English
Related papers

Related papers: Debiased Distribution Compression

200 papers

We introduce a clipping strategy for Stochastic Gradient Descent (SGD) which uses quantiles of the gradient norm as clipping thresholds. We prove that this new strategy provides a robust and efficient optimization algorithm for smooth…

Machine Learning · Statistics 2024-10-15 Ibrahim Merad , Stéphane Gaïffas

We make distributed stochastic gradient descent faster by exchanging sparse updates instead of dense updates. Gradient updates are positively skewed as most updates are near zero, so we map the 99% smallest updates (by absolute value) to…

Computation and Language · Computer Science 2021-11-30 Alham Fikri Aji , Kenneth Heafield

Kernel techniques are among the most popular and flexible approaches in data science allowing to represent probability measures without loss of information under mild conditions. The resulting mapping called mean embedding gives rise to a…

Machine Learning · Statistics 2024-11-27 Linda Chamakh , Zoltan Szabo

We propose LQ-SGD (Low-Rank Quantized Stochastic Gradient Descent), an efficient communication gradient compression algorithm designed for distributed training. LQ-SGD further develops on the basis of PowerSGD by incorporating the low-rank…

Machine Learning · Computer Science 2025-06-24 Hongyang Li , Lincen Bai , Caesar Wu , Mohammed Chadli , Said Mammar , Pascal Bouvry

This work explores the scope of Frequent Sequence Mining in the domain of Lossy Image Compression. The proposed work is based on the idea of clustering pixels and using the cluster identifiers in the compression. The DCT phase in JPEG is…

Image and Video Processing · Electrical Eng. & Systems 2026-01-28 Avinash Kadimisetty , Oswald C , Sivaselvan B , Alekhya Kadimisetty

Hyperspectral measurements from long range sensors can give a detailed picture of the items, materials, and chemicals in a scene but analysis can be difficult, slow, and expensive due to high spatial and spectral resolutions of…

Machine Learning · Computer Science 2023-10-10 Michael G. Rawson , Timothy Doster

The general perception is that kernel methods are not scalable, and neural nets are the methods of choice for nonlinear learning problems. Or have we simply not tried hard enough for kernel methods? Here we propose an approach that scales…

Machine Learning · Computer Science 2015-09-11 Bo Dai , Bo Xie , Niao He , Yingyu Liang , Anant Raj , Maria-Florina Balcan , Le Song

Training state-of-the-art (SOTA) deep models often requires extensive data, resulting in substantial training and storage costs. To address these challenges, dataset condensation has been developed to learn a small synthetic set that…

Computer Vision and Pattern Recognition · Computer Science 2024-02-27 Hansong Zhang , Shikun Li , Pengju Wang , Dan Zeng , Shiming Ge

This paper introduces a new method for minimizing matrix-smooth non-convex objectives through the use of novel Compressed Gradient Descent (CGD) algorithms enhanced with a matrix-valued stepsize. The proposed algorithms are theoretically…

Optimization and Control · Mathematics 2024-04-23 Hanmin Li , Avetik Karagulyan , Peter Richtárik

Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Junzhu Mao , Yang Shen , Jinyang Guo , Yazhou Yao , Xiansheng Hua

Kernel methods are learning algorithms that enjoy solid theoretical foundations while suffering from important computational limitations. Sketching, which consists in looking for solutions among a subspace of reduced dimension, is a well…

Machine Learning · Statistics 2023-11-07 Tamim El Ahmad , Pierre Laforgue , Florence d'Alché-Buc

Distributed data mining is an emerging research topic to effectively and efficiently address hard data mining tasks using big data, which are partitioned and computed on different worker nodes, instead of one centralized server.…

Machine Learning · Computer Science 2022-10-17 Wenhan Xian , Feihu Huang , Heng Huang

Compressed sensing (CS) theory assures us that we can accurately reconstruct magnetic resonance images using fewer k-space measurements than the Nyquist sampling rate requires. In traditional CS-MRI inversion methods, the fact that the…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Liyan Sun , Zhiwen Fan , Xinghao Ding , Congbo Cai , Yue Huang , John Paisley

This paper proposes a deep learning framework to design distributed compression strategies in which distributed agents need to compress high-dimensional observations of a source, then send the compressed bits via bandwidth limited links to…

Information Theory · Computer Science 2022-03-10 Foad Sohrabi , Tao Jiang , Wei Yu

Neural networks are widely used for image-related tasks but typically demand considerable computing power. Once a network has been trained, however, its memory- and compute-footprint can be reduced by compression. In this work, we focus on…

Machine Learning · Computer Science 2025-11-13 Alper Kalle , Theo Rudkiewicz , Mohamed-Oumar Ouerfelli , Mohamed Tamaazousti

Particle-based methods include a variety of techniques, such as Markov Chain Monte Carlo (MCMC) and Sequential Monte Carlo (SMC), for approximating a probabilistic target distribution with a set of weighted particles. In this paper, we…

Machine Learning · Statistics 2024-12-03 Hadi Mohasel Afshar , Gilad Francis , Sally Cripps

This paper investigates the distributed fixed point seeking problem of sum-separable stochastic operators over the multi-agent network. Based on inexact Krasnosel'ski\u{\i}--Mann iterations, the communication-efficient distributed algorithm…

Optimization and Control · Mathematics 2026-05-22 Fan Li , Lei Xu , Xinlei Yi , Guanghui Wen , Yang Shi , Tao Yang

Spiking Neural Networks (SNNs) offer a promising alternative to traditional deep learning frameworks, since they provide higher computational efficiency due to event-driven information processing. SNNs distribute the analog values of pixel…

Machine Learning · Computer Science 2020-10-06 Isha Garg , Sayeed Shafayet Chowdhury , Kaushik Roy

Post-training compression of Transformer models commonly relies on truncated singular value decomposition (SVD). However, enforcing a single shared subspace can degrade accuracy even at moderate compression. Sparse dictionary learning…

Machine Learning · Computer Science 2026-02-18 Denis Makhov , Dmitriy Shopkhoev , Magauiya Zhussip , Ammar Ali , Baher Mohammad , Stamatios Lefkimmiatis

Sliced Stein discrepancy (SSD) and its kernelized variants have demonstrated promising successes in goodness-of-fit tests and model learning in high dimensions. Despite their theoretical elegance, their empirical performance depends…

Machine Learning · Computer Science 2021-07-22 Wenbo Gong , Kaibo Zhang , Yingzhen Li , José Miguel Hernández-Lobato
‹ Prev 1 4 5 6 7 8 10 Next ›