On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “non-estimability”

General and Estimable Learning Bound Unifying Covariate and Concept Shiftsstat.ML

Unified learning bound for covariate and concept shifts.

problem Generalization under distribution shift in machine learning.

method Support-agnostic definitions of covariate and concept shifts using entropic optimal transport, leading to a unified error bound applicable to various loss functions and label spaces.

result Development of estimators for shifts with concentration guarantees and the DataShifts algorithm for quantifying and estimating the error bound.

learning bound distribution shift covariate shift concept shift estimable

2025-06-15abs ↗pdf ↗

On the estimation of correlation in a binary sequence modelmath.ST

Binary sequence correlation estimation fails but trinary data succeeds.

problem Estimating correlation in binary sequences generated by thresholding a hidden continuous sequence.

method Formal analysis and numerical experiments on likelihood maximization and discretization effects.

result Consistent estimation of correlation is possible with trinary data but not with binary data.

binary sequences correlation estimation phase transition discretization non-estimability

2017-12-27abs ↗pdf ↗

Practicality of generalization guarantees for unsupervised domain adaptation with neural networkscs.LG

New bounds improve generalization for deep neural networks in domain adaptation.

problem Deriving tight generalization guarantees for deep neural networks in domain adaptation.

method Combining data-dependent PAC-Bayes analysis with importance weighting.

result A simple importance weighting extension provides the tightest estimable bound.

domain adaptation unsupervised learning neural networks generalization PAC-Bayes

2023-03-15abs ↗pdf ↗