11 papers
On importance sampling and independent Metropolis-Hastings with an unbounded weight function
George Deligiannidis, Pierre E. Jacob, El Mahdi Khribch +1
Importance sampling and independent Metropolis-Hastings are among the fundamental building blocks of Monte Carlo methods. Both require a proposal distribution that globally approxi…
Adaptive Diffusion Guidance via Stochastic Optimal Control
Iskander Azangulov, Peter Potaptchik, Qinyu Li +3
Guidance is a cornerstone of modern diffusion models, playing a pivotal role in conditional generation and enhancing the quality of unconditional samples. However, current approach…
Generalization Bounds for Markov Algorithms through Entropy Flow Computations
Benjamin Dupuis, Maxime Haddouche, George Deligiannidis +1
Many learning algorithms can be represented as Markov processes, and understanding their generalization error is a central topic in learning theory. For specific continuous-time no…
Neural Score Matching for High-Dimensional Causal Inference
Oscar Clivio, Fabian Falck, Brieuc Lehmann +2
Traditional methods for matching in causal inference are impractical for high-dimensional datasets. They suffer from the curse of dimensionality: exact matching and coarsened exact…
Schrödinger Bridge Matching for Tree-Structured Costs and Entropic Wasserstein Barycentres
Samuel Howard, Peter Potaptchik, George Deligiannidis
Recent advances in flow-based generative modelling have provided scalable methods for computing the Schrödinger Bridge (SB) between distributions, a dynamic form of entropy-regula…
Rao-Blackwellised Reparameterisation Gradients
Kevin H. Lam, Thang D. Bui, George Deligiannidis +1
Latent Gaussian variables have been popularised in probabilistic machine learning. In turn, gradient estimators are the machinery that facilitates gradient-based optimisation for m…