paper-with-me

Papers

Subspace Inference for Bayesian Deep Learning

2019-07-17 · Pavel Izmailov, Wesley J. Maddox, Polina Kirichenko, Timur Garipov, Dmitry Vetrov, Andrew Gordon Wilson

Bayesian inference was once a gold standard for learning with neural networks, providing accurate full predictive distributions and well calibrated uncertainty. However, scaling Bayesian inference techniques to deep neural networks is challenging due to the high dimensionality of the parameter space. In this paper, we construct low-dimensional subspaces of parameter space, such as the first principal components of the stochastic gradient descent (SGD) trajectory, which contain diverse sets of high performing models. In these subspaces, we are able to apply elliptical slice sampling and variational inference, which struggle in the full parameter space. We show that Bayesian model averaging over the induced posterior in these subspaces produces accurate predictions and well calibrated predictive uncertainty for both regression and image classification.

📄 PDF Abstract BibTeX arXiv:1907.07504

Code (1)

wjmaddox/drbayes 공식 구현 pytorch

Tasks

Bayesian InferenceDeep Learningimage-classificationImage ClassificationregressionVariational Inference

Similar Papers 제목 키워드 기반

Learning Active Subspaces for Effective and Scalable Uncertainty Quantification in Deep Neural Networks

2023-09-06 · Sanket Jantre, Nathan M. Urban, Xiaoning Qian, Byung-Jun Yoon

Bayesian inference for neural networks, or Bayesian deep learning, has the potential to provide well-calibrated predictions with quantified uncertainty and robustness. However, the main hurdle for Bayesian deep learning …

Bayesian InferenceDeep LearningUncertainty QuantificationVariational Inference

Scalable Bayesian Low-Rank Adaptation of Large Language Models via Stochastic Variational Subspace Inference

2025-06-26 · Colin Samplawski, Adam D. Cobb, Manoj Acharya, Ramneet Kaur 외

Despite their widespread use, large language models (LLMs) are known to hallucinate incorrect information and be poorly calibrated. This makes the uncertainty quantification of these models of critical importance, especi…

Bayesian InferenceUncertainty QuantificationVariational Inference

Optimal Subspace Inference for the Laplace Approximation of Bayesian Neural Networks

2025-02-04 · Josua Faller, Jörg Martin

Subspace inference for neural networks assumes that a subspace of their parameter space suffices to produce a reliable uncertainty quantification. In this work, we mathematically derive the optimal subspace model to a Ba…

Bayesian InferenceUncertainty Quantification

Training Bayesian Neural Networks with Sparse Subspace Variational Inference

2024-02-16 · Junbo Li, Zichen Miao, Qiang Qiu, Ruqi Zhang

Bayesian neural networks (BNNs) offer uncertainty quantification but come with the downside of substantially increased training and inference costs. Sparse BNNs have been investigated for efficient inference, typically b…

Uncertainty QuantificationVariational Inference

Bayesian Semi-structured Subspace Inference

2024-01-23 · Daniel Dold, David Rügamer, Beate Sick, Oliver Dürr

Semi-structured regression models enable the joint modeling of interpretable structured and complex unstructured feature effects. The structured model part is inspired by statistical models and can be used to infer the i…

regression