Borja Rodríguez Gálvez
Researcher at KTH Royal Institute of Technology
Education
- Ph.D in Electrical Engineering & Computer Science, KTH Royal Institute of Technology: August 2019 - April 2024 (Stockholm, Sweden)
- Supervisors: Mikael Skoglund and Ragnar Thobaben
- Doctoral thesis: “An Information-Theoretic Approach to Generalization Theory”
- M.Sc. in Machine Learning, KTH Royal Institute of Technology: August 2017 - June 2019 (Stockholm, Sweden)
- B.Sc. in Telecommunications Engineernig, Universitat Politècnica de Catalunya: August 2013 - July 2017 (Barcelona, Spain)
Professional experience
- Machine Learning Research Intern at Apple: June 2022 - September 2022 (Paris, France)
- I studied multi-view self-supervised learning algorithms. We saw that most of these algorithms were maximizing the same mutual information via different tricks and that they could be simplified and made more robust maximizing it explicitly [resulting paper].
- Machine Learning Research Intern at Apple: June 2021 - September 2021 (Cambridge, UK)
- I developed private federated learning algorithms that also certified a prescribed level of group fairness. [resulting paper].
- Machine Learning Research Intern at CISCO: June 2019 - August 2019 (Oslo, Norway)
- I developed more efficient face detection algorithms.
- Machine Learning Research Intern at Tobii AB: June 2018 - August 2018 (Stockholm, Sweden)
- I developed more efficient gaze estimation and head pose estimation algorithms.
- Computer Vision Intern at Serimag Media: June 2018 - August 2018 (Barcelona, Spain)
- I researched and implemented an algorithm to generate images from video frames. The algorithm was developed with the collaboration of the CVC Barcelona.
Publications
- A note on generalization bounds for losses with finite moments
Borja Rodríguez-Gálvez, Omar Rivasplata, Ragnar Thobaben, and Mikael Skoglund - More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime-validity
Borja Rodríguez-Gálvez, Ragnar Thobaben, and Mikael Skoglund - The Role of Entropy and Reconstruction for Multi-View Self-Supervised Learning
Borja Rodríguez-Gálvez, Arno Blaas, Pau Rodriguez, Adam Golinski, Xavier Suau, Jason Ramapuram, Dan Busbridge, and Luca Zappella - Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards
Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, and Mikael Skoglund - Limitations of information-theoretic generalization bounds for gradient descent methods in stochastic convex optimization
Mahdi Haghifam, Borja Rodríguez-Gálvez, Ragnar Thobaben, Mikael Skoglund, Daniel M. Roy, Gintare Karolina Dziugaite - An Information-Theoretic Analysis of Bayesian Reinforcement Learning
Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, Mikael Skoglund - Tighter expected generalization error bounds via Wasserstein distance
Borja Rodríguez-Gálvez, Germán Bassi, Ragnar Thobaben, and Mikael Skoglund - Measuring Gender Bias in
Contextualized Embeddings
Styliani Katsarou, Borja Rodrı́guez-Gálvez, and Jesse Shanahan - Enforcing fairness in private federated learning via the modified method of differential multipliers
Borja Rodríguez-Gálvez, Filip Granqvist, Rogier van Dalen, and Matt Seigel - Upper Bounds on the Generalization Error of Private Algorithms
Borja Rodríguez-Gálvez, Germán Bassi, and Mikael Skoglund - A Variational Approach to Privacy and Fairness
Borja Rodríguez-Gálvez, Ragnar Thobaben, and Mikael Skoglund - On Random Subset Generalization Error Bounds and the Stochastic Gradient Langevin Dynamics Algorithm
Borja Rodríguez-Gálvez, Germán Bassi, Ragnar Thobaben, and Mikael Skoglund - The Convex Information Bottleneck Lagrangian
Borja Rodríguez-Gálvez, Ragnar Thobaben, and Mikael Skoglund- Entropy (Editor’s choice) (Special Issue) [pdf] [cite] [graphical abstract]
Talks
-
“A Variational Approach to Privacy and Fairness”. Spotlight presentation at the AAAI PPAI Workshop. Online. February 8th, 2021.
-
“Tighter expected generalization error bounds via Wasserstein distance”. Invited talk at the Information Theory, Machine Learning and Statistics Seminar. Online. April 30th, 2021.
-
“Tighter expected generalization error bounds via Wasserstein distance”. Contributed talk at the ICML ITR3 Workshop. Online. July 24th, 2021.
-
“PAC-Bayes bounds’ parameter optimization via events’ space discretization: new bounds for losses with general tail behaviors”. Contributed talk at the ICML PBMIL Workshop. Honolulu, Hawaii. July 28th, 2023.
-
“A Variational Approach to Privacy and Fairness”. Invited talk at the Swiss Data Science Center. Online. October 25th, 2023.
-
“More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime-validity”. Invited talk at the UCL department of statistics. London, UK. November 15h, 2023.
-
“More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime-validity”. Invited talk at Google Deepmind. London, UK. November 17h, 2023.
Teaching
- DD2424 Deep Learning in Data Science at KTH - Spring 2019
- DD2434 Machine Learning, Advanced Course at KTH - Fall 2018
- DD2447 Statistical Methods in Applied Computer Science at KTH - Fall 2018
- DD2380 Artificial Intelligence - Fall 2018, 2019, 2020, and 2021; and Spring 2019
- EQ1270 Stochastic Signals and Systems at KTH - Fall 2021, 2022, and 2023
- EQ2840/F2E5316 Information Theory at KTH - Fall 2022, Spring 2023