Advances in asynchronous parallel and distributed optimization
Motivated by large-scale optimization problems arising in the context of machine learning,
there have been several advances in the study of asynchronous parallel and distributed …
there have been several advances in the study of asynchronous parallel and distributed …
Blockchain empowered asynchronous federated learning for secure data sharing in internet of vehicles
Y Lu, X Huang, K Zhang, S Maharjan… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
In Internet of Vehicles (IoV), data sharing among vehicles for collaborative analysis can
improve the driving experience and service quality. However, the bandwidth, security and …
improve the driving experience and service quality. However, the bandwidth, security and …
Sharper convergence guarantees for asynchronous SGD for distributed and federated learning
We study the asynchronous stochastic gradient descent algorithm, for distributed training
over $ n $ workers that might be heterogeneous. In this algorithm, workers compute …
over $ n $ workers that might be heterogeneous. In this algorithm, workers compute …
Asynchronous decentralized parallel stochastic gradient descent
Most commonly used distributed machine learning systems are either synchronous or
centralized asynchronous. Synchronous algorithms like AllReduce-SGD perform poorly in a …
centralized asynchronous. Synchronous algorithms like AllReduce-SGD perform poorly in a …
The error-feedback framework: SGD with delayed gradients
SU Stich, SP Karimireddy - Journal of Machine Learning Research, 2020 - jmlr.org
We analyze (stochastic) gradient descent (SGD) with delayed updates on smooth quasi-
convex and non-convex functions and derive concise, non-asymptotic, convergence rates …
convex and non-convex functions and derive concise, non-asymptotic, convergence rates …
Asynchronous parallel stochastic gradient for nonconvex optimization
The asynchronous parallel implementations of stochastic gradient (SG) have been broadly
used in solving deep neural network and received many successes in practice recently …
used in solving deep neural network and received many successes in practice recently …
Decentralized gossip-based stochastic bilevel optimization over communication networks
Bilevel optimization have gained growing interests, with numerous applications found in
meta learning, minimax games, reinforcement learning, and nested composition …
meta learning, minimax games, reinforcement learning, and nested composition …
Improving financial trading decisions using deep Q-learning: Predicting the number of shares, action strategies, and transfer learning
G Jeong, HY Kim - Expert Systems with Applications, 2019 - Elsevier
We study trading systems using reinforcement learning with three newly proposed methods
to maximize total profits and reflect real financial market situations while overcoming the …
to maximize total profits and reflect real financial market situations while overcoming the …
Fast federated learning in the presence of arbitrary device unavailability
Federated learning (FL) coordinates with numerous heterogeneous devices to
collaboratively train a shared model while preserving user privacy. Despite its multiple …
collaboratively train a shared model while preserving user privacy. Despite its multiple …
The error-feedback framework: Better rates for SGD with delayed gradients and compressed communication
SU Stich, SP Karimireddy - arXiv preprint arXiv:1909.05350, 2019 - arxiv.org
We analyze (stochastic) gradient descent (SGD) with delayed updates on smooth quasi-
convex and non-convex functions and derive concise, non-asymptotic, convergence rates …
convex and non-convex functions and derive concise, non-asymptotic, convergence rates …