English
Related papers

Related papers: Bi-directional Masks for Efficient N:M Sparse Trai…

200 papers

We provide a new efficient version of the backpropagation algorithm, specialized to the case where the weights of the neural network being trained are sparse. Our algorithm is general, as it applies to arbitrary (unstructured) sparsity and…

Machine Learning · Computer Science 2023-02-10 Mahdi Nikdan , Tommaso Pegolotti , Eugenia Iofinova , Eldar Kurtic , Dan Alistarh

Binary grid mask representation is broadly used in instance segmentation. A representative instantiation is Mask R-CNN which predicts masks on a $28\times 28$ binary grid. Generally, a low-resolution grid is not sufficient to capture the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-28 Xing Shen , Jirui Yang , Chunbo Wei , Bing Deng , Jianqiang Huang , Xiansheng Hua , Xiaoliang Cheng , Kewei Liang

Video diffusion Transformer (DiT) models excel in generative quality but hit major computational bottlenecks when producing high-resolution, long-duration videos. The quadratic complexity of full attention leads to prohibitively high…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Chenlu Zhan , Wen Li , Chuyu Shen , Jun Zhang , Suhui Wu , Hao Zhang

Activation compressed training provides a solution towards reducing the memory cost of training deep neural networks~(DNNs). However, state-of-the-art work combines a search of quantization bit-width with the training, which makes the…

Machine Learning · Computer Science 2023-05-23 Guanchu Wang , Zirui Liu , Zhimeng Jiang , Ninghao Liu , Na Zou , Xia Hu

Compressed Neural Networks have the potential to enable deep learning across new applications and smaller computational environments. However, understanding the range of learning tasks in which such models can succeed is not well studied.…

Machine Learning · Computer Science 2023-08-10 Matt Gorbett , Hossein Shirazi , Indrakshi Ray

We propose a novel adaptive empirical Bayesian method for sparse deep learning, where the sparsity is ensured via a class of self-adaptive spike-and-slab priors. The proposed method works by alternatively sampling from an adaptive…

Machine Learning · Statistics 2020-04-15 Wei Deng , Xiao Zhang , Faming Liang , Guang Lin

The ever-growing computational demands of increasingly complex machine learning models frequently necessitate the use of powerful cloud-based infrastructure for their training. Binary neural networks are known to be promising candidates for…

Recent research has focused on weight sparsity in deep neural network training to reduce FLOPs, aiming for improved efficiency (test accuracy w.r.t training FLOPs). However, sparse weight training often compromises accuracy, requiring…

Machine Learning · Computer Science 2024-07-19 Vithursan Thangarasa , Shreyas Saxena , Abhay Gupta , Sean Lie

The generative self-supervised learning strategy exhibits remarkable learning representational capabilities. However, there is limited attention to end-to-end pre-training methods based on a hybrid architecture of CNN and Transformer, which…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Fenghe Tang , Ronghao Xu , Qingsong Yao , Xueming Fu , Quan Quan , Heqin Zhu , Zaiyi Liu , S. Kevin Zhou

This paper combines autoregressive and masked-diffusion training objectives without any architectural modifications, resulting in flexible language models that outperform single-objective models. Autoregressive modeling has been a popular…

Computation and Language · Computer Science 2026-03-30 David Samuel , Lucas Georges Gabriel Charpentier

Pruning large neural networks to create high-quality, independently trainable sparse masks, which can maintain similar performance to their dense counterparts, is very desirable due to the reduced space and time complexity. As research…

Computer Vision and Pattern Recognition · Computer Science 2022-06-29 Ajay Jaiswal , Haoyu Ma , Tianlong Chen , Ying Ding , Zhangyang Wang

We propose a novel, efficient approach for distributed sparse learning in high-dimensions, where observations are randomly partitioned across machines. Computationally, at each round our method only requires the master machine to solve a…

Machine Learning · Statistics 2016-05-26 Jialei Wang , Mladen Kolar , Nathan Srebro , Tong Zhang

Training a sparse neural network from scratch requires optimizing connections at the same time as the weights themselves. Typically, the weights are redistributed after a predefined number of weight updates, removing a fraction of the…

Machine Learning · Computer Science 2022-11-04 Mathias Parger , Alexander Ertl , Paul Eibensteiner , Joerg H. Mueller , Martin Winter , Markus Steinberger

Memory-efficient optimization methods have recently gained increasing attention for scaling full-parameter training of large language models under the GPU-memory bottleneck. Existing approaches either lack clear convergence guarantees, or…

Machine Learning · Computer Science 2026-03-11 Hui Yang , Tao Ren , Jinyang Jiang , Wan Tian , Yijie Peng

While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Yuxi Liu , Yipeng Hu , Zekun Zhang , Kunze Jiang , Kun Yuan

As the deep learning revolution marches on, masked modeling has emerged as a distinctive approach that involves predicting parts of the original data that are proportionally masked during training, and has demonstrated exceptional…

Image and Video Processing · Electrical Eng. & Systems 2025-06-25 Qinrong Cai , Yu Guan , Zhibo Chen , Dong Liang , Qiuyun Fan , Qiegen Liu

This paper introduces the Bi-linear consensus Alternating Direction Method of Multipliers (Bi-cADMM), aimed at solving large-scale regularized Sparse Machine Learning (SML) problems defined over a network of computational nodes.…

Machine Learning · Computer Science 2024-06-27 Alireza Olama , Andreas Lundell , Jan Kronqvist , Elham Ahmadi , Eduardo Camponogara

Scribble-supervised medical image segmentation tackles the limitation of sparse masks. Conventional approaches alternate between: labeling pseudo-masks and optimizing network parameters. However, such iterative two-stage paradigm is…

Computer Vision and Pattern Recognition · Computer Science 2023-10-02 Zefan Yang , Di Lin , Dong Ni , Yi Wang

Matrices and more generally multidimensional arrays, form the backbone of computational studies. In this paper we demonstrate increases in computational efficiency by performing partial-tracing/tensor-contractions on sparse-arrays. It was…

Data Structures and Algorithms · Computer Science 2023-03-21 Julio Candanedo

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