English
Related papers

Related papers: Simultaneous Weight and Architecture Optimization …

200 papers

Neural networks are a group of neurons stacked together in multiple layers to mimic the biological neurons in a human brain. Neural networks have been trained using the backpropagation algorithm based on gradient descent strategy for…

Neural and Evolutionary Computing · Computer Science 2025-04-22 Deepak Kumar

Neural networks are trained by optimizing multi-dimensional sets of fitting parameters on non-convex loss landscapes. Low-loss regions of the landscapes correspond to the parameter sets that perform well on the training data. A key issue in…

Machine Learning · Computer Science 2026-02-26 Jianneng Yu , Alexandre V. Morozov

Graph Neural Networks (GNN) exhibit superior performance in graph representation learning, but their inference cost can be high, due to an aggregation operation that can require a memory fetch for a very large number of nodes. This…

Machine Learning · Computer Science 2025-03-18 Yaochen Hu , Mai Zeng , Ge Zhang , Pavel Rumiantsev , Liheng Ma , Yingxue Zhang , Mark Coates

In this paper we introduce two algorithms for neural architecture search (NASGD and NASAGD) following the theoretical work by two of the authors [5] which used the geometric structure of optimal transport to introduce the conceptual basis…

Machine Learning · Computer Science 2021-02-16 Nicolas Garcia Trillos , Felix Morales , Javier Morales

Deep learning uses neural networks which are parameterised by their weights. The neural networks are usually trained by tuning the weights to directly minimise a given loss function. In this paper we propose to re-parameterise the weights…

Neural and Evolutionary Computing · Computer Science 2022-03-14 Michael Fairbank , Spyridon Samothrakis , Luca Citi

Deep neural networks have become ubiquitous for applications related to visual recognition and language understanding tasks. However, it is often prohibitive to use typical neural networks on devices like mobile phones or smart watches…

Machine Learning · Computer Science 2017-08-10 Sujith Ravi

While post-training model compression can greatly reduce the inference cost of a deep neural network, uncompressed training still consumes a huge amount of hardware resources, run-time and energy. It is highly desirable to directly train a…

Machine Learning · Computer Science 2021-10-05 Cole Hawkins , Xing Liu , Zheng Zhang

We propose a scalable framework for the learning of high-dimensional parametric maps via adaptively constructed residual network (ResNet) maps between reduced bases of the inputs and outputs. When just few training data are available, it is…

Finding the best neural network architecture requires significant time, resources, and human expertise. These challenges are partially addressed by neural architecture search (NAS) which is able to find the best convolutional layer or cell…

Machine Learning · Computer Science 2019-03-18 Vladimir Macko , Charles Weill , Hanna Mazzawi , Javier Gonzalvo

Deep learning has become in recent years a cornerstone tool fueling key innovations in the industry, such as autonomous driving. To attain good performances, the neural network architecture used for a given application must be chosen with…

Computer Vision and Pattern Recognition · Computer Science 2021-09-17 Anthony Cazasnoves , Pierre-Antoine Ganaye , Kévin Sanchis , Tugdual Ceillier

We solve the analysis sparse coding problem considering a combination of convex and non-convex sparsity promoting penalties. The multi-penalty formulation results in an iterative algorithm involving proximal-averaging. We then unfold the…

Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures. However, these methods inherit issues from the conventional NAS methods, such…

Machine Learning · Computer Science 2023-06-19 Peng Xu , Lin Zhang , Xuanzhou Liu , Jiaqi Sun , Yue Zhao , Haiqin Yang , Bei Yu

We propose a novel strategy for Neural Architecture Search (NAS) based on Bregman iterations. Starting from a sparse neural network our gradient-based one-shot algorithm gradually adds relevant parameters in an inverse scale space manner.…

Machine Learning · Computer Science 2021-06-07 Leon Bungert , Tim Roith , Daniel Tenbrinck , Martin Burger

Training Artificial Neural Networks poses a challenging and critical problem in machine learning. Despite the effectiveness of gradient-based learning methods, such as Stochastic Gradient Descent (SGD), in training neural networks, they do…

Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…

Machine Learning · Computer Science 2025-12-23 Ansh Nagwekar

We propose a learned-structured unfolding neural network for the problem of compressive sparse multichannel blind-deconvolution. In this problem, each channel's measurements are given as convolution of a common source signal and sparse…

Signal Processing · Electrical Eng. & Systems 2021-02-15 Bahareh Tolooshams , Satish Mulleti , Demba Ba , Yonina C. Eldar

We propose a method to incrementally learn an embedding space over the domain of network architectures, to enable the careful selection of architectures for evaluation during compressed architecture search. Given a teacher network, we…

Computer Vision and Pattern Recognition · Computer Science 2019-04-26 Shengcao Cao , Xiaofang Wang , Kris M. Kitani

We introduce an algorithm where the individual bits representing the weights of a neural network are learned. This method allows training weights with integer values on arbitrary bit-depths and naturally uncovers sparse networks, without…

Machine Learning · Computer Science 2022-02-22 Cristian Ivan

Neural architecture search (NAS) aims to automate architecture design processes and improve the performance of deep neural networks. Platform-aware NAS methods consider both performance and complexity and can find well-performing…

Neural and Evolutionary Computing · Computer Science 2022-07-22 Yuhei Noda , Shota Saito , Shinichi Shirakawa

We propose a reconfigurable hardware architecture for deep neural networks (DNNs) capable of online training and inference, which uses algorithmically pre-determined, structured sparsity to significantly lower memory and computational…

Neural and Evolutionary Computing · Computer Science 2017-11-07 Sourya Dey , Yinan Shao , Keith M. Chugg , Peter A. Beerel