Timezone: »
Algorithmic Robust Statistics
Ankur Moitra
Over the past few years, there has been exciting progress on algorithmic robust statistics in unsupervised, supervised and online learning. Much of this progress has been fueled by new algorithmic tools for detecting portions of the samples that have different distributional profiles. We will survey some of these tools as well as discuss prospects for building theories of coping with distribution shift from them.
Author Information
Ankur Moitra (MIT)
More from the Same Authors
-
2017 Poster: Being Robust (in High Dimensions) Can Be Practical »
Ilias Diakonikolas · Gautam Kamath · Daniel Kane · Jerry Li · Ankur Moitra · Alistair Stewart -
2017 Talk: Being Robust (in High Dimensions) Can Be Practical »
Ilias Diakonikolas · Gautam Kamath · Daniel Kane · Jerry Li · Ankur Moitra · Alistair Stewart -
2017 Poster: Learning Determinantal Point Processes with Moments and Cycles »
John C Urschel · Ankur Moitra · Philippe Rigollet · Victor-Emmanuel Brunel -
2017 Talk: Learning Determinantal Point Processes with Moments and Cycles »
John C Urschel · Ankur Moitra · Philippe Rigollet · Victor-Emmanuel Brunel -
2017 Tutorial: Robustness Meets Algorithms (and Vice-Versa) »
Ankur Moitra