Sanya Workshop
on
Algebraic Geometry and Machine Learning
Tsinghua Sanya International Mathematics Forum
January 26th-29th, 2021
The recordings of the talks (if permitted) are available on the YouTube channel.
Workshop Theme:
Machine learning has become ubiquitous across a broad range of science and engineering disciplines in recent years. From medicine, finance, engineering, natural processing, and speech recognition, to many more areas encompassing the full range of human endeavours, we are unquestionably witnessing the emergence of a new, fundamental tool that is starting to revolutionise how science is done.
Results in algebraic geometry have similarly been developed rapidly over the past decade. Examples range from new symbolic and numeric techniques for solving ever more difficult systems of polynomial equations, to the increasing role of big data and methods from data science in fundamental geometry research. Many problems in algebraic geometry and related areas in theoretical physics and pure mathematics are beginning to develop fruitful interactions with machine-learning. In parallel to these developments, machine learning problems such as exploring optimisation landscapes of deep learning and training various machine learning algorithms can be posed as algebraic geometry problems.
The main purpose of this workshop is to bring together researchers from both algebraic geometry and machine learning. The goal is to communicate questions in an accessible way, and so create integrated teams of interdisciplinary researchers. These boundary-crossing teams will develop new theoretical foundations, as well as effective computational methods for answering open research questions.
Topics (not limited to):
Applications of Algebraic Geometry* in Machine Learning**
Applications of Machine Learning in Algebraic Geometry
*Algebraic Geometry is broadly defined: pure, applied and computational (algorithmic: symbolic and numerical), inspired by or applied in scientific areas, etc.
**Machine Learning is also broadly defined: supervised, unsupervised, semi-supervised, self-supervised, reinforcement learning, etc.
The basic premise of this workshop is to provide a platform to the research that aims to combine machine learning and algebraic geometry.
Acknowledgement
We thank Tsinghua Sanya International Mathematics Forum for hosting the workshop and providing us administrative support.
Organizers
Jonathan Hauenstein (University of Notre Dame)
Yang-Hui He (University of Oxford and City, University of London)
Alexander Kasprzyk (University of Nottingham)
Dhagash Mehta (The Vanguard Group)
Shing-Tung Yau (Harvard University, Tsinghua University and BIMSA)
Support Team
Jiakang Bao (jiakang.bao@city.ac.uk)
Ed Hirst (edward.hirst@city.ac.uk)
Suvajit Majumder (suvajit.majumder@city.ac.uk)