English
Related papers

Related papers: Error Feedback Shines when Features are Rare

200 papers

Distributed stochastic gradient descent (SGD) algorithms are widely deployed in training large-scale deep learning models, while the communication overhead among workers becomes the new system bottleneck. Recently proposed gradient…

Machine Learning · Computer Science 2019-11-21 Shaohuai Shi , Xiaowen Chu , Ka Chun Cheung , Simon See

Distributed learning, particularly variants of distributed stochastic gradient descent (DSGD), are widely employed to speed up training by leveraging computational resources of several workers. However, in practise, communication delay…

Machine Learning · Computer Science 2020-11-13 Kerem Ozfatura , Emre Ozfatura , Deniz Gunduz

Gradient sparsification is a widely adopted solution for reducing the excessive communication traffic in distributed deep learning. However, most existing gradient sparsifiers have relatively poor scalability because of considerable…

Machine Learning · Computer Science 2023-07-17 Daegun Yoon , Sangyoon Oh

Federated learning (FL) enables the training of a model leveraging decentralized data in client sites while preserving privacy by not collecting data. However, one of the significant challenges of FL is limited computation and low…

Machine Learning · Computer Science 2023-04-18 Riyasat Ohib , Bishal Thapaliya , Pratyush Gaggenapalli , Jingyu Liu , Vince Calhoun , Sergey Plis

We propose a novel generalization of the conditional gradient (CG / Frank-Wolfe) algorithm for minimizing a smooth function $f$ under an intersection of compact convex sets, using a first-order oracle for $\nabla f$ and linear minimization…

Optimization and Control · Mathematics 2024-10-11 Zev Woodstock , Sebastian Pokutta

Estimates of the generalization error are proved for a residual neural network with $L$ random Fourier features layers $\bar z_{\ell+1}=\bar z_\ell + \mathrm{Re}\sum_{k=1}^K\bar b_{\ell k}e^{\mathrm{i}\omega_{\ell k}\bar z_\ell}+…

Numerical Analysis · Mathematics 2021-04-15 Aku Kammonen , Jonas Kiessling , Petr Plecháč , Mattias Sandberg , Anders Szepessy , Raúl Tempone

Coordinate descent with random coordinate selection is the current state of the art for many large scale optimization problems. However, greedy selection of the steepest coordinate on smooth problems can yield convergence rates independent…

Optimization and Control · Mathematics 2018-10-17 Sai Praneeth Karimireddy , Anastasia Koloskova , Sebastian U. Stich , Martin Jaggi

Although kernel methods are widely used in many learning problems, they have poor scalability to large datasets. To address this problem, sketching and stochastic gradient methods are the most commonly used techniques to derive efficient…

Machine Learning · Statistics 2022-06-03 Shingo Yashima , Atsushi Nitanda , Taiji Suzuki

We consider a standard distributed optimisation setting where $N$ machines, each holding a $d$-dimensional function $f_i$, aim to jointly minimise the sum of the functions $\sum_{i = 1}^N f_i (x)$. This problem arises naturally in…

Machine Learning · Computer Science 2021-12-08 Dan Alistarh , Janne H. Korhonen

The success of gradient descent in ML and especially for learning neural networks is remarkable and robust. In the context of how the brain learns, one aspect of gradient descent that appears biologically difficult to realize (if not…

Neural and Evolutionary Computing · Computer Science 2022-04-12 Shivam Garg , Santosh S. Vempala

Fitting a function by using linear combinations of a large number $N$ of `simple' components is one of the most fruitful ideas in statistical learning. This idea lies at the core of a variety of methods, from two-layer neural networks to…

Statistics Theory · Mathematics 2019-08-20 Adel Javanmard , Marco Mondelli , Andrea Montanari

Modern large scale machine learning applications require stochastic optimization algorithms to be implemented on distributed computational architectures. A key bottleneck is the communication overhead for exchanging information such as…

Machine Learning · Computer Science 2017-10-31 Jianqiao Wangni , Jialei Wang , Ji Liu , Tong Zhang

We revisit the classical problem of finding an approximately stationary point of the average of $n$ smooth and possibly nonconvex functions. The optimal complexity of stochastic first-order methods in terms of the number of gradient…

Machine Learning · Computer Science 2022-06-07 Alexander Tyurin , Lukang Sun , Konstantin Burlachenko , Peter Richtárik

On-device memory concerns in distributed deep learning have become severe due to (i) the growth of model size in multi-GPU training, and (ii) the wide adoption of deep neural networks for federated learning on IoT devices which have limited…

Machine Learning · Computer Science 2023-12-15 Bingcong Li , Shuai Zheng , Parameswaran Raman , Anshumali Shrivastava , Georgios B. Giannakis

We study the first gradient descent step on the first-layer parameters $\boldsymbol{W}$ in a two-layer neural network: $f(\boldsymbol{x}) = \frac{1}{\sqrt{N}}\boldsymbol{a}^\top\sigma(\boldsymbol{W}^\top\boldsymbol{x})$, where…

Machine Learning · Statistics 2022-05-04 Jimmy Ba , Murat A. Erdogdu , Taiji Suzuki , Zhichao Wang , Denny Wu , Greg Yang

Distributed training of massive machine learning models, in particular deep neural networks, via Stochastic Gradient Descent (SGD) is becoming commonplace. Several families of communication-reduction methods, such as quantization,…

Machine Learning · Computer Science 2018-09-28 Dan Alistarh , Torsten Hoefler , Mikael Johansson , Sarit Khirirat , Nikola Konstantinov , Cédric Renggli

In this work, we present a family of vector quantization schemes \emph{vqSGD} (Vector-Quantized Stochastic Gradient Descent) that provide an asymptotic reduction in the communication cost with convergence guarantees in first-order…

Machine Learning · Computer Science 2020-12-29 Venkata Gandikota , Daniel Kane , Raj Kumar Maity , Arya Mazumdar

Many popular distributed optimization methods for training machine learning models fit the following template: a local gradient estimate is computed independently by each worker, then communicated to a master, which subsequently performs…

Machine Learning · Computer Science 2019-06-05 Konstantin Mishchenko , Filip Hanzely , Peter Richtárik

Consider the consensus problem of minimizing $f(x)=\sum_{i=1}^n f_i(x)$ where each $f_i$ is only known to one individual agent $i$ out of a connected network of $n$ agents. All the agents shall collaboratively solve this problem and obtain…

Optimization and Control · Mathematics 2016-10-13 Kun Yuan , Qing Ling , Wotao Yin

We develop new stochastic gradient methods for efficiently solving sparse linear regression in a partial attribute observation setting, where learners are only allowed to observe a fixed number of actively chosen attributes per example at…

Optimization and Control · Mathematics 2018-12-04 Tomoya Murata , Taiji Suzuki