Seminars

Adrianna Gillman, Department of Applied Mathematics, University of Colorado Boulder Fast algorithms group: Accurate, efficient and robust techniques for solving partial differential equations Partial differential equations are often used to model physical phenomena. Unfortunately, it is impossible to simply write down the solution to most of the equations. Instead we...

Marsha Berger; Silver Professor of Computer Science and Mathematics; Courant Institute of Mathematical Sciences, New York University Computing Fluid Flows in Complex Geometry We give an overview of the difficulties in simulating fluid flow in complex geometry. The principal approaches use either overlapping or patched body-fitted grdis, unstructured grids, or...

APPM Department Colloquium - Joan Bruna Joan Bruna; Assistant Professor; Courant Institute of Mathematical Sciences, New York University Mathematical aspects of neural network approximation and learning High-dimensional learning remains an outstanding phenomena where experimental evidence outpaces our current mathematical understanding, mostly due to the recent empirical successes of Deep Learning...

Dumitru Erhan, Staff Research Scientist and Tech Lead Manager, Google Brain Enabling world models via unsupervised representation learning of environments. In order to build intelligent agents that quickly adapt to new scenes, conditions, tasks, we need to develop techniques, algorithms and models that can operate on little data or that...

Kalesha Bullard, Postdoctoral Researcher, Facebook AI Research Learning through Interaction in Cooperative Multi-Agent Systems Effective communication is an important skill for enabling information exchange and cooperation in multi-agent systems, in which agents coexist in a shared environment with humans and/or other artificial agents. Indeed, human domain experts can be a...

Mingxing Tan, Staff Software Engineer, Google Brain AutoML for Efficient Vision Learning This talk will focus on a few recent progresses we have made on AutoML, particularly on neural architecture search for efficient convolutional neural networks. We will first discuss the challenges and solutions in designing network architecture search spaces...

Philip Stark; Department of Statistics; University of California, Berkeley Evidence-Based Elections Elections rely on people, hardware, and software, all of which are fallible and subject to manipulation. Well resourced nation-states continue to attack U.S. elections. Voting equipment is built by private vendors–some foreign, but all using foreign parts. Many states...

Jeffrey Pennington, Research Scientist, Google Brain Demystifying deep learning through high-dimensional statistics As deep learning continues to amass ever more practical success, its novelty has slowly faded, but a sense of mystery persists and we still lack satisfying explanations for how and why these models perform so well. Among the...

Esteban Real, Software Engineer, Google Brain Evolving Machine Learning Algorithms The effort devoted to hand-crafting machine learning (ML) models has motivated the use of automated methods. These methods, collectively known as AutoML, can today optimize the models' architectures to surpass the performance of manual designs. I will discuss how evolutionary...

Christian Szegedy, Staff Research Scientist, Google Machine Learning for Mathematical Reasoning In this talk I will discuss the application of transformer based language models and graph neural networks on automated reasoning tasks in first-order and higher-order logic. After a short introduction of the type of problems addressed and the general...