English
Related papers

Related papers: Deep Neural Network Initialization with Sparsity I…

200 papers

Training neural networks with first order optimisation methods is at the core of the empirical success of deep learning. The scale of initialisation is a crucial factor, as small initialisations are generally associated to a feature…

Machine Learning · Computer Science 2025-09-16 Etienne Boursier , Nicolas Flammarion

Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of the activation function, which may hide dependencies that are not visible to vanilla-SGD (using first order…

Machine Learning · Computer Science 2016-04-05 Caglar Gulcehre , Marcin Moczulski , Misha Denil , Yoshua Bengio

We present a novel algorithm for training deep neural networks in supervised (classification and regression) and unsupervised (reinforcement learning) scenarios. This algorithm combines the standard stochastic gradient descent and the…

Machine Learning · Computer Science 2023-05-23 Arunselvan Ramaswamy , Shalabh Bhatnagar , Naman Saxena

It is known that sparsity can improve interpretability for deep neural networks. However, existing methods in the area either require networks that are pre-trained with sparsity constraints, or impose sparsity after the fact, altering the…

Machine Learning · Computer Science 2024-07-22 Arshia Soltani Moakhar , Eugenia Iofinova , Elias Frantar , Dan Alistarh

Activation sparsity offers a compelling route to accelerate large language model (LLM) inference by selectively suppressing hidden activations, yet existing approaches exhibit severe accuracy degradation at high sparsity. We show that this…

Machine Learning · Computer Science 2026-05-22 Haotian Xu , Jiannan Yang , Tian Gao , Tsui-Wei Weng , Tengfei Ma

Deep learning has been widely used in many fields, but the model training process usually consumes massive computational resources and time. Therefore, designing an efficient neural network training method with a provable convergence…

Machine Learning · Computer Science 2023-07-14 Lianke Qin , Zhao Song , Yuanyuan Yang

Long training times of deep neural networks are a bottleneck in machine learning research. The major impediment to fast training is the quadratic growth of both memory and compute requirements of dense and convolutional layers with respect…

Machine Learning · Computer Science 2020-02-20 Mihailo Isakov , Michel A. Kinsy

Overparameterized Neural Networks (NN) display state-of-the-art performance. However, there is a growing need for smaller, energy-efficient, neural networks tobe able to use machine learning applications on devices with limited…

Machine Learning · Statistics 2021-05-21 Soufiane Hayou , Jean-Francois Ton , Arnaud Doucet , Yee Whye Teh

We present extensive experiments training and testing hidden units in deep networks that emit only a predefined, static, number of discretized values. These units provide benefits in real-world deployment in systems in which memory and/or…

Neural and Evolutionary Computing · Computer Science 2018-01-17 Shumeet Baluja

Inducing sparseness while training neural networks has been shown to yield models with a lower memory footprint but similar effectiveness to dense models. However, sparseness is typically induced starting from a dense model, and thus this…

Machine Learning · Computer Science 2022-03-30 Thomas Demeester , Johannes Deleu , Fréderic Godin , Chris Develder

Deep neural networks (DNNs), particularly those using Rectified Linear Unit (ReLU) activation functions, have achieved remarkable success across diverse machine learning tasks, including image recognition, audio processing, and language…

Machine Learning · Computer Science 2026-03-26 Emi Zeger , Mert Pilanci

Sparsification of neural networks is one of the effective complexity reduction methods to improve efficiency and generalizability. Binarized activation offers an additional computational saving for inference. Due to vanishing gradient issue…

Optimization and Control · Mathematics 2019-02-12 Thu Dinh , Jack Xin

We study the implicit bias of ReLU neural networks trained by a variant of SGD where at each step, the label is changed with probability $p$ to a random label (label smoothing being a close variant of this procedure). Our experiments…

Machine Learning · Computer Science 2021-11-04 Elisabetta Cornacchia , Jan Hązła , Ido Nachum , Amir Yehudayoff

The paper briefy reviews several recent results on hierarchical architectures for learning from examples, that may formally explain the conditions under which Deep Convolutional Neural Networks perform much better in function approximation…

Machine Learning · Computer Science 2016-08-12 Hrushikesh Mhaskar , Tomaso Poggio

Although deep convolutional neural networks have achieved rapid development, it is challenging to widely promote and apply these models on low-power devices, due to computational and storage limitations. To address this issue, researchers…

Computer Vision and Pattern Recognition · Computer Science 2024-05-31 Xiaolong Yu , Cong Tian

Recent work in Deep Learning has re-imagined the representation of data as functions mapping from a coordinate space to an underlying continuous signal. When such functions are approximated by neural networks this introduces a compelling…

Machine Learning · Statistics 2022-08-09 Jonathan Richard Schwarz , Yee Whye Teh

The infinitely wide neural network has been proven a useful and manageable mathematical model that enables the understanding of many phenomena appearing in deep learning. One example is the convergence of random deep networks to Gaussian…

Machine Learning · Statistics 2024-03-19 Thiziri Nait-Saada , Alireza Naderi , Jared Tanner

Consider the multivariate nonparametric regression model. It is shown that estimators based on sparsely connected deep neural networks with ReLU activation function and properly chosen network architecture achieve the minimax rates of…

Statistics Theory · Mathematics 2020-09-15 Johannes Schmidt-Hieber

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the…

Machine Learning · Computer Science 2019-02-14 Samet Oymak , Mahdi Soltanolkotabi

Activation functions influence behavior and performance of DNNs. Nonlinear activation functions, like Rectified Linear Units (ReLU), Exponential Linear Units (ELU) and Scaled Exponential Linear Units (SELU), outperform the linear…

Neural and Evolutionary Computing · Computer Science 2019-02-05 Alberto Marchisio , Muhammad Abdullah Hanif , Semeen Rehman , Maurizio Martina , Muhammad Shafique