Code & Projects

Spearmint Bayesian optimization codebase — the canonical research implementation maintained for new acquisition functions and constraints.

Parallel Predictive Entropy Search for Multi-objective Bayesian Optimization with Constraints (PPESMOC). Reference implementation for the 2020 paper.

Many-objective Bayesian optimization tools, extending Spearmint to handle problems with high-dimensional objective spaces.

Fork of BoTorch (Bayesian optimization in PyTorch) with experimental modifications for ongoing research.

Experiments on simplex transformations for Bayesian optimization implemented on top of PyTorch / BoTorch.

Multi-class Gaussian Process Classification with Noisy Inputs — reference code for the stat.ML paper applied to astronomical data.

Replication code for "Bayesian optimization of the PC algorithm for learning Gaussian Bayesian networks" (CAEPIA 2018, LNAI).

BO full bio search optimization package — tooling around end-to-end pipelines combining BO and biological search problems.

Microeconomic agents trained with Deep Reinforcement Learning on microeconomic market simulators. Companion code for the 2024 multi-agent RL paper.

PyTorch fork of Stable Baselines — reliable implementations of reinforcement learning algorithms used as the backbone in several research projects.

Training framework for Stable Baselines3 with hyperparameter optimization driven by BoTorch.

Probabilistic Causal Graphs (PCGs) Python ↔ Prolog implementation, with a fake-news classifier built on top of uncertainty-weighted causal graphs.

Optimization of Φ (phi) — experimental code for Integrated Information Theory metrics used in the 2022 IIT paper.

Notebooks for the Gaussian Processes and Bayesian Optimization course at the UPM summer school. Hands-on material with derivations and code.

BoTorch tutorials in Jupyter notebook format, ready to be launched on Google Colab. Practical entry point for new BO practitioners.

Earlier edition of the GP & BO summer school notebooks — preserved for reference.

Data science tutorials covering core ML concepts, used in undergraduate teaching at Comillas.

Curated list of links to high-quality machine learning books available freely online. A reading map for students.