Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Lin, Jihao Andreas"'
A key task in AutoML is to model learning curves of machine learning models jointly as a function of model hyper-parameters and training progression. While Gaussian processes (GPs) are suitable for this task, na\"ive GPs require $\mathcal{O}(n^3m^3)$
Externí odkaz:
http://arxiv.org/abs/2410.09239
Autor:
Lin, Jihao Andreas, Padhy, Shreyas, Mlodozeniec, Bruno, Antorán, Javier, Hernández-Lobato, José Miguel
Scaling hyperparameter optimisation to very large datasets remains an open problem in the Gaussian process community. This paper focuses on iterative methods, which use linear system solvers, like conjugate gradients, alternating projections or stoch
Externí odkaz:
http://arxiv.org/abs/2405.18457
Gaussian processes are a versatile probabilistic machine learning model whose effectiveness often depends on good hyperparameters, which are typically learned by maximising the marginal likelihood. In this work, we consider iterative methods, which u
Externí odkaz:
http://arxiv.org/abs/2405.18328
Autor:
Lin, Jihao Andreas, Padhy, Shreyas, Antorán, Javier, Tripp, Austin, Terenin, Alexander, Szepesvári, Csaba, Hernández-Lobato, José Miguel, Janz, David
As is well known, both sampling from the posterior and computing the mean of the posterior in Gaussian process regression reduces to solving a large linear system of equations. We study the use of stochastic gradient descent for solving this linear s
Externí odkaz:
http://arxiv.org/abs/2310.20581
This paper studies the qualitative behavior and robustness of two variants of Minimal Random Code Learning (MIRACLE) used to compress variational Bayesian neural networks. MIRACLE implements a powerful, conditionally Gaussian variational approximatio
Externí odkaz:
http://arxiv.org/abs/2307.07816
The Laplace approximation provides a closed-form model selection objective for neural networks (NN). Online variants, which optimise NN parameters jointly with hyperparameters, like weight decay strength, have seen renewed interest in the Bayesian de
Externí odkaz:
http://arxiv.org/abs/2307.06093
Bayesian deep learning approaches assume model parameters to be latent random variables and infer posterior distributions to quantify uncertainty, increase safety and trust, and prevent overconfident and unpredictable behavior. However, weight-space
Externí odkaz:
http://arxiv.org/abs/2307.06055
Autor:
Tazi, Kenza, Lin, Jihao Andreas, Viljoen, Ross, Gardner, Alex, John, ST, Ge, Hong, Turner, Richard E.
Gaussian Processes (GPs) offer an attractive method for regression over small, structured and correlated datasets. However, their deployment is hindered by computational costs and limited guidelines on how to apply GPs beyond simple low-dimensional d
Externí odkaz:
http://arxiv.org/abs/2307.03093
Autor:
Lin, Jihao Andreas, Antorán, Javier, Padhy, Shreyas, Janz, David, Hernández-Lobato, José Miguel, Terenin, Alexander
Publikováno v:
Advances in Neural Information Processing Systems, 2023
Gaussian processes are a powerful framework for quantifying uncertainty and for sequential decision-making but are limited by the requirement of solving linear systems. In general, this has a cubic cost in dataset size and is sensitive to conditionin
Externí odkaz:
http://arxiv.org/abs/2306.11589
While 2D object detection has improved significantly over the past, real world applications of computer vision often require an understanding of the 3D layout of a scene. Many recent approaches to 3D detection use LiDAR point clouds for prediction. W
Externí odkaz:
http://arxiv.org/abs/2011.09977