English
Related papers

Related papers: Do We Actually Need Dense Over-Parameterization? I…

200 papers

Exploiting sparsity in deep neural networks (DNNs) has been a promising area for meeting the growing computation requirements. To minimize the overhead of sparse acceleration, hardware designers have proposed structured sparsity support,…

Machine Learning · Computer Science 2025-05-27 Geonhwa Jeong , Po-An Tsai , Abhimanyu R. Bambhaniya , Stephen W. Keckler , Tushar Krishna

Large language models have demonstrated capabilities in text generation, while their increasing parameter scales present challenges in computational and memory efficiency. Post-training sparsity (PTS), which reduces model cost by removing…

Computation and Language · Computer Science 2026-02-26 Minhao Jiang , Zhikai Li , Xuewen Liu , Jing Zhang , Mengjuan Chen , Qingyi Gu

Structured dilated attention has an appealing inference-time efficiency knob: it reduces the FLOPs of attention and the KV cache size by a factor of the dilation size D, while preserving long-range connectivity. While prior work studies it…

Machine Learning · Computer Science 2026-05-29 Xiuying Wei , Caglar Gulcehre

While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding tasks. For this reason, self-supervised…

Deep learning has been wildly successful in practice and most state-of-the-art machine learning methods are based on neural networks. Lacking, however, is a rigorous mathematical theory that adequately explains the amazing performance of…

Machine Learning · Statistics 2023-10-03 Rahul Parhi , Robert D. Nowak

The demand for efficient processing of deep neural networks (DNNs) on embedded devices is a significant challenge limiting their deployment. Exploiting sparsity in the network's feature maps is one of the ways to reduce its inference…

Computer Vision and Pattern Recognition · Computer Science 2023-09-28 Matteo Grimaldi , Darshan C. Ganji , Ivan Lazarevich , Sudhakar Sah

Under certain statistical assumptions of noise, recent self-supervised approaches for denoising have been introduced to learn network parameters without true clean images, and these methods can restore an image by exploiting information…

Computer Vision and Pattern Recognition · Computer Science 2020-01-10 Seunghwan Lee , Donghyeon Cho , Jiwon Kim , Tae Hyun Kim

Deep learning have achieved promising results on a wide spectrum of AI applications. Larger datasets and models consistently yield better performance. However, we generally spend longer training time on more computation and communication.…

Machine Learning · Computer Science 2021-11-03 Xiaoxin He , Fuzhao Xue , Xiaozhe Ren , Yang You

The identification of states and parameters from noisy measurements of a dynamical system is of great practical significance and has received a lot of attention. Classically, this problem is expressed as optimization over a class of models.…

The deployment of Deep Neural Networks (DNNs) on edge devices is hindered by the substantial gap between performance requirements and available processing power. While recent research has made significant strides in developing pruning…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Hamid Mousavi , Mohammad Loni , Mina Alibeigi , Masoud Daneshtalab

Neural operators (NOs) employ deep neural networks to learn mappings between infinite-dimensional function spaces. Deep operator network (DeepONet), a popular NO architecture, has demonstrated success in the real-time prediction of complex…

Machine Learning · Computer Science 2025-06-03 Sharmila Karumuri , Lori Graham-Brady , Somdatta Goswami

The high energy cost of processing deep convolutional neural networks impedes their ubiquitous deployment in energy-constrained platforms such as embedded systems and IoT devices. This work introduces convolutional layers with pre-defined…

Computer Vision and Pattern Recognition · Computer Science 2020-02-06 Souvik Kundu , Mahdi Nazemi , Massoud Pedram , Keith M. Chugg , Peter A. Beerel

We consider the neural ODE perspective of supervised learning and study the impact of the final time $T$ (which may indicate the depth of a corresponding ResNet) in training. For the classical $L^2$--regularized empirical risk minimization…

Optimization and Control · Mathematics 2021-03-31 Carlos Esteve , Borjan Geshkovski , Dario Pighin , Enrique Zuazua

Distributed deep learning (DDL) is a promising research area, which aims to increase the efficiency of training deep learning tasks with large size of datasets and models. As the computation capability of DDL nodes continues to increase,…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-07-11 Zixuan Chen , Lei Shi , Xuandong Liu , Jiahui Li , Sen Liu , Yang Xu

The Transformer has been an indispensable staple in deep learning. However, for real-life applications, it is very challenging to deploy efficient Transformers due to immense parameters and operations of models. To relieve this burden,…

Hardware Architecture · Computer Science 2022-11-01 Chao Fang , Aojun Zhou , Zhongfeng Wang

Although modern deep learning often relies on massive over-parameterized models, the fundamental interplay between capacity, sparsity, and robustness in low-capacity networks remains a vital area of study. We introduce a controlled…

Machine Learning · Computer Science 2025-07-23 Yash Kumar

The cost of hyperparameter tuning in deep learning has been rising with model sizes, prompting practitioners to find new tuning methods using a proxy of smaller networks. One such proposal uses $\mu$P parameterized networks, where the…

Machine Learning · Statistics 2023-12-11 Blake Bordelon , Lorenzo Noci , Mufan Bill Li , Boris Hanin , Cengiz Pehlevan

As deep neural networks are growing in size and being increasingly deployed to more resource-limited devices, there has been a recent surge of interest in network pruning methods, which aim to remove less important weights or activations of…

Machine Learning · Computer Science 2020-06-23 Minyoung Song , Jaehong Yoon , Eunho Yang , Sung Ju Hwang

We propose a novel parameter-efficient training (PET) method for large language models that adapts models to downstream tasks by optimizing a small subset of the existing model parameters. Unlike prior methods, this subset is not fixed in…

Computation and Language · Computer Science 2024-11-14 Felix Stahlberg , Jared Lichtarge , Shankar Kumar

Overfitting is one of the fundamental challenges when training convolutional neural networks and is usually identified by a diverging training and test loss. The underlying dynamics of how the flow of activations induce overfitting is…

Machine Learning · Computer Science 2021-04-14 Karim Huesmann , Luis Garcia Rodriguez , Lars Linsen , Benjamin Risse