paper-with-me

Papers

Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference

2022-03-07 · Luca Rendsburg, Agustinus Kristiadi, Philipp Hennig, Ulrike Von Luxburg

Full Bayesian posteriors are rarely analytically tractable, which is why real-world Bayesian inference heavily relies on approximate techniques. Approximations generally differ from the true posterior and require diagnostic tools to assess whether the inference can still be trusted. We investigate a new approach to diagnosing approximate inference: the approximation mismatch is attributed to a change in the inductive bias by treating the approximations as exact and reverse-engineering the corresponding prior. We show that the problem is more complicated than it appears to be at first glance, because the solution generally depends on the observation. By reframing the problem in terms of incompatible conditional distributions we arrive at a natural solution: the Gibbs prior. The resulting diagnostic is based on pseudo-Gibbs sampling, which is widely applicable and easy to implement. We illustrate how the Gibbs prior can be used to discover the inductive bias in a controlled Gaussian setting and for a variety of Bayesian models and approximations.

📄 PDF Abstract BibTeX arXiv:2203.03353

Code (1)

tml-tuebingen/gibbs-prior-diagnostic 공식 구현

Tasks

Bayesian InferenceDiagnosticInductive Bias

Similar Papers 제목 키워드 기반

Noether Networks: Meta-Learning Useful Conserved Quantities

2021-12-06 · NeurIPS 2021 12 · Ferran Alet, Dylan Doblar, Allan Zhou, Joshua Tenenbaum 외

Progress in machine learning (ML) stems from a combination of data availability, computational resources, and an appropriate encoding of inductive biases. Useful biases often exploit symmetries in the prediction problem,…

Meta-LearningPredictionTranslation

VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges

2022-01-21 · Attila Lengyel, Robert-Jan Bruintjes, Marcos Baptista Rios, Osman Semih Kayhan 외

The second edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges featured five data-impaired challenges, where models are trained from scratch on a reduced number of training samp…

Data AugmentationDeep LearningTransfer Learning

C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder

2023-10-26 · NeurIPS 2023 11 · Xiaoyu Liu, Jiaxin Yuan, Bang An, Yuancheng Xu 외

Representation learning assumes that real-world data is generated by a few semantically meaningful generative factors (i.e., sources of variation) and aims to discover them in the latent space. These factors are expected…

DisentanglementInductive BiasRepresentation Learning

Listening to the Noise: Blind Denoising with Gibbs Diffusion

2024-02-29 · David Heurtel-Depeiges, Charles C. Margossian, Ruben Ohana, Bruno Régaldo-Saint Blancard

In recent years, denoising problems have become intertwined with the development of deep generative models. In particular, diffusion models are trained like denoisers, and the distribution they model coincide with denois…

Bayesian InferenceDenoisingDiagnostic

Deep Audio Priors Emerge From Harmonic Convolutional Networks

2020-05-01 · ICLR 2020 1 · Zhoutong Zhang, Yunyun Wang, Chuang Gan, Jiajun Wu 외

Convolutional neural networks (CNNs) excel in image recognition and generation. Among many efforts to explain their effectiveness, experiments show that CNNs carry strong inductive biases that capture natural image prior…