I am a PhD Student at the Autonomous University of Madrid and study foundational topics in probabilistic machine learning and variational inference. My research focuses on studying the application of variational inference to modern Bayesian deep learning.
2021 - Present
Research Personnel, Ph.D. Student granted with FPI-UAM Scholarship, Autonomous University , Madrid |
11/2021 - 11/2025
Ph.D. Student, Autonomous University of Madrid
|
2020 - 2022
M.S. in Data Science, Autonomous University of Madrid
|
2015 - 2020
B.S. in Computer Science, University of Granada
|
2015 - 2020
B.S. in Mathematics, University of Granada
|
2021 - 2021
Research Assistant, University of Almería (with Andrés R. Masegosa studing the effect of diversity on Deep Neural Network ensembles.) |
2023
Granted Santander-UAM Scholarship. Uncertainty Estimation in LLM at Cambridge University.
Computational and Biological Learning Lab, University of Cambridge |
2021
Granted FPI-UAM Scholarship. Competitive Predoctoral Contract for Training Research Personnel
Department of Computer Science, Autonomous University of Madrid |
2020
Research Collaboration Scholarship
Department of Computer Science, Autonomous University of Madrid |
2020
Granted Highest Mark on Bachelor's Thesis, 10/10. Statistical Models with Variational Methods
Department of Computer Science and Faculty of Science, University of Granada |
1. |
Deep Variational Implicit Processes
[abs] [code] Luis A. Ortega, Simón Rodríguez-Santana, and Daniel Hernández-Lobato International Conference on Learning Representations (ICLR) 2023 |
2. |
Diversity and Generalization in Neural Network Ensembles
[abs] [code] Luis A. Ortega, Rafael Cabañas, and Andrés R. Masegosa Artificial Intelligence and Statistics (AISTATS) 2022 |
3. |
Correcting Model Bias with Sparse Implicit Processes
[abs] [code] Simón Rodríguez-Santana, Luis A. Ortega, Daniel Hernández-Lobato, and Bryan Zaldívar ICML Workshop "Beyond Bayes: Paths Towards Universal Reasoning Systems" 2022 |
Variational Linearized Laplace Approximation for Bayesian Deep Learning (Under Review)
[pre-print]
Uncertainty estimation on pre-trained Deep Learning models using Variational Inference and LLA. |
PAC-Chernoff Bounds: Understanding Generalization in the Interpolation Regime
[pre-print]
Explaining deep learning techniques (weight-decay, overparameterization, data-augmentation) using Large Deviation Theory |
If there is no underfitting, there is no Cold Posterior Effect
[pre-print]
Misspecification leads to Cold Posterior Effect (CPE) only when the resulting Bayesian posterior underfits. |
PAC-Bayes-Chernoff Bounds for Unbounded Losses
[pre-print]
PAC-Bayes version of the Chernoff bound which solves the open problem of optimizing the free parameter on many PAC-Bayes bounds. |
Last updated on 2024-03-23