Learning and Testing in High Dimensions

Because of COVID-19, we cannot schedule in-person events on the Berkeley campus through December 2020. This workshop will take place online. It will be open to the public for online participation. Please register to receive the zoom webinar access details. Registration will open in early October.

Many learning and testing problems naturally occur in a high-dimensional setting, where it is important to obtain results that are dimension-free (or with only mild dimension-dependence). As a representative example, one can consider the problems of testing and learning juntas: functions of many variables that depend (either precisely or approximately) only on a small subset of the variables. The problem of testing juntas is relatively well understood, while for the problem of learning juntas, there is a large gap between information-theoretic lower bounds and algorithmic results. More recent work introduced some variants of junta testing of a more geometric flavor, where many basic questions remain open. The techniques developed for these problems so far have involved a mixture of algorithmic methods and tools from high-dimensional probability. The purpose of this workshop is to make progress on these problems by bringing learning theorists together with geometers and probabilists who have expertise in high-dimensional phenomena.

This workshop will now be held virtually. The workshop is being live streamed on our website. Full participation (including the capacity to ask questions) will be available via Zoom webinar. A link to the Zoom webinar will be shared with registrants closer to the event date. Please register by clicking the registration link above.

If you require accommodation for communication, please contact our Access Coordinator at simonsevents@berkeley.edu with as much advance notice as possible.