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
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
A Hotelling-Downs Game for Strategic Candidacy with Binary Issues
Published in AAMAS, 2023
This paper is about how elections based on binary preferences can be subject to the strategic behavior of candidates, who can modify their political views to obtain a better outcome in the election.
Symmetries in Overparametrized Neural Networks: A Mean Field View
Published in NeurIPS, 2024
This paper studies, under the Mean Field lens, how overparametrized neural networks behave when the data they are trained on satisfies simple symmetries and/or when symmetry-leveraging techniques (such as Data Augmentation, Feature Averaging or Equivariant Architectures) are used.
talks
Fête de la Science 2021 - Les maths et la prise de décision
Published:
As part of the Parcours Recherche program, I participated in the “Fête de la Science 2021” together with a team consisting of Jean-Baptiste Dubois, Clément Mosser, Pedro Sotomayor and myself. We presented a tutorial to the 4th grade students from Collège Roland Garros on the topic of “Mathematics for Decision-Making” (“Les maths et la prise de décision”), and included a didactic game to illustrate the phenomenon of strategic voting. We also showed a video in which some of the key concepts were explained; the video can be found here (it’s in French).
Summer School on Discrete Mathematics - A Hotelling-Downs Game for Strategic Candidacy with Binary Issues
Published:
I presented my work on a Hotelling-Downs Game for elections with binary issues at the XVIII Summer School on Discrete Mathematics organized by the Center for Mathematical Modelling (CMM) at the ISCV in Valparaíso, Chile. The details of the program are given in the following link.
Download Download Slides
</p>AAMAS 2023 - A Hotelling-Downs Game for Strategic Candidacy with Binary Issues
Published:
In this talk I presented the work we developed with Vincent Mousseau and Anaëlle Wilczynski on the study of strategic candidacy on a Hotelling-Downs Game for elections which model voters as having binary preferences over a given set of issues. The slides of the talk can be found here.
Download Download Slides
</p>Thesis Defense - Symmetries in Overparametrized Neural Networks: A Mean Field View
Published:
In order to receive my Master’s degree, I had to defend my Master’s thesis. This was a 40 minute talk in which I outlined all the different elements as well as the main results.
Download Download Slides
</p>Probability Seminar - Symmetries in Overparametrized Neural Networks: A Mean Field View
Published:
I presented the contents of our accepted Neurips paper on the Probability Seminar from the FCFM at Universidad de Chile. It was a ~50 minute talk in which I outlined all the different elements and the main results from the paper. The slides are available here, and the full presentation is available here.
Download Download Slides
</p>Neurips 2024 - Symmetries in Overparametrized Neural Networks: A Mean Field View
Published:
As a spotlight paper at NeurIPS, we presented our work in a 5 min video which was available through the conference website, as well as a poster in one of the main poster sessions. The talk outlined the different elements of our paper (together with Joaquín Fontbona) on the effect of data-symmetries in neural-network training at the Mean Field level.
Download Download Slides
</p>teaching
BasiCS Summer School
Summer School, CentraleSupélec, BasiCS, 2021
I was part of the team that organized and instructed the Math tutorships for international students arriving to CentraleSupélec. We were supervised by Erik Herbin (Mathematics professor at CentraleSupélec).
Teaching Assistant (TA) for Undergraduate and MSc. Courses
Undergraduate course, Universidad de Chile, Departmento de Ingeniería Matemática, 2024
I was in charge of planning, desinging and teaching the Tutorials for many subjects during my undergraduate years. Namely:
- ’Newtonian Physics’ (2019), undergraduate level.
- ’Multivariable Calculus’ (2020), undergraduate level.
- ’Markov Processes’ (2023), undergraduate level.
- ’Statistics’ (2023), undergraduate level.
- ’Abstract Algebra’ (2023), undergraduate level.
- ’Mathematical topics on Machine Learning, Neural Networks and Deep Learning’ (2024), masters level.
ENIM 2024 - The Math Behind the Magic: Neural Networks, Theory and Practice
Short Course, Mathematical Engineering Department, Universidad de Chile, 2024
Together with my fellow TA Diego Olguín, we taught a short course for the National Mathematical Engineering Encounter (ENIM 2024). It covered key theoretical and mathematical results related to neural networks; essential concepts such as network architectures, the universal approximation theorem, and optimization through stochastic gradient descent. Theoretical discussions were also combined with practical tutorials, focusing on applying the concepts on real-world data, with convolutional neural networks for image classification and physics-informed neural networks (PINNs) for simulating ODEs. The official course page is here, and the official GitHub repository shall be found here.