Banach-valued random feature models, including random single-hidden-layer networks, universally approximate elements of Bochner spaces over non-compact domains with explicit approximation rates.
Global universal approximation of functional input maps on weighted spaces
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Bayesian neural SDE calibration produces posterior mixtures that deliver robust bounds on implied volatility by jointly using historical and option data, learning the historical-to-risk-neutral measure change, and sampling via Langevin dynamics.
citing papers explorer
-
Universal approximation property of Banach space-valued random feature models including random neural networks
Banach-valued random feature models, including random single-hidden-layer networks, universally approximate elements of Bochner spaces over non-compact domains with explicit approximation rates.
-
Robust financial calibration: a Bayesian approach for neural SDEs
Bayesian neural SDE calibration produces posterior mixtures that deliver robust bounds on implied volatility by jointly using historical and option data, learning the historical-to-risk-neutral measure change, and sampling via Langevin dynamics.