generalized mean-reflected McKean-Vlasov BSDEs via stability estimates for uniqueness and a penalization-plus-smooth-approximation argument for existence.
Bayesian nonparametric mixtures of Poisson and normal regressions using DP and PY priors are fitted via MCMC to predict claims frequency and severity, with an illustration on French motor insurance data.
citing papers explorer
-
Newton's Algorithm as a Gradient Flow: A Geometric Framework for Recursive Mixture Estimation
Newton's recursive mixture estimator is a discrete gradient flow on the Fisher-Rao manifold of probability measures.
-
Sharp Gaussian Isoperimetry along a Ricci Flow
Proves sharp Gaussian isoperimetric inequality for conjugate heat-kernel measures along Ricci flow via monotonicity formula, with consequences for concentration estimates, log-Sobolev inequalities, and related results.
-
Uniform analyticity of local observables in FK-percolation and analyticity of the Ising spontaneous magnetisation
Uniform analyticity of local observables is proved in FK-percolation under mixing conditions, yielding analyticity of Potts/Ising magnetization in the supercritical regime and susceptibility in the subcritical regime.
-
Construction of $p$-energy measures associated with strongly local $p$-energy forms
Constructs canonical p-energy measures for strongly local p-energy forms, proves chain/Leibniz rules and uniqueness, and shows coincidence with Korevaar-Schoen-type measures via a p-analogue of Le Jan's domination principle.
-
Well-Posedness of Generalized Mean-Reflected McKean-Vlasov Backward Stochastic Differential Equations
The paper establishes existence and uniqueness for generalized mean-reflected McKean-Vlasov BSDEs via stability estimates for uniqueness and a penalization-plus-smooth-approximation argument for existence.
-
Modeling Insurance Claims using Bayesian Nonparametric Regression
Bayesian nonparametric mixtures of Poisson and normal regressions using DP and PY priors are fitted via MCMC to predict claims frequency and severity, with an illustration on French motor insurance data.