
TL;DR
The paper proves that no computable randomized sampling method can generate arbitrarily large samples free of outliers for a given computable probability measure over natural numbers or infinite binary sequences.
Contribution
It establishes a fundamental limitation on computable sampling methods in avoiding outliers in large samples.
Findings
No computable randomized method can produce arbitrarily large outlier-free samples.
The result applies to measures over natural numbers and infinite binary sequences.
It highlights inherent constraints in algorithmic sampling processes.
Abstract
Given a computable probability measure P over natural numbers or infinite binary sequences, there is no computable, randomized method that can produce an arbitrarily large sample such that none of its members are outliers of P.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
