paper-with-me

Papers

Learning from Non-Random Data in Hilbert Spaces: An Optimal Recovery Perspective

2020-06-05 · Simon Foucart, Chunyang Liao, Shahin Shahrampour, Yinsong Wang

The notion of generalization in classical Statistical Learning is often attached to the postulate that data points are independent and identically distributed (IID) random variables. While relevant in many applications, this postulate may not hold in general, encouraging the development of learning frameworks that are robust to non-IID data. In this work, we consider the regression problem from an Optimal Recovery perspective. Relying on a model assumption comparable to choosing a hypothesis class, a learner aims at minimizing the worst-case error, without recourse to any probabilistic assumption on the data. We first develop a semidefinite program for calculating the worst-case error of any recovery map in finite-dimensional Hilbert spaces. Then, for any Hilbert space, we show that Optimal Recovery provides a formula which is user-friendly from an algorithmic point-of-view, as long as the hypothesis class is linear. Interestingly, this formula coincides with kernel ridgeless regression in some cases, proving that minimizing the average error and worst-case error can yield the same solution. We provide numerical experiments in support of our theoretical findings.

📄 PDF Abstract BibTeX arXiv:2006.03706

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Optimal Recovery from Inaccurate Data in Hilbert Spaces: Regularize, but what of the Parameter?

2021-11-04 · 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 made on the functions to be learned. Wor…

valid

Infinite dimensional generative sensing

2026-03-03 · Paolo Angella, Vito Paolo Pastore, Matteo Santacesaria arxiv

Deep generative models have become a standard for modeling priors for inverse problems, going beyond classical sparsity-based methods. However, existing theoretical guarantees are mostly confined to finite-dimensional ve…

Optimal deep learning of holomorphic operators between Banach spaces

2024-06-20 · Ben Adcock, Nick Dexter, Sebastian Moraga

Operator learning problems arise in many key areas of scientific computing where Partial Differential Equations (PDEs) are used to model physical systems. In such scenarios, the operators map between Banach or Hilbert sp…

Deep LearningGeneralization BoundsOperator learning

Random-Effects Algorithm for Random Objects in Metric Spaces

2026-05-04 · Marcos Matabuena, Mateo Cámara arxiv

Across many scientific disciplines, multiple observations are collected from the same experimental units, and in modern datasets these observations often arise as non-Euclidean random objects. In such settings, the incor…

Decentralized Online Learning for Random Inverse Problems Over Graphs

2023-03-20 · Tao Li, Xiwei Zhang, Yan Chen

We propose a decentralized online learning algorithm for distributed random inverse problems over network graphs with online measurements, and unifies the distributed parameter estimation in Hilbert spaces and the least …

parameter estimation