English
Related papers

Related papers: Improving Normalization with the James-Stein Estim…

200 papers

Many statistical applications require an estimate of a covariance matrix and/or its inverse. When the matrix dimension is large compared to the sample size, which happens frequently, the sample covariance matrix is known to perform poorly…

Statistics Theory · Mathematics 2012-07-24 Olivier Ledoit , Michael Wolf

The mechanisms by which certain training interventions, such as increasing learning rates and applying batch normalization, improve the generalization of deep networks remains a mystery. Prior works have speculated that "flatter" solutions…

Machine Learning · Computer Science 2023-05-25 Simran Kaur , Jeremy Cohen , Zachary C. Lipton

Estimating the ratio of two probability densities from finitely many samples, is a central task in machine learning and statistics. In this work, we show that a large class of kernel methods for density ratio estimation suffers from error…

Machine Learning · Computer Science 2024-06-04 Lukas Gruber , Markus Holzleitner , Johannes Lehner , Sepp Hochreiter , Werner Zellinger

The impact of gradient noise on training deep models is widely acknowledged but not well understood. In this context, we study the distribution of gradients during training. We introduce a method, Gradient Clustering, to minimize the…

Machine Learning · Computer Science 2020-07-10 Fartash Faghri , David Duvenaud , David J. Fleet , Jimmy Ba

When imaging through a semi-reflective medium such as glass, the reflection of another scene can often be found in the captured images. It degrades the quality of the images and affects their subsequent analyses. In this paper, a novel deep…

Image and Video Processing · Electrical Eng. & Systems 2022-08-11 Tingtian Li , Yuk-Hee Chan , Daniel P. K. Lun

Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks. In this paper, we argue that such a metric is highly beneficial for training predictive models, even when we do not…

Machine Learning · Statistics 2019-11-01 Jayaraman J. Thiagarajan , Bindya Venkatesh , Deepta Rajan

When extracting the weak lensing shear signal, one may employ either locally normalized or globally normalized shear estimators. The former is the standard approach when estimating cluster masses, while the latter is the more common method…

Cosmology and Nongalactic Astrophysics · Physics 2015-05-19 Eduardo Rozo , Hao-Yi Wu , Fabian Schmidt

The successful training of deep neural networks requires addressing challenges such as overfitting, numerical instabilities leading to divergence, and increasing variance in the residual stream. A common solution is to apply regularization…

Machine Learning · Computer Science 2025-11-20 Jörg K. H. Franke , Urs Spiegelhalter , Marianna Nezhurina , Jenia Jitsev , Frank Hutter , Michael Hefenbrock

Segmentation of very large images is a common problem in microscopy, medical imaging or remote sensing. The problem is usually addressed by sliding window inference, which can theoretically lead to seamlessly stitched predictions. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Elena Buglakova , Anwai Archit , Edoardo D'Imprima , Julia Mahamid , Constantin Pape , Anna Kreshuk

Batch Normalization is a commonly used trick to improve the training of deep neural networks. These neural networks use L2 regularization, also called weight decay, ostensibly to prevent overfitting. However, we show that L2 regularization…

Machine Learning · Computer Science 2017-06-19 Twan van Laarhoven

Embeddings play a pivotal role across various disciplines, offering compact representations of complex data structures. Randomized methods like Johnson-Lindenstrauss (JL) provide state-of-the-art and essentially unimprovable theoretical…

Machine Learning · Statistics 2024-12-11 Nikos Tsikouras , Constantine Caramanis , Christos Tzamos

Various normalization layers have been proposed to help the training of neural networks. Group Normalization (GN) is one of the effective and attractive studies that achieved significant performances in the visual recognition task. Despite…

Computer Vision and Pattern Recognition · Computer Science 2022-07-06 Agus Gunawan , Xu Yin , Kang Zhang

We consider the problem of efficiently computing the maximum likelihood estimator in Generalized Linear Models (GLMs) when the number of observations is much larger than the number of coefficients ($n \gg p \gg 1$). In this regime,…

Machine Learning · Statistics 2015-12-01 Murat A. Erdogdu

We propose two novel samplers to generate high-quality samples from a given (un-normalized) probability density. Motivated by the success of generative adversarial networks, we construct our samplers using deep neural networks that…

Machine Learning · Statistics 2021-02-10 Tianyang Hu , Zixiang Chen , Hanxi Sun , Jincheng Bai , Mao Ye , Guang Cheng

Image reconstruction methods based on deep neural networks have shown outstanding performance, equalling or exceeding the state-of-the-art results of conventional approaches, but often do not provide uncertainty information about the…

Computer Vision and Pattern Recognition · Computer Science 2020-12-01 Riccardo Barbano , Željko Kereta , Chen Zhang , Andreas Hauptmann , Simon Arridge , Bangti Jin

Deep learning based image steganalysis has attracted increasing attentions in recent years. Several Convolutional Neural Network (CNN) models have been proposed and achieved state-of-the-art performances on detecting steganography. In this…

Multimedia · Computer Science 2017-11-22 Songtao Wu , Sheng-hua Zhong , Yan Liu

In this paper, we propose Selective Output Smoothing Regularization, a novel regularization method for training the Convolutional Neural Networks (CNNs). Inspired by the diverse effects on training from different samples, Selective Output…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Xuan Cheng , Tianshu Xie , Xiaomin Wang , Qifeng Weng , Minghui Liu , Jiali Deng , Ming Liu

In this paper we are concerned with fully automatic and locally adaptive estimation of functions in a "signal + noise"-model where the regression function may additionally be blurred by a linear operator, e.g. by a convolution. To this end,…

Applications · Statistics 2015-03-17 Klaus Frick , Philipp Marnitz , Axel Munk

Based on the manifold hypothesis, real-world data often lie on a low-dimensional manifold, while normalizing flows as a likelihood-based generative model are incapable of finding this manifold due to their structural constraints. So, one…

Machine Learning · Computer Science 2022-06-08 Seyedeh Fatemeh Razavi , Mohammad Mahdi Mehmanchi , Reshad Hosseini , Mostafa Tavassolipour

With the development of deep learning, Deep Metric Learning (DML) has achieved great improvements in face recognition. Specifically, the widely used softmax loss in the training process often bring large intra-class variations, and feature…

Computer Vision and Pattern Recognition · Computer Science 2018-05-02 Bowen Wu , Huaming Wu , Monica M. Y. Zhang