English
Related papers

Related papers: Fast and Scalable Bayesian Deep Learning by Weight…

200 papers

We propose SWA-Gaussian (SWAG), a simple, scalable, and general purpose approach for uncertainty representation and calibration in deep learning. Stochastic Weight Averaging (SWA), which computes the first moment of stochastic gradient…

Machine Learning · Computer Science 2020-01-01 Wesley Maddox , Timur Garipov , Pavel Izmailov , Dmitry Vetrov , Andrew Gordon Wilson

We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, machine translation,…

Modern neural network architectures have achieved remarkable accuracies but remain highly dependent on their training data, often lacking interpretability in their learned mappings. While effective on large datasets, they tend to overfit on…

Machine Learning · Computer Science 2025-03-19 Pavia Bera , Sanjukta Bhanja

The vast majority of successful deep neural networks are trained using variants of stochastic gradient descent (SGD) algorithms. Recent attempts to improve SGD can be broadly categorized into two approaches: (1) adaptive learning rate…

Machine Learning · Computer Science 2019-12-04 Michael R. Zhang , James Lucas , Geoffrey Hinton , Jimmy Ba

Despite the dominant role of deep models in machine learning, limitations persist, including overconfident predictions, susceptibility to adversarial attacks, and underestimation of variability in predictions. The Bayesian paradigm provides…

Machine Learning · Statistics 2025-06-18 Alisa Sheinkman , Sara Wade

One of the core problems of modern statistics is to approximate difficult-to-compute probability densities. This problem is especially important in Bayesian statistics, which frames all inference about unknown quantities as a calculation…

Computation · Statistics 2018-05-11 David M. Blei , Alp Kucukelbir , Jon D. McAuliffe

Bayesian neural networks and deep ensembles represent two modern paradigms of uncertainty quantification in deep learning. Yet these approaches struggle to scale mainly due to memory inefficiency issues, since they require parameter storage…

Machine Learning · Statistics 2021-11-24 Hippolyt Ritter , Martin Kukla , Cheng Zhang , Yingzhen Li

Uncertainty estimation for unlabeled data is crucial to active learning. With a deep neural network employed as the backbone model, the data selection process is highly challenging due to the potential over-confidence of the model…

Machine Learning · Computer Science 2024-02-14 Xingjian Li , Pengkun Yang , Yangcheng Gu , Xueying Zhan , Tianyang Wang , Min Xu , Chengzhong Xu

Adam is the de facto optimization algorithm for several deep learning applications, but an understanding of its implicit bias and how it differs from other algorithms, particularly standard first-order methods such as (stochastic) gradient…

Machine Learning · Computer Science 2025-10-27 Bhavya Vasudeva , Jung Whan Lee , Vatsal Sharan , Mahdi Soltanolkotabi

Gradient-based first-order adaptive optimization methods such as the Adam optimizer are prevalent in training artificial networks, achieving the state-of-the-art results. This work attempts to answer the question whether it is viable for…

Neural and Evolutionary Computing · Computer Science 2022-12-20 Yukun Yang , Peng Li

To obtain uncertainty estimates with real-world Bayesian deep learning models, practical inference approximations are needed. Dropout variational inference (VI) for example has been used for machine vision and medical applications, but VI…

Machine Learning · Computer Science 2017-03-09 Yingzhen Li , Yarin Gal

Adaptive gradient methods, which adopt historical gradient information to automatically adjust the learning rate, despite the nice property of fast convergence, have been observed to generalize worse than stochastic gradient descent (SGD)…

Machine Learning · Computer Science 2020-06-24 Jinghui Chen , Dongruo Zhou , Yiqi Tang , Ziyan Yang , Yuan Cao , Quanquan Gu

Active learning methods for neural networks are usually based on greedy criteria which ultimately give a single new design point for the evaluation. Such an approach requires either some heuristics to sample a batch of design points at one…

Machine Learning · Computer Science 2020-01-28 Evgenii Tsymbalov , Sergei Makarychev , Alexander Shapeev , Maxim Panov

Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due to non-smooth components such as ReLU activations and quantization operators. In such…

Machine Learning · Computer Science 2026-05-29 Ruoran Xu , Borong She , Xiaobo Jin , Qiufeng Wang

Bayesian neural networks (BNNs) hold great promise as a flexible and principled solution to deal with uncertainty when learning from finite data. Among approaches to realize probabilistic inference in deep neural networks, variational Bayes…

Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification - a critical requirement for real-world applications. Bayesian Neural Networks (BNN) are…

Machine Learning · Computer Science 2023-12-27 Gianni Franchi , Olivier Laurent , Maxence Leguéry , Andrei Bursuc , Andrea Pilzer , Angela Yao

We introduce a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop. It regularises the weights by minimising a compression…

Machine Learning · Statistics 2015-05-22 Charles Blundell , Julien Cornebise , Koray Kavukcuoglu , Daan Wierstra

During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function. Only this final state of the weights is typically kept for testing, while the…

Machine Learning · Computer Science 2021-03-26 Gianni Franchi , Andrei Bursuc , Emanuel Aldea , Severine Dubuisson , Isabelle Bloch

Variational inference (VI) is a computationally efficient and scalable methodology for approximate Bayesian inference. It strikes a balance between accuracy of uncertainty quantification and practical tractability. It excels at generative…

Machine Learning · Statistics 2025-04-15 Alex Glyn-Davies , Arnaud Vadeboncoeur , O. Deniz Akyildiz , Ieva Kazlauskaite , Mark Girolami

Learning rate adaptation is a popular topic in machine learning. Gradient Descent trains neural nerwork with a fixed learning rate. Learning rate adaptation is proposed to accelerate the training process through adjusting the step size in…

Machine Learning · Computer Science 2022-10-20 Bozhou Chen , Hongzhi Wang , Chenmin Ba