Distribution-robust mean estimation via smoothed random perturbations

PAC-Bayes under potentially heavy tails

Original

Holland, M. J. (2019a) · 1905

Earlier work this paper cites.

Systems of frequency curves generated by methods of translation

Johnson, N. L. (1949) · 1949

Earlier work this paper cites.

Handbook of Mathematical Functions With Formulas, Graphs, and Mathematical Tables

Abramowitz, M. and Stegun, I. A. (1964) · 1964

Earlier work this paper cites.

Kendall’s Advanced Theory of Statistics Volume 1: Distribution Theory

Stuart, A. and Ord, J. K. (1994) · 1994

Earlier work this paper cites.

Robust empirical mean estimators

Original

Lerasle, M. and Oliveira, R. I. (2011) · 2011

Earlier work this paper cites.

Challenging the empirical mean and empirical variance: a deviation study

Catoni, O. (2012) · 2012

Cited alongside, same era.

Computing the Kullback-Leibler divergence between two Weibull distributions

Original

Bauckhage, C. (2013) · 2013

Cited alongside, same era.

Empirical risk minimization for heavy-tailed losses

Brownlees, C., Joly, E., and Lugosi, G. (2015) · 2015

Cited alongside, same era.

Sub-gaussian mean estimators

Devroye, L., Lerasle, M., Lugosi, G., and Oliveira, R. I. (2016) · 2016

Cited alongside, same era.

Dimension-free PAC-Bayesian bounds for matrices, vectors, and linear least squares regression

Original

Catoni, O. and Giulini, I. (2017) · 2017

Cited alongside, same era.

Robust descent using smoothed multiplicative noise

Holland, M. J. (2019b)

Distributed statistical machine learning in adversarial settings: Byzantine gradient descent

Chen, Y., Su, L., and Xu, J. (2017) · 2017

Later among the works it cites.

Robust regression using biased objectives

Holland, M. J. and Ikeda, K. (2017) · 2017

Later among the works it cites.

Objective priors for the number of degrees of freedom of a multivariate

Original

Villa, C. and Rubio, F. J. (2018) · 2018

Later among the works it cites.

Better generalization with less data using robust gradient descent

Holland, M. J. and Ikeda, K. (2019) · 2019

Closest in time.