4 problems

0 votes0 replies0 views
Conjecture on handling matrix-normal measurement errors with separable covariance
Let $W$ be a measurement-error matrix following a matrix normal distribution with separable covariance matrix … where $C$ is an $m\times m$ positive semi-definite covariance matrix…
Conjectureopenerrors-in-variables high-dimensional-statistics matrix-normal-distributionsarXiv posted 2 days ago
0 votes0 replies1 view
Qualitative extension of active-learning results to symmetric error models
The paper studies active learning under the Berkson errors-in-variables model, in which an observed feature $W$ is perturbed to $X=W+\delta$ before the oracle returns a label depen…
Conjectureopenactive-learning errors-in-variables statistical-learningarXiv posted 2 days ago
0 votes0 replies0 views
Conjecture on handling matrix-normal measurement errors with separable covariance
Let $W$ be a measurement-error matrix following a matrix normal distribution with separable covariance matrix … where $C$ is an $m\times m$ positive semi-definite covariance matrix…
Conjectureopenerrors-in-variables high-dimensional-statistics matrix-normal-distributionsarXiv posted 2 days ago
0 votes0 replies1 view
Extension of the minimax lower bound to all margin exponents
The paper considers classification with errors in variables, under a noise assumption, and studies estimators of the optimal discriminant set $G_K^{\star}$ over the class…
Conjectureopenclassification errors-in-variables statistical-learning-theoryarXiv posted 2 days ago

4 problems

Conjecture on handling matrix-normal measurement errors with separable covariance

Qualitative extension of active-learning results to symmetric error models

Conjecture on handling matrix-normal measurement errors with separable covariance

Extension of the minimax lower bound to all margin exponents