English
Related papers

Related papers: Distributed Learning with Dependent Samples

200 papers

Stochastic gradient descent algorithms for training linear and kernel predictors are gaining more and more importance, thanks to their scalability. While various methods have been proposed to speed up their convergence, the model selection…

Machine Learning · Computer Science 2014-06-17 Francesco Orabona

Equalizer parameter optimization is critical for signal integrity in high-speed memory systems operating at multi-gigabit data rates. However, existing methods suffer from computationally expensive eye diagram evaluation, optimization of…

Machine Learning · Computer Science 2026-05-07 Muhammad Usama , Dong Eui Chang

In this work, multiplicative stochasticity is applied to the learning rate of stochastic optimization algorithms, giving rise to stochastic learning-rate schemes. In-expectation theoretical convergence results of Stochastic Gradient Descent…

Optimization and Control · Mathematics 2022-03-22 Theodoros Mamalis , Dusan Stipanovic , Petros Voulgaris

Modern large-scale kernel-based tests such as maximum mean discrepancy (MMD) and kernelized Stein discrepancy (KSD) optimize kernel hyperparameters on a held-out sample via data splitting to obtain the most powerful test statistics. While…

Machine Learning · Computer Science 2020-10-20 Jonas M. Kübler , Wittawat Jitkrittum , Bernhard Schölkopf , Krikamol Muandet

State-of-the-art decentralized learning algorithms typically require the data distribution to be Independent and Identically Distributed (IID). However, in practical scenarios, the data distribution across the agents can have significant…

Machine Learning · Computer Science 2024-03-07 Sai Aparna Aketi , Sakshi Choudhary , Kaushik Roy

Deep learning based methods for image reconstruction are state-of-the-art for a variety of imaging tasks. However, neural networks often perform worse if the training data differs significantly from the data they are applied to. For…

Image and Video Processing · Electrical Eng. & Systems 2024-08-08 Kang Lin , Reinhard Heckel

We propose a distributed approach to train deep neural networks (DNNs), which has guaranteed convergence theoretically and great scalability empirically: close to 6 times faster on instance of ImageNet data set when run with 6 machines. The…

Machine Learning · Statistics 2016-10-04 Abhimanu Kumar , Pengtao Xie , Junming Yin , Eric P. Xing

Deep neural network training spends most of the computation on examples that are properly handled, and could be ignored. We propose to mitigate this phenomenon with a principled importance sampling scheme that focuses computation on…

Machine Learning · Computer Science 2019-10-29 Angelos Katharopoulos , François Fleuret

We consider a distributed system, consisting of a heterogeneous set of devices, ranging from low-end to high-end. These devices have different profiles, e.g., different energy budgets, or different hardware specifications, determining their…

Machine Learning · Computer Science 2020-06-11 Martin Rapp , Ramin Khalili , Jörg Henkel

Learning with kernels is an important concept in machine learning. Standard approaches for kernel methods often use predefined kernels that require careful selection of hyperparameters. To mitigate this burden, we propose in this paper a…

Machine Learning · Computer Science 2020-06-26 Yufan Zhou , Changyou Chen , Jinhui Xu

In this paper we analyze a budgeted learning setting, in which the learner can only choose and observe a small subset of the attributes of each training example. We develop efficient algorithms for ridge and lasso linear regression, which…

Machine Learning · Computer Science 2014-10-24 Doron Kukliansky , Ohad Shamir

In this paper, we aim at establishing an approximation theory and a learning theory of distribution regression via a fully connected neural network (FNN). In contrast to the classical regression methods, the input variables of distribution…

Machine Learning · Statistics 2023-07-10 Zhongjie Shi , Zhan Yu , Ding-Xuan Zhou

Over the past decade, there is a growing interest in collaborative learning that can enhance AI models of multiple parties. However, it is still challenging to enhance performance them without sharing private data and models from individual…

Machine Learning · Computer Science 2024-10-31 Sejun Park , Kihun Hong , Ganguk Hwang

Deep neural networks dominate modern machine learning, while alternative function approximators remain comparatively underexplored at scale. In this work, we revisit kernel methods as drop-in components for standard deep learning pipelines.…

Machine Learning · Computer Science 2026-05-05 Jean-Marc Mercier , Gabriele Santin

Parameter selection without communicating local data is quite challenging in distributed learning, exhibing an inconsistency between theoretical analysis and practical application of it in tackling distributively stored data. Motivated by…

Machine Learning · Computer Science 2024-09-10 Shao-Bo Lin

Training large machine learning models requires a distributed computing approach, with communication of the model updates being the bottleneck. For this reason, several methods based on the compression (e.g., sparsification and/or…

Machine Learning · Computer Science 2023-12-29 Konstantin Mishchenko , Eduard Gorbunov , Martin Takáč , Peter Richtárik

We consider estimation under scenarios where the signals of interest exhibit change of characteristics over time. In particular, we consider the continual learning problem where different tasks, e.g., data with different distributions,…

Machine Learning · Computer Science 2023-12-05 Martin Hellkvist , Ayça Özçelikkale , Anders Ahlén

We address the consistency of a kernel ridge regression estimate of the conditional mean embedding (CME), which is an embedding of the conditional distribution of $Y$ given $X$ into a target reproducing kernel Hilbert space $\mathcal{H}_Y$.…

Machine Learning · Statistics 2023-12-13 Zhu Li , Dimitri Meunier , Mattes Mollenhauer , Arthur Gretton

This paper proposes a novel kernel approach to linear dimension reduction for supervised learning. The purpose of the dimension reduction is to find directions in the input space to explain the output as effectively as possible. The…

Machine Learning · Statistics 2011-09-05 Kenji Fukumizu , Chenlei Leng

In many areas, practitioners need to analyze large datasets that challenge conventional single-machine computing. To scale up data analysis, distributed and parallel computing approaches are increasingly needed. Here we study a fundamental…

Statistics Theory · Mathematics 2020-06-04 Edgar Dobriban , Yue Sheng
‹ Prev 1 4 5 6 7 8 10 Next ›