English
Related papers

Related papers: Are wider nets better given the same number of par…

200 papers

Wide neural networks have proven to be a rich class of architectures for both theory and practice. Motivated by the observation that finite width convolutional networks appear to outperform infinite width networks, we study scaling laws for…

Machine Learning · Computer Science 2020-08-21 Anders Andreassen , Ethan Dyer

Datasets for training object recognition systems are steadily increasing in size. This paper investigates the question of whether existing detectors will continue to improve as data grows, or saturate in performance due to limited model…

Computer Vision and Pattern Recognition · Computer Science 2015-03-06 Xiangxin Zhu , Carl Vondrick , Charless Fowlkes , Deva Ramanan

While larger neural models are pushing the boundaries of what deep learning can do, often more weights are needed to train models rather than to run inference for tasks. This paper seeks to understand this behavior using search spaces --…

Machine Learning · Computer Science 2021-05-28 Darko Stosic , Dusan Stosic

In contrast to conventional artificial neural networks, which are structurally static, we present two approaches for evolving small networks into larger ones during training. The first method employs an auxiliary weight that directly…

Machine Learning · Computer Science 2025-07-29 Anil Radhakrishnan , John F. Lindner , Scott T. Miller , Sudeshna Sinha , William L. Ditto

Random pruning is arguably the most naive way to attain sparsity in neural networks, but has been deemed uncompetitive by either post-training pruning or sparse training. In this paper, we focus on sparse training and highlight a perhaps…

Machine Learning · Computer Science 2022-02-08 Shiwei Liu , Tianlong Chen , Xiaohan Chen , Li Shen , Decebal Constantin Mocanu , Zhangyang Wang , Mykola Pechenizkiy

We perform an empirical study of the behaviour of deep networks when fully linearizing some of its feature channels through a sparsity prior on the overall number of nonlinear units in the network. In experiments on image classification and…

Machine Learning · Computer Science 2023-06-02 Christian H. X. Ali Mehmeti-Göpel , Jan Disselhoff

Neural networks are known to give better performance with increased depth due to their ability to learn more abstract features. Although the deepening of networks has been well established, there is still room for efficient feature…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Dumindu Tissera , Rukshan Wijessinghe , Kasun Vithanage , Alex Xavier , Subha Fernando , Ranga Rodrigo

Overparameterization, the condition where models have more parameters than necessary to fit their training loss, is a crucial factor for the success of deep learning. However, the characteristics of the features learned by overparameterized…

Machine Learning · Computer Science 2024-07-02 Ahmet Cagri Duzgun , Samy Jelassi , Yuanzhi Li

To better understand the theoretical behavior of large neural networks, several works have analyzed the case where a network's width tends to infinity. In this regime, the effect of random initialization and the process of training a neural…

Machine Learning · Computer Science 2022-01-14 Florian Juengermann , Maxime Laasri , Marius Merkle

A different parametrization of the hyperplanes is used in the neural network algorithm. As demonstrated on several autoencoder examples it significantly outperforms the usual parametrization, reaching lower training error values with only a…

Machine Learning · Computer Science 2017-06-05 Michael F. Zimmer

Modern deep learning models are highly overparameterized, resulting in large sets of parameter configurations that yield the same outputs. A significant portion of this redundancy is explained by symmetries in the parameter…

Machine Learning · Computer Science 2025-12-12 Bo Zhao , Robin Walters , Rose Yu

We propose to impose symmetry in neural network parameters to improve parameter usage and make use of dedicated convolution and matrix multiplication routines. Due to significant reduction in the number of parameters as a result of the…

Machine Learning · Computer Science 2019-01-11 Xu Shell Hu , Sergey Zagoruyko , Nikos Komodakis

What makes a good Large Language Model (LLM)? That it performs well on the relevant benchmarks -- which hopefully measure, with some validity, the presence of capabilities that are also challenged in real application. But what makes the…

Computation and Language · Computer Science 2024-06-21 Nidhir Bhavsar , Jonathan Jordan , Sherzod Hakimov , David Schlangen

As neural networks are increasingly employed in machine learning practice, how to efficiently share limited training resources among a diverse set of model training tasks becomes a crucial issue. To achieve better utilization of the shared…

Machine Learning · Computer Science 2021-04-27 Rui Liu , Sanjay Krishnan , Aaron J. Elmore , Michael J. Franklin

Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization. However, having a large parameter space is considered one of the main suspects of the neural networks'…

Training neural networks means solving a high-dimensional optimization problem. Normally the goal is to minimize a loss function that depends on what is called the network function, or in other words the function that gives the network…

Machine Learning · Computer Science 2022-11-15 Umberto Michelucci

When the data are sparse, optimization of hyperparameters of the kernel in Gaussian process regression by the commonly used maximum likelihood estimation (MLE) criterion often leads to overfitting. We show that choosing hyperparameters (in…

Methodology · Statistics 2023-01-27 Sergei Manzhos , Manabu Ihara

We consider a deep structured linear network under sparsity constraints. We study sharp conditions guaranteeing the stability of the optimal parameters defining the network. More precisely, we provide sharp conditions on the network…

Optimization and Control · Mathematics 2023-02-03 Francois Malgouyres

During typical gradient-based training of deep neural networks, all of the model's parameters are updated at each iteration. Recent work has shown that it is possible to update only a small subset of the model's parameters during training,…

Machine Learning · Computer Science 2021-11-19 Yi-Lin Sung , Varun Nair , Colin Raffel

Deep neural networks often contain far more parameters than training examples, yet they still manage to generalize well in practice. Classical complexity measures such as VC-dimension or PAC-Bayes bounds usually become vacuous in this…

Machine Learning · Computer Science 2025-08-26 Aviral Dhingra