English
Related papers

Related papers: Mask-Encoded Sparsification: Mitigating Biased Gra…

200 papers

A stochastic gradient method for synchronous distributed optimization is studied. For reducing communication cost, we particularly focus on utilization of compression of communicated gradients. Several work has shown that {\it{sparsified}}…

Optimization and Control · Mathematics 2020-06-22 Tomoya Murata , Taiji Suzuki

Federated Learning (FL) is a privacy-preserving distributed deep learning paradigm that involves substantial communication and computation effort, which is a problem for resource-constrained mobile and IoT devices. Model…

Machine Learning · Computer Science 2023-03-28 Xiaopeng Jiang , Cristian Borcea

Learned Image Compression (LIC) has shown remarkable progress in recent years. Existing works commonly employ CNN-based or self-attention-based modules as transform methods for compression. However, there is no prior research on neural…

Computer Vision and Pattern Recognition · Computer Science 2024-09-25 Yuxi Liu , Wenhan Yang , Huihui Bai , Yunchao Wei , Yao Zhao

We propose a general method called truncated gradient to induce sparsity in the weights of online learning algorithms with convex loss functions. This method has several essential properties: The degree of sparsity is continuous -- a…

Machine Learning · Computer Science 2008-07-04 John Langford , Lihong Li , Tong Zhang

In this letter, we propose a sparsification method for precoding codebooks that reduces the peak-to-average power ratio (PAPR) while preserving the achievable rate. By exploiting the fact that precoder matrices lie on the Grassmann…

Signal Processing · Electrical Eng. & Systems 2026-04-22 Joe Asano , Yuto Hama , Hiroki Iimori , Szabolcs Malomsoky , Naoki Ishikawa

Scaling laws have shaped recent advances in machine learning by enabling predictable scaling of model performance based on model size, computation, and data volume. Concurrently, the rise in computational cost for AI has motivated model…

Machine Learning · Computer Science 2025-06-03 Andrei Panferov , Alexandra Volkova , Ionut-Vlad Modoranu , Vage Egiazarian , Mher Safaryan , Dan Alistarh

Federated learning (FL) enables collaborative model training without exposing clients' private data, but its deployment is often constrained by the communication cost of transmitting gradients between clients and the central server,…

Machine Learning · Computer Science 2025-11-11 Zhijing Ye , Sheng Di , Jiamin Wang , Zhiqing Zhong , Zhaorui Zhang , Xiaodong Yu

Finding neural network weights that generalize well from small datasets is difficult. A promising approach is to learn a weight initialization such that a small number of weight changes results in low generalization error. We show that this…

Error accumulation is effective for gradient sparsification in distributed settings: initially-unselected gradient entries are eventually selected as their accumulated error exceeds a certain level. The accumulation essentially behaves as a…

Machine Learning · Computer Science 2026-02-17 Ali Bereyhi , Ben Liang , Gary Boudreau , Ali Afana

Leveraging second-order information about the loss at the scale of deep networks is one of the main lines of approach for improving the performance of current optimizers for deep learning. Yet, existing approaches for accurate full-matrix…

Machine Learning · Computer Science 2024-06-06 Ionut-Vlad Modoranu , Aleksei Kalinov , Eldar Kurtic , Elias Frantar , Dan Alistarh

Collecting annotated data for semantic segmentation is time-consuming and hard to scale up. In this paper, we for the first time propose a unified framework, termed as Multi-Dataset Pretraining, to take full advantage of the fragmented…

Computer Vision and Pattern Recognition · Computer Science 2021-06-09 Bowen Shi , Xiaopeng Zhang , Haohang Xu , Wenrui Dai , Junni Zou , Hongkai Xiong , Qi Tian

Asynchronous computation and gradient compression have emerged as two key techniques for achieving scalability in distributed optimization for large-scale machine learning. This paper presents a unified analysis framework for distributed…

Optimization and Control · Mathematics 2018-11-30 Sarit Khirirat , Hamid Reza Feyzmahdavian , Mikael Johansson

Federated Learning (FL) enables multiple clients to train a collaborative model without sharing their local data. Split Learning (SL) allows a model to be trained in a split manner across different locations. Split-Federated (SplitFed)…

Machine Learning · Computer Science 2024-12-24 Chamani Shiranthika , Hadi Hadizadeh , Parvaneh Saeedi , Ivan V. Bajić

The energy consumption of large-scale ML models is dominated by data movement, shuffling billions of parameters across memory hierarchies and data centers. Sparsification offers a principled way to mitigate these costs by pruning redundant…

Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance. Most existing methods adopt spatially invariant bit length allocation and incorporate discrete entropy approximation to constrain…

Computer Vision and Pattern Recognition · Computer Science 2019-04-02 Mu Li , Wangmeng Zuo , Shuhang Gu , Jane You , David Zhang

The communication bottleneck has been a critical problem in large-scale distributed deep learning. In this work, we study distributed SGD with random block-wise sparsification as the gradient compressor, which is ring-allreduce compatible…

Machine Learning · Computer Science 2022-06-14 An Xu , Heng Huang

The objective of this paper is self-supervised learning of video object segmentation. We develop a unified framework which simultaneously models cross-frame dense correspondence for locally discriminative feature learning and embeds…

Computer Vision and Pattern Recognition · Computer Science 2023-03-20 Liulei Li , Wenguan Wang , Tianfei Zhou , Jianwu Li , Yi Yang

Modern realities and trends in learning require more and more generalization ability of models, which leads to an increase in both models and training sample size. It is already difficult to solve such tasks in a single device mode. This is…

Optimization and Control · Mathematics 2024-12-03 Dmitry Bylinkin , Kirill Degtyarev , Aleksandr Beznosikov

Dictionary learning methods continue to gain popularity for the solution of challenging inverse problems. In the dictionary learning approach, the computational forward model is replaced by a large dictionary of possible outcomes, and the…

Machine Learning · Statistics 2023-09-06 Alberto Bocchinfuso , Daniela Calvetti , Erkki Somersalo

The maximum entropy encoding framework provides a unified perspective for many non-contrastive learning methods like SimSiam, Barlow Twins, and MEC. Inspired by this framework, we introduce Matrix-SSL, a novel approach that leverages matrix…

Machine Learning · Computer Science 2024-09-17 Yifan Zhang , Zhiquan Tan , Jingqin Yang , Weiran Huang , Yang Yuan