Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About
About me
news
"A principled approach for generating adversarial images under non-smooth dissimilarity metrics" was accepted to AISTATS 2020
Published:
Gave a talk at UCLA during the IPAM workshop on PDEs and Inverse Problems in Machine Learning
Published:
"How to train your neural ODE: …" was accepted to ICML 2020
Published:
New preprint on learning Continuous Normalizing Flows as gradients of potential functions, using Optimal Transport & duality
Published:
Started as a research scientist at Deep Render
Published:
Our work on Normalizing Flows and potential functions was featured as a contributing talk at the INNF workshop at ICML
Published:
My work with Adam Oberman on Scaleable adversarial robustness was accepted to Machine Learning with Applications
Published:
publications
From cell population models to tumor control probability: including cell cycle effects
Published in Acta Oncologica, 2010
Recommended citation: Hillen, Thomas, Gerda De Vries, Jiafen Gong, and Chris Finlay. "From cell population models to tumor control probability: including cell cycle effects." Acta Oncologica 49, no. 8 (2010): 1315-1323.
Are more complicated tumour control probability models better?
Published in Mathematical Medicine and Biology, 2013
Recommended citation: Gong, Jiafen, Mairon M. Dos Santos, Chris Finlay, and Thomas Hillen. "Are more complicated tumour control probability models better?" Mathematical Medicine and Biology: a journal of the IMA 30, no. 1 (2011): 1-19.
Annual ring density for lodgepole pine as derived from models for earlywood density, latewood density and latewood proportion
Published in Forestry: An International Journal of Forest Research, 2015
Recommended citation: Sattler, Derek F., Chris Finlay, and James D. Stewart. "Annual ring density for lodgepole pine as derived from models for earlywood density, latewood density and latewood proportion." Forestry: An International Journal of Forest Research 88, no. 5 (2015): 622-632.
Approximate homogenization of fully nonlinear elliptic PDEs: estimates and results for Pucci type equations
Published in Journal of Scientific Computing, 2018
Recommended citation: Finlay, Chris, and Adam M. Oberman. "Approximate homogenization of fully nonlinear elliptic PDEs: estimates and results for Pucci type equations." Journal of Scientific Computing 77, no. 2 (2018): 936-949.
Approximate homogenization of convex nonlinear elliptic PDEs
Published in Communications in Mathematical Sciences, 2018
Recommended citation: Finlay, Chris, and Adam M. Oberman. "Approximate homogenization of convex nonlinear elliptic PDEs." Communications in Mathematical Sciences 16, no. 7 (2018): 1895-1906.
Lipschitz regularized deep neural networks generalize and are adversarially robust
Published in , 2019
Recommended citation: Finlay, Chris, Jeff Calder, Bilal Abbasi, and Adam M. Oberman. "Lipschitz regularized deep neural networks generalize and are adversarially robust." arXiv preprint arXiv:1808.09540 (2019).
Improved accuracy of monotone finite difference schemes on point clouds and regular grids
Published in SIAM Journal on Scientific Computing (SISC), 2019
Recommended citation: Finlay, Chris, and Adam M. Oberman. "Improved accuracy of monotone finite difference schemes on point clouds and regular grids." SIAM Journal on Scientific Computing 49, no. 15 (2019): 3097-3117.
The LogBarrier adversarial attack: making effective use of decision boundary information
Published in International Conference on Computer Vision (ICCV), 2019
Recommended citation: Finlay, Chris, Aram-Alexandre Pooladian and Adam M. Oberman. "The LogBarrier adversarial attack: making effective use of decision boundary information." International Conference on Computer Vision, 2019.
A principled approach for generating adversarial images under non-smooth dissimilarity metrics
Published in Artificial Intelligence and Statistics (AISTATS), 2020
Recommended citation: Aram-Alexandre Pooladian, Chris Finlay, Tim Hoheisel, and Adam M. Oberman. "A principled approach for generating adversarial images under non-smooth dissimilarity metrics." 23rd International Conference on Artificial Intelligence and Statistics (2020).
Deterministic Gaussian Averaged Neural Networks
Published in , 2020
Recommended citation: Campbell, Ryan, Chris Finlay, and Adam M. Oberman. "Deterministic Gaussian Averaged Neural Networks." arXiv preprint arXiv:2006.06061 (2020).
