Victor Sanches Portella

I am a PhD student at the Department of Computer Science from the University of British Columbia where I am supervised by prof. Nick Harvey. In 2019 obtained a Master's degree in Computer Science from the Institute of Mathematics and Statistics of the University of São Paulo under the supervision of prof. Marcel K. de Carli Silva.

Research interests: I am broadly interested in combinatorial and convex optimization, and even more broadly interested in theoretical computer science. Lately I have been specially interested in online learning and optimization.

E-mail: victorsp [AT] cs [DOT] ubc [DOT] ca


Continuous Prediction with Experts’ Advice.
with Chris Liaw and Nick Harvey. [arXiv]
Efficient and Optimal Fixed-Time Regret with Two Experts. (ALT 2022).
with Laura Greenstreet and Nick Harvey. [arXiv] [ALT 2022]
Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses. (NeurIPS 2020).
with Yihan Zhou, Mark Schmidt, and Nick Harvey. [arXiv] [NeurIPS 2020]
Online Mirror Descent and Dual Averaging: Keeping Pace in the Dynamic Case. (ICML 2020, Extended version on JMLR 2022).
with Huang Fang, Nick Harvey, Michael Friedlander. [arXiv] [ICML 2020] [JMLR]


Online Convex Optimization: Learning, Duality, and Algorithms.
Master's Thesis, 2019. [webpage] [pdf]
Almost Linear Time Algorithms for Flows in Graphs.
Undergraduate Thesis, 2016. [webpage] [pdf]


Slides for some of my talks.
Resume (PDF) [Last updated: Sept. 2022]
I have recently made a video explainer on the HyperLogLog algorithm as part of the Summer of Math Exposition 1.
In 2018 I helped to port form Python 2 to Python 3 a framework for visualizing algorithms for computational geometry. You can find the port here (usage instructions are in portuguese). Prof. Cristina Gomes is the usual lecturer the the computational geometry course at the University of São Paulo and she might have more up to date versions of this tool.
Github page.