GA4ML | Geometric Algorithms for Machine Learning
This workshop is merging with another: Workshop on Geometry and Machine Learning all further details can be found there.
Organized by Jinhui Xu and Jeff Phillips.

Machine learning concerns techniques that can learn from and make predictions on data. Algorithms for these goals are built to explore the useful pattern of the input data, which usually can be stated in terms of geometry (e.g., problems in high dimensional feature space). Hence computational geometry plays a crucial and natural role in interacting with machine learning. Since geometric algorithms often come with quality guaranteed solutions, they are of ciritical importance in formalizing the effectiveness of various techniques and in developing new ones. On the other hand, problems in machine learning serve as important motivation for work central to geometric algorithms.

This workshop is intended to provide a forum for those working in the fields of computational geometry, algorithms, machine learning and the various theoretical and algorithmic challenges to promote their interaction and blending. To this end, the workshop will consist of several invited talks and contributed talks. Invited talks will mainly serve as tutorials about the applications of geometric algorithms in machine learning. Such interaction will stimulate those working in both fields, and we can expect that a synergy can promote many new interesting geometric problems, concepts and ideas, which will contribute to open up new vistas in computational geometry and theory communities.

As a joint STOC/SoCG workshop, we hope researchers who normally frequent only one of STOC or SoCG, but work in geometric algorithms for machine learning, will converge together sharing their insights and developments.



This workshop is being held as a joint STOC/SoCG Workshop on June 18, 2016 in Boston, MA. It will be part of both CG Week 2016 (which also includes SOCG) and STOC.

Invited Talks:
Confirmed speakers: Sanjoy Dasgupta, Piotr Indyk ... more TBA



Contributed Talks: To submit a contributed talk to be considered for a talk and/or poster, send an email to GA4ML2016@gmail.com with an abstract (e.g., 2 pages) or link to permanent, publically available version (e.g., at arXiv.org).

We plan to create a longterm record of this workshop, hosted here. For this purpose we will request that authors of accepted papers provide us with a short (e.g., 2 pages) freely available abstract which we can host on this site, or a link to a permanent link of a freely available version (e.g., from arXiv.org, JoCG, ECCC).



Program: TBA
The program will include both invited and contributed talks, and a poster session.