English
Related papers

Related papers: Shared-Weights Extender and Gradient Voting for Ne…

200 papers

Network quantization aims at reducing bit-widths of weights and/or activations, particularly important for implementing deep neural networks with limited hardware resources. Most methods use the straight-through estimator (STE) to train…

Computer Vision and Pattern Recognition · Computer Science 2021-04-05 Junghyup Lee , Dohyung Kim , Bumsub Ham

Variational autoencoders (VAEs) are a popular class of deep generative models with many variants and a wide range of applications. Improvements upon the standard VAE mostly focus on the modelling of the posterior distribution over the…

Machine Learning · Computer Science 2022-11-02 James Langley , Miguel Monteiro , Charles Jones , Nick Pawlowski , Ben Glocker

We introduce the Singular Value Representation (SVR), a new method to represent the internal state of neural networks using SVD factorization of the weights. This construction yields a new weighted graph connecting what we call spectral…

Machine Learning · Computer Science 2023-02-17 Dan Meller , Nicolas Berkouk

We propose a neural network weight encoding method for network property prediction that utilizes set-to-set and set-to-vector functions to efficiently encode neural network parameters. Our approach is capable of encoding neural networks in…

Machine Learning · Computer Science 2025-01-15 Bruno Andreis , Soro Bedionita , Philip H. S. Torr , Sung Ju Hwang

Binary Neural Networks (BNNs) rely on a real-valued auxiliary variable W to help binary training. However, pioneering binary works only use W to accumulate gradient updates during backward propagation, which can not fully exploit its power…

Computer Vision and Pattern Recognition · Computer Science 2021-10-13 Weixiang Xu , Qiang Chen , Xiangyu He , Peisong Wang , Jian Cheng

Distributed learning is commonly used for accelerating model training by harnessing the computational capabilities of multiple-edge devices. However, in practical applications, the communication delay emerges as a bottleneck due to the…

Machine Learning · Computer Science 2024-03-26 Chanho Park , H. Vincent Poor , Namyoon Lee

We consider distributed optimization under communication constraints for training deep learning models. We propose a new algorithm, whose parameter updates rely on two forces: a regular gradient step, and a corrective direction dictated by…

Machine Learning · Computer Science 2022-04-29 Yunfei Teng , Wenbo Gao , Francois Chalus , Anna Choromanska , Donald Goldfarb , Adrian Weller

Stochastic Gradient Descent (SGD) is one of the most widely used techniques for online optimization in machine learning. In this work, we accelerate SGD by adaptively learning how to sample the most useful training examples at each time…

Machine Learning · Computer Science 2016-03-16 Guillaume Bouchard , Théo Trouillon , Julien Perez , Adrien Gaidon

While there exists a wide variety of graph neural networks (GNN) for node classification, only a minority of them adopt mechanisms that effectively target noise propagation during the message-passing procedure. Additionally, a very…

Machine Learning · Computer Science 2022-04-26 Steph-Yves Louis , Alireza Nasiri , Fatima J. Rolland , Cameron Mitro , Jianjun Hu

Single encoder-decoder methodologies for semantic segmentation are reaching their peak in terms of segmentation quality and efficiency per number of layers. To address these limitations, we propose a new architecture based on a decoder…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Gabriel L. Oliveira , Senthil Yogamani , Wolfram Burgard , Thomas Brox

Energy efficient mobility management is an important problem in modern wireless networks with heterogeneous cell sizes and increased nodes densities. We show that optimization-based mobility protocols cannot achieve long-term optimal energy…

Networking and Internet Architecture · Computer Science 2016-08-30 Cong Shen , Cem Tekin , Mihaela van der Schaar

Deep learning has become a de facto method of choice for speech enhancement tasks with significant improvements in speech quality. However, real-time processing with reduced size and computations for low-power edge devices drastically…

Audio and Speech Processing · Electrical Eng. & Systems 2024-05-28 Monisankha Pal , Arvind Ramanathan , Ted Wada , Ashutosh Pandey

Despite the success of deep learning for text and image data, tree-based ensemble models are still state-of-the-art for machine learning with heterogeneous tabular data. However, there is a significant need for tabular-specific…

Machine Learning · Computer Science 2024-03-13 Sascha Marton , Stefan Lüdtke , Christian Bartelt , Heiner Stuckenschmidt

Neural network training is computationally and memory intensive. Sparse training can reduce the burden on emerging hardware platforms designed to accelerate sparse computations, but it can affect network convergence. In this work, we…

Machine Learning · Computer Science 2020-11-03 Md Aamir Raihan , Tor M. Aamodt

Stochastic variational inference for Bayesian deep neural network (DNN) requires specifying priors and approximate posterior distributions over neural network weights. Specifying meaningful weight priors is a challenging problem,…

Neural and Evolutionary Computing · Computer Science 2020-01-01 Ranganath Krishnan , Mahesh Subedar , Omesh Tickoo

Gradient sparsification is a widely adopted solution for reducing the excessive communication traffic in distributed deep learning. However, most existing gradient sparsifiers have relatively poor scalability because of considerable…

Machine Learning · Computer Science 2023-07-17 Daegun Yoon , Sangyoon Oh

Expressivity plays a fundamental role in evaluating deep neural networks, and it is closely related to understanding the limit of performance improvement. In this paper, we propose a three-pipeline training framework based on critical…

Machine Learning · Computer Science 2020-12-17 Gege Zhang

Sampling rate offsets (SROs) between devices in a heterogeneous wireless acoustic sensor network (WASN) can hinder the ability of distributed adaptive algorithms to perform as intended when they rely on coherent signal processing. In this…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-13 Paul Didier , Toon van Waterschoot , Simon Doclo , Marc Moonen

The increasing distributed and renewable energy resources and controllable devices in distribution systems make fast distribution system state estimation (DSSE) crucial in system monitoring and control. We consider a large multi-phase…

Optimization and Control · Mathematics 2020-05-22 Xinyang Zhou , Zhiyuan Liu , Yi Guo , Changhong Zhao , Jianqiao Huang , Lijun Chen

Salient Object Detection (SOD) has traditionally relied on feature refinement modules that utilize the features of an ImageNet pre-trained backbone. However, this approach limits the possibility of pre-training the entire network because of…

Computer Vision and Pattern Recognition · Computer Science 2024-08-30 Rohit Venkata Sai Dulam , Chandra Kambhamettu