Chris Cremer

I'm a PhD student in Computer Science at the University of Toronto and Vector Institute. I'm interested in reinforcement learning, deep learning, and Bayesian learning.
I'm co-supervised by David Duvenaud and Quaid Morris.


Inference Suboptimality in Variational Autoencoders

We analyze approximate inference in variational autoencoders in terms of the approximation and amortization gaps. We find that suboptimal inference is often due to amortizing inference rather than the limited complexity of the approximating distribution. We show that this is due partly to the generator learning to accommodate the choice of approximation. Furthermore, we show that the parameters used to increase the expressiveness of the approximation play a role in generalizing inference rather than simply improving the complexity of the approximation.
Chris Cremer, Xuechen Li, David Duvenaud
ICML, July 2018

Reinterpreting Importance-Weighted Autoencoders

The standard interpretation of importance-weighted autoencoders is that they maximize a tighter lower bound on the marginal likelihood than the standard evidence lower bound. We give an alternate interpretation of this procedure: that it optimizes the standard variational lower bound, but using a more complex distribution. We formally derive this result, present a tighter lower bound, and visualize the implicit importance-weighted distribution.
Chris Cremer, Quaid Morris, David Duvenaud
ICLR Workshop, April 2017

Presentation Slides

Uncertainty in Bayesian Neural Networks

Visualizations of decision boundaries
August 2017

Gradients of Deep Networks

A small look at skip-connection models
March 2017
[pdf] [blog]

Intro to Probability for ML

Review of probability theory
September 2015


Approximate Posterior Building Blocks

This is a short review of orthogonal methods for improving inference in latent variable models. I examine the lower bounds and complexities of these models as well as their combinations.
June 2017

MSc Dissertation: Gene Expression Deconvolution with Subpopulation Proportions

Personalized cancer strategies are currently being hindered by intratumor heterogeneity. One source of heterogeneity, clonal evolution, can lead to genetically distinct subpopulations within a sample. Through the use of subclonal reconstruction methods, we can obtain estimates of the subpopulation proportions within a single sample. Here, I leverage these proportion estimates by incorporating it into the deconvolution of tumour gene expression data in order to estimate the subclone specific gene expression profiles.
Advisor: Quaid Morris
University of Toronto, February 2016


As a side project, I started a deep learning company that helps businesses automate their workflow and learn from their data. We are currently serving a driving safety company where we automate the classification of their driving videos for their driver safety review process.