https://youtu.be/0FCgpyCfb4o New Technologies in Mathematics Seminar Speaker: Michael Borinsky, Perimeter Institute Title: Tropicalized quantum field theory Abstract: Quantum field theory (QFT) is one of the most accurate methods for making phenomenological predictions in physics, but it has a significant drawback: obtaining concrete predictions from it is computationally very demanding. The standard perturbative approach expands an […]
https://youtu.be/04E8r76TetQ New Technologies in Mathematics Seminar Speaker: Alex Damian, Harvard Title: Understanding Optimization in Deep Learning with Central Flows Abstract: Traditional theories of optimization cannot describe the dynamics of optimization in deep learning, even in the simple setting of deterministic training. The challenge is that optimizers typically operate in a complex, oscillatory regime called the "edge of […]
New Technologies in Mathematics Seminar Speaker: María Inés de Frutos Fernández, Mathematical Institute, University of Bonn Title: The Carleson project: A collaborative formalization Abstract: A well-known result in Fourier analysis establishes that the partial Fourier sums of a smooth periodic function $f$ converge uniformly to $f$, but the situation is a lot more subtle for […]
New Technologies in Mathematics Seminar Speaker: Yongji Wang, NYU Courant Institute of Mathematical Sciences Title: Discovery of unstable singularity with machine precision Abstract: Whether singularities can form in fluids remains a foundational unanswered question in mathematics. This phenomenon occurs when solutions to governing equations, such as the 3D Euler equations, develop infinite gradients from smooth initial […]
New Technologies in Mathematics Seminar Speaker: Adam Zsolt Wagner, Google DeepMind Title: Machine learning tools for mathematical discovery Abstract: I will discuss various ML tools we can use today to try to find interesting constructions to various mathematical problems. I will briefly mention simple reinforcement learning setups and PatternBoost, but the talk will mainly focus […]
New Technologies in Mathematics Seminar Speaker: George Tsoukalas, UT Austin Dept. of Computer Science and Google DeepMind. Title: Automated Theory Formation and Interestingness in Mathematics Abstract: Advances in modern learning systems are beginning to demonstrate utility for select problems in research mathematics. A broader challenge is that of developing new theories automatically. This area has a rich […]
New Technologies in Mathematics Seminar Speaker: Yiannis Vlassopoulos, Athena Research Center Title: ReLU and Softplus neural nets as zero-sum, turn-based, stopping games Abstract: Neural networks are for the most part treated as black boxes. In an effort to begin elucidating the mathematical structure they encode, we will explain how ReLU neural nets can be interpreted as […]
New Technologies in Mathematics Seminar Speaker: Courtney Paquette, McGill University Title: Scaling Stochastic Momentum from Theory to LLMs Abstract: Given the massive scale of modern ML models, we now often get only a single shot to train them effectively. This limits our ability to sweep architectures and hyperparameters, making it essential to understand how learning algorithms scale […]