We are pleased to announce our confirmed lineup of invited speakers for DeepMath 2022:

• Francis Bach (INRIA)

• Anima Anandkumar (CalTech)

• Sara Solla (Northwestern)

• Berk Ustun (UCSD) 

• Yisong Yue (Caltech)

• Courtney Paquette (McGill) 

We are now accepting abstract submissions to the 2022 Conference on mathematical theory of deep neural networks (DeepMath; see https://deepmath-conference.com for more information). DeepMath is a highly interdisciplinary conference focused on understanding fundamental theory driving the success of Deep Learning. A principal goal of this conference is to bring together theoreticians working on deep learning from various disciplines and perspectives.  We therefore encourage submissions from researchers from diverse disciplines including, but not limited to 

• Statistics

• Physics

• Computer science

• Neuroscience

• Mathematics

• Psychology

• Engineering

Topics may address any area of deep learning research such as 

• Expressivity

• Generalization

• Optimization

• Representations

• Computation

• Network architectures

• Recurrent networks. 

To complement the many conferences with applications and theory the focus for DeepMath 2022 will be exclusively on the theoretical and mechanistic understanding of the underlying properties of neural networks.

Abstracts will not be made public (i.e., no official proceedings), and will be doubly-blind reviewed and selected for quality. All poster submissions should be properly anonymized in order to allow for blind refereeing. Submissions should be no more than 1 page although a second page may be used for references. Authors should submit a pdf file prepared using the Latex style file available here and should adopt all formatting, subject headings, font sizes, etc. defined therein. Submissions that fail to meet the format requirements will not be reviewed. The first author listed on the abstract is considered to be the presenting author. Each presenting author may submit only one abstract.

Investigators interested in having their abstracts considered for presentation should submit their abstracts no later than August 14, 2022 AOE. Authors may submit their abstracts at: https://cmt3.research.microsoft.com/DEEPMATH2022/

== Location == 

DeepMath 2022 will be held in San Diego, CA, USA.  We anticipate requiring proof of full vaccination as a condition of attendance, and plan on having masking and other requirements equal or more stringent than local and national public health guidelines. Stay tuned to the DeepMath website (www.deepmath-conference.com) for more details on venue and hotels. As with all prior years, all talks will be freely live-streamed over YouTube and subsequently posted on the DeepMath YouTube channel 

== Registration == 

DeepMath 2022 registration will open late summer. As with previous DeepMath conferences, all talks will be live-streamed for free and uploaded for later viewing subject to presenter approval.

All the best,

Ahmed El Hady

On behalf of the DeepMath 2022 Organizational Committee