Seminario: Optimización y Aprendizaje Automático (2026)

Segundo semestre

Viernes 14:30–16:00 | salón 726 (7mo piso) | FING

Descripción

Este semestre el seminario tiene por objetivo discutir temas de investigación reciente en optimización y aprendizaje automático de interés para los participantes: Esto incluye formulaciones no-lineales (Burer-Monteiro) de problemas convexos, optimización en espacios de medidas, transferabilidad de GNNs, neural operators, entre otros.

Calendario del Seminario

Fecha Título Links Conferencista
21/8/2026 Reunion Organizacional
28/8/2026 Formal certificates for peak estimation TBA Mauricio Velasco
4/9/2026 CANCELADO
11/9/2026 Rational GNNs y CayleyNets TBA Pedro Raigorodsky
18/9/2026 Sequential minimax search TBA Matias Carrasco
25/9/2026 CANCELADO
2/10/2026 Consensus-based optimization TBA Matias Carrasco (2ª charla)
9/10/2026 Diffusion models on spheres TBA Leandro Bentancur
16/10/2026 TBA TBA Marcelo Fiori
23/10/2026 TBA TBA Bernardo Marenco
30/10/2026 TBA TBA Luca Frachelle
6/11/2026 TBA TBA CICADA
13/11/2026 TBA TBA CURSO
20/11/2026 TBA TBA María Nakwaqui
27/11/2026 TBA TBA Federico Correa
4/12/2026 TBA TBA Diego Armentano
11/12/2026 TBA TBA Sofía Llavayol

Referencias de interés

Título Autores Link Tema
On the low-rank approach for semidefinite programs arising in synchronization and community detection Afonso S. Bandeira, Nicolas Boumal, Vladislav Voroninski arXiv:1602.04426 Burer Monteiro Exactness 1
On the Burer-Monteiro method for general semidefinite programs Diego Cifuentes arXiv:1904.07147 Burer Monteiro Exactness 2
Benign landscape for Burer-Monteiro factorizations of MaxCut-type semidefinite programs Faniriana Rakoto Endor, Irène Waldspurger arXiv:2411.03103 Burer Monteiro Exactness 3
On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport Lenaic Chizat, Francis Bach arXiv:1805.09545 Optimization on measures 1
Sparse Optimization on Measures with Over-parameterized Gradient Descent Lenaic Chizat arXiv:1907.10300 Optimization on measures 2
Convergence Rates of Gradient Methods for Convex Optimization in the Space of Measures Lenaic Chizat arXiv:2105.08368 Optimization on measures 3
CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters Ron Levie, Federico Monti, Xavier Bresson, Michael M. Bronstein arXiv:1705.07664 Cayley Nets
On the Transferability of Spectral Graph Filters Ron Levie, Elvin Isufi, Gitta Kutyniok arXiv:1901.10524 Transferability 1
Transferability of Spectral Graph Convolutional Neural Networks Ron Levie, Wei Huang, Lorenzo Bucci, Michael M. Bronstein, Gitta Kutyniok arXiv:1907.12972 Transferability 2
A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation Ofek Amran, Tom Gilat, Ron Levie arXiv:2602.08785 Transferability 3
A Short Tour of Operator Learning Theory: Convergence Rates, Statistical Limits, and Open Questions Simone Brugiapaglia, Nicola Rares Franco, Nicholas H. Nelsen arXiv:2603.00819 Neural operators 1
Generalization Error Bounds for Picard-Type Operator Learning in Nonlinear Parabolic PDEs Koichi Taniguchi, Sho Sonoda arXiv:2605.10277 Neural operators 2
Geometric Generalization of Neural Operators from Kernel Integral Perspective Mingyu Han, Daniel Zhengyu Huang, Yuhan Wang, Yanshu Zhang, Jiayi Zhou arXiv:2602.01498 Neural operators 3

Organizadores