2 papers
math.OC2021
Optimal Recovery from Inaccurate Data in Hilbert Spaces: Regularize, but what of the Parameter?
Simon Foucart, Chunyang Liao
In Optimal Recovery, the task of learning a function from observational data is tackled deterministically by adopting a worst-case perspective tied to an explicit model assumption…
cs.LG2020
Learning from Non-Random Data in Hilbert Spaces: An Optimal Recovery Perspective
Simon Foucart, Chunyang Liao, Shahin Shahrampour +1
The notion of generalization in classical Statistical Learning is often attached to the postulate that data points are independent and identically distributed (IID) random variable…