How to train your Neural ODE: the world of Jacobian and kinetic regularization
Published in International Conference on Machine Learning (ICML), 2020
Recommended citation: Finlay, Chris, Jörn-Henrik Jacobsen, Levon Nurbekyan, and Adam M. Oberman. "How to train your Neural ODE: the world of Jacobian and kinetic regularization." International Conference on Machine Learning, 2020..
Learning normalizing flows from Entropy-Kantorovich potentials
Published in ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (Contributed talk), 2020
Recommended citation: Finlay, Chris, Augusto Gerolin, Adam M. Oberman, and Aram-Alexandre Pooladian. "Learning normalizing flows from Entropy-Kantorovich potentials." arXiv preprint arXiv:2006.06033 (2020).
Scaleable input gradient regularization for adversarial robustness
Published in Machine Learning with Applications, 2021
Recommended citation: Finlay, Chris, and Adam M. Oberman. "Scaleable input gradient regularization for adversarial robustness." Machine Learning with Applications 3 (2021): 100017.
talks
TV Regularization leads to adversarially robust and accurate neural networks
Published:
This was an invited talk I gave at the at the Level Set Collective, in the UCLA Math department. This presentation was based off of joint work with Adam Oberman and Bilal Abbasi, where we trained adversarially robust neural networks with both Lipshitz and TV gradient regularization.
Scaleable input regularization for adversarial robustness
Published:
This was a poster presentation at the Deep Learning and Reinforcement Learning summer school, organized by CIFAR and AMII, and hosted at the University of Alberta. This presentation was based off of joint work with Adam Oberman on training adversarially robust networks using gradient regularization.
On some applied problems using nonlinear elliptic PDEs
Published:
My PhD defence presentation, on solving some applied problems using nonlinear elliptic PDEs.
The LogBarrier adversarial attack
Published:
This was a poster presentation at the 2019 International Conference on Computer Vision (ICCV), in Seoul, Korea. This presentation was based on our paper on the LogBarrier adversarial attack.
Regularized neural ODEs for density estimation with normalizing flows
Published:
Montreal has a strong group of optimization researchers working in machine learning. They meet every second Friday under the umbrella organization MtlOPT, where researchers present current research they are working on. This was a talk I gave on a paper we had recently submitted on training neural ODEs with kinetic regularization
Training neural ODEs for density estimation
Published:
Pre-pandemic, I was invited to be a visiting fellow at IPAM’s spring 2020 long program on high-dimensional Hamilton-Jacobi PDEs. Although my stay was cut short, I did give a virtual talk as part of the program’s workshop on PDEs and Inverse Problems in Machine Learning. This talk was based on our paper on training neural ODEs with kinetic regularization
teaching
Music instructor
Private guitar lessons, Long & McQuade, Edmonton, Alberta, 2010
Before grad school, I taught private guitar lessons for many years. I tailored lessons to each student’s ability and interests, teaching material ranging anywhere from beginning acoustic guitar, to classical pedagogy, to jazz guitar.
Calculus II
TA, undergraduate course, McGill University, Department of Mathematics and Statistics, 2015
Teaching assistant for first year calculus, mainly on techniques of integration and series.
Linear Algebra I
TA, undergraduate course, McGill University, Department of Mathematics and Statistics, 2015
Teaching assistant for first year linear algebra, covering fundamentals of linear algebra.
Numerical Analysis
TA, undergraduate course, McGill University, Department of Mathematics and Statistics, 2016
Teaching assistant for third year course on numerical analysis. Topics included numerical solvers for ODEs and PDEs, root finding algorithms, and first- and second-order optimization algorithms. Among other duties, I taught a weekly lab introducing fundamentals of coding for students who had not coded before.
Convex Analysis & Nonsmooth Analysis
TA, graduate topics course, McGill University, Department of Mathematics and Statistics, 2017
Teaching assistant for a graduate level topics course on convex analysis. I guided a weekly study group where students solved problems designed to sharpen their convex analysis skills.
Optimization
TA, graduate course, McGill University, Department of Mathematics and Statistics, 2018
Teaching assistant for a graduate level course on continuous optimization for students in Electrical Engineering. Topics included first- and second-order optimization algorithms, their convergence, and rates of convergence.