paper-with-me

Papers

Sampling-based inference for large linear models, with application to linearised Laplace

2022-10-10 · Javier Antorán, Shreyas Padhy, Riccardo Barbano, Eric Nalisnick, David Janz, José Miguel Hernández-Lobato

Large-scale linear models are ubiquitous throughout machine learning, with contemporary application as surrogate models for neural network uncertainty quantification; that is, the linearised Laplace method. Alas, the computational cost associated with Bayesian linear models constrains this method's application to small networks, small output spaces and small datasets. We address this limitation by introducing a scalable sample-based Bayesian inference method for conjugate Gaussian multi-output linear models, together with a matching method for hyperparameter (regularisation) selection. Furthermore, we use a classic feature normalisation method (the g-prior) to resolve a previously highlighted pathology of the linearised Laplace method. Together, these contributions allow us to perform linearised neural network inference with ResNet-18 on CIFAR100 (11M parameters, 100 outputs x 50k datapoints), with ResNet-50 on Imagenet (50M parameters, 1000 outputs x 1.2M datapoints) and with a U-Net on a high-resolution tomographic reconstruction task (2M parameters, 251k output~dimensions).

📄 PDF Abstract BibTeX arXiv:2210.04994

Code (1)

cambridge-mlg/sampled-laplace 공식 구현 jax

Tasks

Bayesian InferenceUncertainty Quantification

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
U-Net 설명 없음

Similar Papers 제목 키워드 기반

Scalable Bayesian Inference in the Era of Deep Learning: From Gaussian Processes to Deep Neural Networks

2024-04-29 · Javier Antoran

Large neural networks trained on large datasets have become the dominant paradigm in machine learning. These systems rely on maximum likelihood point estimates of their parameters, precluding them from expressing model u…

Bayesian InferenceGaussian ProcessesSequential Decision MakingTomographic Reconstructions

Interpolation Filter Design for Sample Rate Independent Audio Effect RNNs

2024-09-24 · Alistair Carson, Alec Wright, Stefan Bilbao

Recurrent neural networks (RNNs) are effective at emulating the non-linear, stateful behavior of analog guitar amplifiers and distortion effects. Unlike the case of direct circuit simulation, RNNs have a fixed sample rat…

Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Prior

2022-07-11 · Riccardo Barbano, Johannes Leuschner, Javier Antorán, Bangti Jin 외

We investigate adaptive design based on a single sparse pilot scan for generating effective scanning strategies for computed tomography reconstruction. We propose a novel approach using the linearised deep image prior. I…

Experimental Design

Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generation

2024-04-01 · Xingwei Tan, Yuxiang Zhou, Gabriele Pergola, Yulan He

Event temporal graphs have been shown as convenient and effective representations of complex temporal relations between events in text. Recent studies, which employ pre-trained language models to auto-regressively genera…

Graph GenerationText Generation

Linearised Laplace Inference in Networks with Normalisation Layers and the Neural g-Prior

2021-11-22 · pproximateinference AABI Symposium 2022 2 · Javier Antoran, James Urquhart Allingham, David Janz, Erik Daxberger 외

We show that for neural networks (NN) with normalisation layers, i.e. batch norm, layer norm, or group norm, the Laplace model evidence does not approximate the volume of a posterior mode and is thus unsuitable for model…

image-classificationImage ClassificationModel Selectionregression