Aaron Lou

Stanford CS PhD

I am a Computer Science PhD student at Stanford, where I am supported by a NSF Graduate Research Fellowship. Previously, I completed my undergraduate studies at Cornell, where I was advised by Professor Chris De Sa through CUAI.

I'm primarily interested in applications of topological and geometric methods in deep learning.

[Email:   al968@cornell.edu] [Google Scholar] [LinkedIn] [Github] [CV]

Publications


Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks
NeurIPS 2021
[Arxiv][Code]

Tolga Birdal, Aaron Lou, Leonidas Guibas, Umut Şimşekli

Equivariant Manifold Flows
NeurIPS 2021
[Arxiv][Code]

Isay Katsman*, Aaron Lou*, Derek Lim*, Qingxuan Jiang*, Ser-Nam Lim, Christopher De Sa

Deep Riemannian Manifold Learning
NeurIPS Geo4dl Workshop 2020
[Paper]

Aaron Lou, Maximilian Nickel, Brandon Amos

Neural Manifold Ordinary Differential Equations
NeurIPS 2020
[Arxiv][Code][Video]

Aaron Lou*, Derek Lim*, Isay Katsman*, Leo Huang*, Qingxuan Jiang, Ser-Nam Lim, Christopher De Sa

Differentiating through the Fréchet Mean
ICML 2020
[Arxiv][Code][Slides]

Aaron Lou*, Isay Katsman*, Qingxuan Jiang*, Serge Belongie, Ser-Nam Lim, Christopher De Sa

Adversarial Example Decomposition
ICML SPML Workshop 2019
[Arxiv]

Horace He, Aaron Lou*, Qingxuan Jiang*, Isay Katsman*, Serge Belongie, Ser-Nam Lim

(* indicates equal contribution)

Industry Experience


Facebook AI

Research Intern
May 2020 - Aug 2020

Google

Software Engineering Intern
May 2019 - Aug 2019


Activities


Cornell University Artificial Intelligence

Co-President
Sept 2020 - May 2021

Undergraduate Researcher
Aug 2018 - May 2021

Cornell ICPC

Competitive Programmer
Aug 2018 - May 2021

Notes