Biography

Francisco completed his PhD in the Computer Laboratory in 2025. He was interested in the duality between optimisation and sampling with a focus on applications. In particular, exploring stochastic control based methodologies (e.g. Schrödinger Bridges) in practical contexts such as Bayesian machine learning as well as generative modelling, for example developing better samplers for Bayesian Deep Learning. Overall, he aimed to focus on dynamical formulations of different learning tasks to explore physically motivated efficient algorithms, always keeping the practical/application component as the main focus.

Recent Publications

Dimensionality Reduction as Probabilistic Inference

Aditya Ravuri, Francisco Vargas, Vidhi Lalchand, Neil D. Lawrence

:

Bayesian learning via neural Schrödinger–Föllmer flows

Francisco Vargas, Andrius Ovsianas, David Fernandes, Mark Girolami, Neil D. Lawrence, Nikolas Nüsken

Statistics and Computing, 33(3):

Adversarial Concept Erasure in Kernel Space

Shauli Ravfogel, Francisco Vargas, Yoav Goldberg, Ryan Cotterell

:

Efficient Representations for Privacy-Preserving Inference

Han Xuanyuan, Francisco Vargas, Stephen Cummins

:

Solving Schrödinger Bridges via Maximum Likelihood

Francisco Vargas, Pierre Thodoroff, Austen Lamacraft, Neil D. Lawrence

Entropy, 23(9):1134