9 papers
Soft Specialists: -Rényi Ensembles for Uncertainty-Aware LLM Post-Training
Paula Cordero-Encinar, Georgy Tyukin, Andrew B. Duncan
Existing training approaches for large language models learn a single set of parameters, based on large volumes of data, which is typically heterogeneous, conflicting and often out…
Weak Functional Inequalities for Perturbed Measures
Patrick Cattiaux, Paula Cordero-Encinar, Arnaud Guillin
This paper is a follow up to an article by two of the authors dedicated to the study of Poincaré and logarithmic Sobolev inequalities for measures of the form where…
Diffusion Path Samplers via Sequential Monte Carlo
James Matthew Young, Paula Cordero-Encinar, Sebastian Reich +2
We develop diffusion-based samplers for target distributions known up to a normalising constant. To this end, we rely on the well-known diffusion path that smoothly interpolates be…
Diffusion annealed Langevin dynamics: a theoretical study
Patrick Cattiaux, Paula Cordero-Encinar, Arnaud Guillin
In this work we study the diffusion annealed Langevin dynamics, a score-based diffusion process recently introduced in the theory of generative models and which is an alternative t…
Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMs
Paula Cordero-Encinar, Andrew B. Duncan
Recent advances such as self-consistency and test-time reinforcement learning (TTRL) improve the reliability of large language models (LLMs) without additional supervision, yet the…
Sampling by averaging: A multiscale approach to score estimation
Paula Cordero-Encinar, Andrew B. Duncan, Sebastian Reich +1
We introduce a novel framework for efficient sampling from complex, unnormalised target distributions by exploiting multiscale dynamics. Traditional score-based sampling methods ei…
Non-asymptotic Analysis of Diffusion Annealed Langevin Monte Carlo for Generative Modelling
Paula Cordero-Encinar, O. Deniz Akyildiz, Andrew B. Duncan
We investigate the theoretical properties of general diffusion (interpolation) paths and their Langevin Monte Carlo implementation, referred to as diffusion annealed Langevin Monte…
Deep Optimal Sensor Placement for Black Box Stochastic Simulations
Paula Cordero-Encinar, Tobias Schröder, Peter Yatsyshin +1
Selecting cost-effective optimal sensor configurations for subsequent inference of parameters in black-box stochastic systems faces significant computational barriers. We propose a…
Proximal Interacting Particle Langevin Algorithms
Paula Cordero Encinar, Francesca R. Crucinio, O. Deniz Akyildiz
We introduce a class of algorithms, termed proximal interacting particle Langevin algorithms (PIPLA), for inference and learning in latent variable models whose joint probability d…