Recently Added

The Geography of Immersed Lagrangian Fillings of Legendrian Submanifolds

Lisa Traynor
April 24, 2020
Given a smooth knot K in the 3-sphere, a classic question in knot theory is: What surfaces in the 4-ball have boundary equal to K? One can also consider immersed surfaces and ask a “geography” question: What combinations of genus and double points can be realized by surfaces with boundary equal to K? I will discuss symplectic analogues of these questions: Given a Legendrian knot, what Lagrangian surfaces can it bound? What immersed Lagrangian surfaces can it bound?

Deep Generative models and Inverse Problems

Alexandros Dimakis
University of Texas at Austin
April 23, 2020
Modern deep generative models like GANs, VAEs and invertible flows are showing amazing results on modeling high-dimensional distributions, especially for images. We will show how they can be used to solve inverse problems by generalizing compressed sensing beyond sparsity. We will present the general framework, new results and open problems in this space.

Geodesically Convex Optimization (or, can we prove P!=NP using gradient descent)

Avi Wigderson
Herbert H. Maass Professor, School of Mathematics
April 21, 2020
This talk aims to summarize a project I was involved in during the past 5 years, with the hope of explaining our most complete understanding so far, as well as challenges and open problems. The main messages of this project are summarized below; I plan to describe, through examples, many of the concepts they refer to, and the evolution of ideas leading to them. No special background is assumed.

Interpretability for Everyone

Been Kim
April 16, 2020
In this talk, I would like to share some of my reflections on the progress made in the field of interpretable machine learning. We will reflect on where we are going as a field, and what are the things that we need to be aware of to make progress. With that perspective, I will then discuss some of my work on 1) sanity checking popular methods and 2) developing more lay person-friendly interpretability methods. I will also share some open theoretical questions that may help us move forward.

Steps towards more human-like learning in machines

Josh Tenenbaum
April 16, 2020
There are several broad insights we can draw from computational models of human cognition in order to build more human-like forms of machine learning. (1) The brain has a great deal of built-in structure, yet still tremendous need and potential for learning. Instead of seeing built-in structure and learning as in tension, we should be thinking about how to learn effectively with more and richer forms of structure. (2) The most powerful forms of human knowledge are symbolic and often causal and probabilistic.

Tradeoffs between Robustness and Accuracy

Percy Liang
April 16, 2020
Standard machine learning produces models that are highly accurate on average but that degrade dramatically when the test distribution deviates from the training distribution. While one can train robust models, this often comes at the expense of standard accuracy (on the training distribution). We study this tradeoff in two settings, adversarial examples and minority groups, creating simple examples which highlight generalization issues as a major source of this tradeoff.

Modularity, Attention and Credit Assignment: Efficient information dispatching in neural computations

Anirudh Goyal
April 16, 2020
Physical processes in the world often have a modular structure, with complexity emerging through combinations of simpler subsystems. Machine learning seeks to uncover and use regularities in the physical world. Although these regularities manifest themselves as statistical dependencies, they are ultimately due to dynamic processes governed by physics. These processes are often independent and only interact sparsely..Despite this, most machine learning models employ the opposite inductive bias, i.e., that all processes interact.

The Peculiar Optimization and Regularization Challenges in Multi-Task Learning and Meta-Learning

Chelsea Finn
April 16, 2020
Despite the success of deep learning, much of its success has existed in settings where the goal is to learn one, single-purpose function from data. However, in many contexts, we hope to optimize neural networks for multiple, distinct tasks (i.e. multi-task learning), and optimize so that what is learned from these tasks is transferable to the acquisition of new tasks (e.g. as in meta-learning).