70 citations · 369 across the 48 of their papers we have counts for
30 papers · 1 filter
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-regular…
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…
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…
Conditioning Diffusions Using Malliavin Calculus
Jakiw Pidstrigach, Elizabeth Baker, Carles Domingo-Enrich +2
In generative modelling and stochastic optimal control, a central computational task is to modify a reference diffusion process to maximise a given terminal-time reward. Most exist…
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…
Linear Convergence of Diffusion Models Under the Manifold Hypothesis
Peter Potaptchik, Iskander Azangulov, George Deligiannidis
Score-matching generative models have proven successful at sampling from complex high-dimensional data distributions. In many applications, this distribution is believed to concent…
Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions
Iskander Azangulov, George Deligiannidis, Judith Rousseau
Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used f…
Differentiable Cost-Parameterized Monge Map Estimators
Samuel Howard, George Deligiannidis, Patrick Rebeschini +1
Within the field of optimal transport (OT), the choice of ground cost is crucial to ensuring that the optimality of a transport map corresponds to usefulness in real-world applicat…
Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets
Benjamin Dupuis, Paul Viallard, George Deligiannidis +1
We propose data-dependent uniform generalization bounds by approaching the problem from a PAC-Bayesian perspective. We first apply the PAC-Bayesian framework on "random sets" in a…
Particle Denoising Diffusion Sampler
Angus Phillips, Hai-Dang Dau, Michael John Hutchinson +3
Denoising diffusion models have become ubiquitous for generative modeling. The core idea is to transport the data distribution to a Gaussian by using a diffusion. Approximate sampl…
Nearly -Linear Convergence Bounds for Diffusion Models via Stochastic Localization
Joe Benton, Valentin De Bortoli, Arnaud Doucet +1
Denoising diffusions are a powerful method to generate approximate samples from high-dimensional data distributions. Recent results provide polynomial bounds on their convergence r…
On the Expected Size of Conformal Prediction Sets
Guneet S. Dhillon, George Deligiannidis, Tom Rainforth
While conformal predictors reap the benefits of rigorous statistical guarantees on their error frequency, the size of their corresponding prediction sets is critical to their pract…
A Unified Framework for U-Net Design and Analysis
Christopher Williams, Fabian Falck, George Deligiannidis +3
U-Nets are a go-to, state-of-the-art neural architecture across numerous tasks for continuous signals on a square such as images and Partial Differential Equations (PDE), however t…
Error Bounds for Flow Matching Methods
Joe Benton, George Deligiannidis, Arnaud Doucet
Score-based generative models are a popular class of generative modelling techniques relying on stochastic differential equations (SDE). From their inception, it was realized that…
Generalization Bounds with Data-dependent Fractal Dimensions
Benjamin Dupuis, George Deligiannidis, Umut Şimşekli
Providing generalization guarantees for modern neural networks has been a crucial task in statistical learning. Recently, several studies have attempted to analyze the generalizati…
A Multi-Resolution Framework for U-Nets with Applications to Hierarchical VAEs
Fabian Falck, Christopher Williams, Dominic Danks +5
U-Net architectures are ubiquitous in state-of-the-art deep learning, however their regularisation properties and relationship to wavelets are understudied. In this paper, we formu…
From Denoising Diffusions to Denoising Markov Models
Joe Benton, Yuyang Shi, Valentin De Bortoli +2
Denoising diffusions are state-of-the-art generative models exhibiting remarkable empirical performance. They work by diffusing the data distribution into a Gaussian distribution a…
Generalisation under gradient descent via deterministic PAC-Bayes
Eugenio Clerico, Tyler Farghly, George Deligiannidis +2
We establish disintegrated PAC-Bayesian generalisation bounds for models trained with gradient descent methods or continuous gradient flows. Contrary to standard practice in the PA…
Ranking In Generalized Linear Bandits
Amitis Shidani, George Deligiannidis, Arnaud Doucet
We study the ranking problem in generalized linear bandits. At each time, the learning agent selects an ordered list of items and observes stochastic outcomes. In recommendation sy…
A Continuous Time Framework for Discrete Denoising Models
Andrew Campbell, Joe Benton, Valentin De Bortoli +3
We provide the first complete continuous time framework for denoising diffusion models of discrete data. This is achieved by formulating the forward noising process and correspondi…
Chained Generalisation Bounds
Eugenio Clerico, Amitis Shidani, George Deligiannidis +1
This work discusses how to derive upper bounds for the expected generalisation error of supervised learning algorithms by means of the chaining technique. By developing a general t…
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…
Conditional Simulation Using Diffusion Schrödinger Bridges
Yuyang Shi, Valentin De Bortoli, George Deligiannidis +1
Denoising diffusion models have recently emerged as a powerful class of generative models. They provide state-of-the-art results, not only for unconditional simulation, but also wh…
Quantitative Uniform Stability of the Iterative Proportional Fitting Procedure
George Deligiannidis, Valentin De Bortoli, Arnaud Doucet
We establish the uniform in time stability, w.r.t. the marginals, of the Iterative Proportional Fitting Procedure, also known as Sinkhorn algorithm, used to solve entropy-regularis…