English
Related papers

Related papers: Weight Normalization: A Simple Reparameterization …

200 papers

Training neural networks with batch normalization and weight decay has become a common practice in recent years. In this work, we show that their combined use may result in a surprising periodic behavior of optimization dynamics: the…

Machine Learning · Computer Science 2022-01-19 Ekaterina Lobacheva , Maxim Kodryan , Nadezhda Chirkova , Andrey Malinin , Dmitry Vetrov

Batch Normalization (BN) is essential to effectively train state-of-the-art deep Convolutional Neural Networks (CNN). It normalizes inputs to the layers during training using the statistics of each mini-batch. In this work, we study BN from…

Machine Learning · Computer Science 2018-11-16 Mahdi M. Kalayeh , Mubarak Shah

We introduce repriorisation, a data-dependent reparameterisation which transforms a Bayesian neural network (BNN) posterior to a distribution whose KL divergence to the BNN prior vanishes as layer widths grow. The repriorisation map acts…

Machine Learning · Statistics 2022-06-16 Jiri Hron , Roman Novak , Jeffrey Pennington , Jascha Sohl-Dickstein

Weight-sharing is ubiquitous in deep learning. Motivated by this, we propose a "weight-sharing regularization" penalty on the weights $w \in \mathbb{R}^d$ of a neural network, defined as $\mathcal{R}(w) = \frac{1}{d - 1}\sum_{i > j}^d |w_i…

Machine Learning · Computer Science 2024-03-12 Mehran Shakerinava , Motahareh Sohrabi , Siamak Ravanbakhsh , Simon Lacoste-Julien

We introduce a method for fast estimation of data-adapted, spatio-temporally dependent regularization parameter-maps for variational image reconstruction, focusing on total variation (TV)-minimization. Our approach is inspired by recent…

Deep Neural Networks (DNNs) have become increasingly popular in computer vision, natural language processing, and other areas. However, training and fine-tuning a deep learning model is computationally intensive and time-consuming. We…

Machine Learning · Computer Science 2018-07-04 Jiayi Liu , Samarth Tripathi , Unmesh Kurup , Mohak Shah

Existing neural networks are memory-consuming and computationally intensive, making deploying them challenging in resource-constrained environments. However, there are various methods to improve their efficiency. Two such methods are…

Machine Learning · Computer Science 2023-11-10 Anastasiia Prutianova , Alexey Zaytsev , Chung-Kuei Lee , Fengyu Sun , Ivan Koryakovskiy

Quantization of deep neural networks is a promising approach that reduces the inference cost, making it feasible to run deep networks on resource-restricted devices. Inspired by existing methods, we propose a new framework to learn the…

Machine Learning · Computer Science 2022-02-28 Amir Ardakani , Arash Ardakani , Brett Meyer , James J. Clark , Warren J. Gross

Data augmentation is an effective technique to improve the generalization of deep neural networks. However, previous data augmentation methods usually treat the augmented samples equally without considering their individual impacts on the…

Machine Learning · Computer Science 2021-03-17 Mingyang Yi , Lu Hou , Lifeng Shang , Xin Jiang , Qun Liu , Zhi-Ming Ma

This paper proposes a novel, efficient transfer learning method, called Scalable Weight Reparametrization (SWR) that is efficient and effective for multiple downstream tasks. Efficient transfer learning involves utilizing a pre-trained…

Machine Learning · Computer Science 2023-02-28 Byeonggeun Kim , Jun-Tae Lee , Seunghan yang , Simyung Chang

Many machine learning tasks that involve predicting an output response can be solved by training a weighted regression model. Unfortunately, the predictive power of this type of models may severely deteriorate under low sample sizes or…

Machine Learning · Statistics 2021-10-01 Tam Le , Truyen Nguyen , Makoto Yamada , Jose Blanchet , Viet Anh Nguyen

The minibatch stochastic gradient descent method (SGD) is widely applied in deep learning due to its efficiency and scalability that enable training deep networks with a large volume of data. Particularly in the distributed setting, SGD is…

Machine Learning · Computer Science 2020-11-19 Qiwei Yuan , Weizhe Hua , Yi Zhou , Cunxi Yu

Appropriate weight initialization has been of key importance to successfully train neural networks. Recently, batch normalization has diminished the role of weight initialization by simply normalizing each layer based on batch statistics.…

Computer Vision and Pattern Recognition · Computer Science 2022-08-03 Pedro Hermosilla , Michael Schelling , Tobias Ritschel , Timo Ropinski

Histogram-based template fits are the main technique used for estimating parameters of high energy physics Monte Carlo generators. Parametrized neural network reweighting can be used to extend this fitting procedure to many dimensions and…

High Energy Physics - Phenomenology · Physics 2021-04-08 Anders Andreassen , Shih-Chieh Hsu , Benjamin Nachman , Natchanon Suaysom , Adi Suresh

Unlike its intercept, a linear classifier's weight vector cannot be tuned by a simple grid search. Hence, this paper proposes weight vector tuning of a generic binary linear classifier through the parameterization of a decomposition of the…

Machine Learning · Statistics 2021-10-04 Lama B. Niyazi , Abla Kammoun , Hayssam Dahrouj , Mohamed-Slim Alouini , Tareq Al-Naffouri

This work is substituted by the paper in arXiv:2011.14066. Stochastic gradient descent is the de facto algorithm for training deep neural networks (DNNs). Despite its popularity, it still requires fine tuning in order to achieve its best…

Machine Learning · Statistics 2020-12-02 Vatsal Shah , Anastasios Kyrillidis , Sujay Sanghavi

In real-world scenarios, the number of training samples across classes usually subjects to a long-tailed distribution. The conventionally trained network may achieve unexpected inferior performance on the rare class compared to the frequent…

Computer Vision and Pattern Recognition · Computer Science 2025-01-07 Yuxiang Bao , Guoliang Kang , Linlin Yang , Xiaoyue Duan , Bo Zhao , Baochang Zhang

Using weight decay to penalize the L2 norms of weights in neural networks has been a standard training practice to regularize the complexity of networks. In this paper, we show that a family of regularizers, including weight decay, is…

Machine Learning · Computer Science 2022-06-09 Ziquan Liu , Yufei Cui , Antoni B. Chan

Deep neural networks are learning models with a very high capacity and therefore prone to over-fitting. Many regularization techniques such as Dropout, DropConnect, and weight decay all attempt to solve the problem of over-fitting by…

Machine Learning · Computer Science 2016-12-06 Armen Aghajanyan

Deep neural networks are typically trained by optimizing a loss function with an SGD variant, in conjunction with a decaying learning rate, until convergence. We show that simple averaging of multiple points along the trajectory of SGD,…

Machine Learning · Computer Science 2019-02-26 Pavel Izmailov , Dmitrii Podoprikhin , Timur Garipov , Dmitry Vetrov , Andrew Gordon Wilson
‹ Prev 1 3 4 5 6 7 10 Next ›