English
Related papers

Related papers: Topology-Aware Revival for Efficient Sparse Traini…

200 papers

Increasingly expensive training of ever larger models such as Vision Transfomers motivate reusing the vast library of already trained state-of-the-art networks. However, their latency, high computational costs and memory demands pose…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Uranik Berisha , Jens Mehnert , Alexandru Paul Condurache

Adapting pre-trained models with broad capabilities has become standard practice for learning a wide range of downstream tasks. The typical approach of fine-tuning different models for each task is performant, but incurs a substantial…

Sparse training is emerging as a promising avenue for reducing the computational cost of training neural networks. Several recent studies have proposed pruning methods using learnable thresholds to efficiently explore the non-uniform…

Machine Learning · Computer Science 2023-04-17 Abhisek Kundu , Naveen K. Mellempudi , Dharma Teja Vooturi , Bharat Kaul , Pradeep Dubey

Many recent works have shown trainability plays a central role in neural network pruning -- unattended broken trainability can lead to severe under-performance and unintentionally amplify the effect of retraining learning rate, resulting in…

Machine Learning · Computer Science 2023-03-06 Huan Wang , Yun Fu

Several challenges make it difficult for sparse neural networks to compete with dense models. First, setting a large fraction of weights to zero impairs forward and gradient signal propagation. Second, sparse studies often need to test…

Machine Learning · Computer Science 2026-02-04 Nolan Dey , Shane Bergsma , Joel Hestness

Pruning neural networks has regained interest in recent years as a means to compress state-of-the-art deep neural networks and enable their deployment on resource-constrained devices. In this paper, we propose a robust compressive learning…

Machine Learning · Computer Science 2020-06-05 George Retsinas , Athena Elafrou , Georgios Goumas , Petros Maragos

Synthetic aperture radar tomographic imaging reconstructs the three-dimensional reflectivity of a scene from a set of coherent acquisitions performed in an interferometric configuration. In forest areas, a large number of elements…

Image and Video Processing · Electrical Eng. & Systems 2024-02-09 Zoé Berenger , Loïc Denis , Florence Tupin , Laurent Ferro-Famil , Yue Huang

We present Statistical Calibrated Activation Pruning (SCAP), a post-training activation pruning framework that (1) generalizes sparsification by input activations of Fully-Connected layers for generic and flexible application across…

Machine Learning · Computer Science 2024-12-11 Vui Seng Chua , Yujie Pan , Nilesh Jain

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

Deep neural networks exploiting millions of parameters are nowadays the norm in deep learning applications. This is a potential issue because of the great amount of computational resources needed for training, and of the possible loss of…

Computation and Language · Computer Science 2022-10-31 Giovanni Bonetta , Matteo Ribero , Rossella Cancelliere

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…

Machine Learning · Computer Science 2025-10-13 T. Ed Li , Junyu Ren

Sparsity in Deep Neural Networks (DNNs) is studied extensively with the focus of maximizing prediction accuracy given an overall parameter budget. Existing methods rely on uniform or heuristic non-uniform sparsity budgets which have…

Machine Learning · Computer Science 2020-06-24 Aditya Kusupati , Vivek Ramanujan , Raghav Somani , Mitchell Wortsman , Prateek Jain , Sham Kakade , Ali Farhadi

This study investigates the loss of generalization ability in neural networks, revisiting warm-starting experiments from Ash & Adams. Our empirical analysis reveals that common methods designed to enhance plasticity by maintaining…

Machine Learning · Computer Science 2025-02-05 Hojoon Lee , Hyeonseo Cho , Hyunseung Kim , Donghu Kim , Dugki Min , Jaegul Choo , Clare Lyle

We present Spartan, a method for training sparse neural network models with a predetermined level of sparsity. Spartan is based on a combination of two techniques: (1) soft top-k masking of low-magnitude parameters via a regularized optimal…

Machine Learning · Computer Science 2022-10-18 Kai Sheng Tai , Taipeng Tian , Ser-Nam Lim

Antenna arrays are widely used in wireless communication, radar systems, radio astronomy, and military defense to enhance signal strength, directivity, and interference suppression. We introduce a deep learning-based optimization approach…

Machine Learning · Computer Science 2025-04-25 David Lu , Lior Maman , Jackson Earls , Amir Boag , Pierre Baldi

Structured pruning is an effective approach for compressing large pre-trained neural networks without significantly affecting their performance. However, most current structured pruning methods do not provide any performance guarantees, and…

Machine Learning · Computer Science 2023-02-14 Marwa El Halabi , Suraj Srinivas , Simon Lacoste-Julien

Sparsity helps reduce the computational complexity of deep neural networks by skipping zeros. Taking advantage of sparsity is listed as a high priority in next generation DNN accelerators such as TPU. The structure of sparsity, i.e., the…

Machine Learning · Computer Science 2017-06-06 Huizi Mao , Song Han , Jeff Pool , Wenshuo Li , Xingyu Liu , Yu Wang , William J. Dally

Current deep learning architectures are growing larger in order to learn from complex datasets. These architectures require giant matrix multiplication operations to train millions of parameters. Conversely, there is another growing trend…

Machine Learning · Statistics 2016-12-06 Ryan Spring , Anshumali Shrivastava

Parameter regularization or allocation methods are effective in overcoming catastrophic forgetting in lifelong learning. However, they solve all tasks in a sequence uniformly and ignore the differences in the learning difficulty of…

Machine Learning · Computer Science 2023-04-12 Wenjin Wang , Yunqing Hu , Qianglong Chen , Yin Zhang

The rectified linear unit (ReLU) is a highly successful activation function in neural networks as it allows networks to easily obtain sparse representations, which reduces overfitting in overparameterized networks. However, in network…

Machine Learning · Computer Science 2022-12-14 Shiyu Liu , Rohan Ghosh , Dylan Tan , Mehul Motani
‹ Prev 1 4 5 6 7 8 10 Next ›