English
Related papers

Related papers: Fast Adaptive Weight Noise

200 papers

We propose and investigate new complementary methodologies for estimating predictive variance networks in regression neural networks. We derive a locally aware mini-batching scheme that result in sparse robust gradients, and show how to…

Machine Learning · Statistics 2019-11-05 Nicki S. Detlefsen , Martin Jørgensen , Søren Hauberg

Dropout has been proven to be an effective algorithm for training robust deep networks because of its ability to prevent overfitting by avoiding the co-adaptation of feature detectors. Current explanations of dropout include bagging, naive…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Xu Shen , Xinmei Tian , Tongliang Liu , Fang Xu , Dacheng Tao

We analyze gradient descent with randomly weighted data points in a linear regression model, under a generic weighting distribution. This includes various forms of stochastic gradient descent, importance sampling, but also extends to…

Machine Learning · Statistics 2025-12-12 Gabriel Clara , Yazan Mash'al

We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output…

Machine Learning · Statistics 2017-11-01 Yihao Feng , Dilin Wang , Qiang Liu

Weighted empirical risk minimization is a common approach to prediction under distribution drift. This article studies its out-of-sample prediction error under nonstationarity. We provide a general decomposition of the excess risk into a…

Machine Learning · Statistics 2026-05-19 Tobias Brock , Thomas Nagler

An important problem in training deep networks with high capacity is to ensure that the trained network works well when presented with new inputs outside the training dataset. Dropout is an effective regularization technique to boost the…

Computer Vision and Pattern Recognition · Computer Science 2017-12-06 Mostafa Rahmani , George Atia

Overfitting is a major problem in training machine learning models, specifically deep neural networks. This problem may be caused by imbalanced datasets and initialization of the model parameters, which conforms the model too closely to the…

Neural and Evolutionary Computing · Computer Science 2019-02-26 Hojjat Salehinejad , Shahrokh Valaee

The training phases of Deep neural network~(DNN) consumes enormous processing time and energy. Compression techniques utilizing the sparsity of DNNs can effectively accelerate the inference phase of DNNs. However, it can be hardly used in…

Machine Learning · Computer Science 2018-12-17 Zhuoran Song , Ru Wang , Dongyu Ru , Hongru Huang , Zhenghao Peng , Jing Ke , Xiaoyao Liang , Li Jiang

Assumptions about invariances or symmetries in data can significantly increase the predictive power of statistical models. Many commonly used models in machine learning are constraint to respect certain symmetries in the data, such as…

Machine Learning · Statistics 2022-08-03 Tycho F. A. van der Ouderaa , Mark van der Wilk

Dropout, a stochastic regularisation technique for training of neural networks, has recently been reinterpreted as a specific type of approximate inference algorithm for Bayesian neural networks. The main contribution of the…

Machine Learning · Statistics 2018-07-06 Jiri Hron , Alexander G. de G. Matthews , Zoubin Ghahramani

The inductive biases of trained neural networks are difficult to understand and, consequently, to adapt to new settings. We study the inductive biases of linearizations of neural networks, which we show to be surprisingly good summaries of…

Machine Learning · Statistics 2021-04-29 Wesley J. Maddox , Shuai Tang , Pablo Garcia Moreno , Andrew Gordon Wilson , Andreas Damianou

While variational dropout approaches have been shown to be effective for network sparsification, they are still suboptimal in the sense that they set the dropout rate for each neuron without consideration of the input data. With such…

Machine Learning · Statistics 2019-03-05 Juho Lee , Saehoon Kim , Jaehong Yoon , Hae Beom Lee , Eunho Yang , Sung Ju Hwang

Weight initialization plays a crucial role in the optimization behavior and convergence efficiency of neural networks. Most existing initialization methods, such as Xavier and Kaiming initializations, rely on random sampling and do not…

Machine Learning · Computer Science 2026-02-09 Shaowen Wang , Tariq Alkhalifah

Bayesian Neural Networks (BNNs) provide a tool to estimate the uncertainty of a neural network by considering a distribution over weights and sampling different models for each input. In this paper, we propose a method for uncertainty…

Machine Learning · Computer Science 2024-10-28 Illia Oleksiienko , Dat Thanh Tran , Alexandros Iosifidis

Deep neural networks tend to underestimate uncertainty and produce overly confident predictions. Recently proposed solutions, such as MC Dropout and SDENet, require complex training and/or auxiliary out-of-distribution data. We propose a…

Machine Learning · Computer Science 2021-10-14 Akib Mashrur , Wei Luo , Nayyar A. Zaidi , Antonio Robles-Kelly

Neural networks are popular state-of-the-art models for many different tasks.They are often trained via back-propagation to find a value of the weights that correctly predicts the observed data. Although back-propagation has shown good…

Machine Learning · Statistics 2020-12-29 Simón Rodríguez Santana , Daniel Hernández-Lobato

It is important to understand how the popular regularization method dropout helps the neural network training find a good generalization solution. In this work, we show that the training with dropout finds the neural network with a flatter…

Machine Learning · Computer Science 2022-05-24 Zhongwang Zhang , Hanxu Zhou , Zhi-Qin John Xu

Two main obstacles preventing the widespread adoption of variational Bayesian neural networks are the high parameter overhead that makes them infeasible on large networks, and the difficulty of implementation, which can be thought of as…

Machine Learning · Computer Science 2019-05-24 Oscar Chang , Yuling Yao , David Williams-King , Hod Lipson

Active learning is relevant and challenging for high-dimensional regression models when the annotation of the samples is expensive. Yet most of the existing sampling methods cannot be applied to large-scale problems, consuming too much time…

Machine Learning · Computer Science 2020-01-24 Evgenii Tsymbalov , Maxim Panov , Alexander Shapeev

Learning to infer the conditional posterior model is a key step for robust meta-learning. This paper presents a new Bayesian meta-learning approach called Neural Variational Dropout Processes (NVDPs). NVDPs model the conditional posterior…

Machine Learning · Computer Science 2025-10-23 Insu Jeon , Youngjin Park , Gunhee Kim