41 citations · 143 across the 39 of their papers we have counts for
Showing 2017Show all
3 papers · 1 filter
math.ST2017
Finite-sample risk bounds for maximum likelihood estimation with arbitrary penalties
W. D. Brinda, Jason M. Klusowski
The MDL two-part coding provides a finite-sample upper bound on the statistical risk of penalized likelihood estimators over countable models. H…
stat.ML2017★ 3 cited
Estimating the Coefficients of a Mixture of Two Linear Regressions by Expectation Maximization
Jason M. Klusowski, Dana Yang, W. D. Brinda
We give convergence guarantees for estimating the coefficients of a symmetric mixture of two linear regressions by expectation maximization (EM). In particular, we show that the em…
stat.ML2017★ 1 cited
Minimax Lower Bounds for Ridge Combinations Including Neural Nets
Jason M. Klusowski, Andrew R. Barron
Estimation of functions of variables is considered using ridge combinations of the form where th…