Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Sharrock, Louis"'
In recent years, interest in gradient-based optimization over Riemannian manifolds has surged. However, a significant challenge lies in the reliance on hyperparameters, especially the learning rate, which requires meticulous tuning by practitioners t
Externí odkaz:
http://arxiv.org/abs/2406.02296
Continuous normalizing flows (CNFs) learn the probability path between a reference and a target density by modeling the vector field generating said path using neural networks. Recently, Lipman et al. (2022) introduced a simple and inexpensive method
Externí odkaz:
http://arxiv.org/abs/2405.14392
We introduce a suite of new particle-based algorithms for sampling in constrained domains which are entirely learning rate free. Our approach leverages coin betting ideas from convex optimisation, and the viewpoint of constrained sampling as a mirror
Externí odkaz:
http://arxiv.org/abs/2305.14943
We introduce two new particle-based algorithms for learning latent variable models via marginal maximum likelihood estimation, including one which is entirely tuning-free. Our methods are based on the perspective of marginal maximum likelihood estima
Externí odkaz:
http://arxiv.org/abs/2305.14916
Autor:
Sharrock, Louis, Nemeth, Christopher
In recent years, particle-based variational inference (ParVI) methods such as Stein variational gradient descent (SVGD) have grown in popularity as scalable methods for Bayesian inference. Unfortunately, the properties of such methods invariably depe
Externí odkaz:
http://arxiv.org/abs/2301.11294
We introduce Sequential Neural Posterior Score Estimation (SNPSE), a score-based method for Bayesian inference in simulator-based models. Our method, inspired by the remarkable success of score-based methods in generative modelling, leverages conditi
Externí odkaz:
http://arxiv.org/abs/2210.04872
Autor:
Sharrock, Louis
We analyse the asymptotic properties of a continuous-time, two-timescale stochastic approximation algorithm designed for stochastic bilevel optimisation problems in continuous-time models. We obtain the weak convergence rate of this algorithm in the
Externí odkaz:
http://arxiv.org/abs/2206.06995
Publikováno v:
Entropy 2021, 23(10), 1281
Generative modelling is an important unsupervised task in machine learning. In this work, we study a hybrid quantum-classical approach to this task, based on the use of a quantum circuit Born machine. In particular, we consider training a quantum cir
Externí odkaz:
http://arxiv.org/abs/2110.04253
We consider the problem of parameter estimation for a stochastic McKean-Vlasov equation, and the associated system of weakly interacting particles. We study two cases: one in which we observe multiple independent trajectories of the McKean-Vlasov SDE
Externí odkaz:
http://arxiv.org/abs/2106.13751
Autor:
Sharrock, Louis, Kantas, Nikolas
Publikováno v:
SIAM/ASA J. Uncertainty Quantification, 2022, 10(1), 55-95
In this paper, we consider the problem of jointly performing online parameter estimation and optimal sensor placement for a partially observed infinite dimensional linear diffusion process. We present a novel solution to this problem in the form of a
Externí odkaz:
http://arxiv.org/abs/2009.08693