AI & Fundamentals

Overcoming Mode Collapse and the Curse of Dimensionality - Ke Li, Assistant Professor, Simon Fraser University

Please register for this event here.

Abstract:

In this talk, I will present our work on overcoming two long-standing problems in machine learning:

1. Mode collapse in generative adversarial nets (GANs)

Generative adversarial nets (GANs) are perhaps the most popular class of generative models in use today. Unfortunately, they suffer from the well-documented problem of mode collapse, which the many successive variants of GANs have failed to overcome. I will illustrate why mode collapse happens fundamentally and show a simple way to overcome it, which is the basis of a new method known as Implicit Maximum Likelihood Estimation (IMLE). Whereas conditional GANs can only generate identical outputs from the same input, conditional IMLE can generate arbitrarily many diverse outputs from the same input.

2. Curse of dimensionality in exact nearest neighbour search

Efficient algorithms for exact nearest neighbour search developed over the past 40 years do not work in high (intrinsic) dimensions, due to the curse of dimensionality. It turns out that this problem is not insurmountable - I will explain how the curse of dimensionality arises and show a simple way to overcome it, which gives rise to a new family of algorithms known as Dynamic Continuous Indexing (DCI).

Bio:

Ke Li is an Assistant Professor in the School of Computing Science at Simon Fraser University. He is interested in a broad range of topics in machine learning, computer vision, NLP and algorithms and has worked on generative modelling, nearest neighbour search and Learning to Optimize. He is particularly passionate about tackling long-standing fundamental problems that cannot be tackled with a straightforward application of conventional techniques. He was previously a Member of the Institute for Advanced Study (IAS), and received his Ph.D. from UC Berkeley and B.Sc. from the University of Toronto.

Please register for this event here.