scientific article; zbMATH DE number 6982979

zbMath1469.68088arXiv1610.03774MaRDI QIDQ4558562

Praneeth Netrapalli, Rahul Kidambi, Prateek Jain, Aaron Sidford, Sham M. Kakade

Publication date: 22 November 2018

Full work available at URL: https://arxiv.org/abs/1610.03774

Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.

zbMATH Keywords

stochastic approximationparallelizationagnostic learningleast squares regressionheteroscedastic noisemodel averagingstochastic gradient descentmis-specified modelsbatchsize doublingiterate averagingmini batch SGDparameter mixingsuffix averaging

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Learning and adaptive systems in artificial intelligence (68T05) Stochastic programming (90C15) Parallel algorithms in computer science (68W10)

Related Items

Some Limit Properties of Markov Chains Induced by Recursive Stochastic Algorithms, A stochastic subgradient method for distributionally robust non-convex and non-smooth learning, A hybrid ensemble method with negative correlation learning for regression, Accelerated gradient boosting, Bridging the gap between constant step size stochastic gradient descent and Markov chains, Stochastic heavy ball, Optimization for deep learning: an overview, On variance reduction for stochastic smooth convex optimization with multiplicative noise, Unnamed Item, Unnamed Item, A selective overview of deep learning, An elementary analysis of ridge regression with random design, Unnamed Item, Unnamed Item, Dimension independent excess risk by stochastic gradient descent, On the Effectiveness of Richardson Extrapolation in Data Science

Uses Software

• HOGWILD
• DiSCO
• Saga

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Nonparametric stochastic approximation with large step-sizes
• Stochastic approximation methods for constrained and unconstrained systems
• On optimal estimation methods using stochastic approximation procedures
• Asymptotically efficient stochastic approximation; the RM case
• Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates
• Adaptivity of averaged stochastic gradient descent to local strong convexity for logistic regression
• Asymptotic Properties of Distributed and Communicating Stochastic Approximation Algorithms
• Acceleration of Stochastic Approximation by Averaging
• On the optimality of averaging in distributed statistical learning
• Optimization Methods for Large-Scale Machine Learning
• Katyusha: the first direct acceleration of stochastic gradient methods
• Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization
• Optimal Distributed Online Prediction using Mini-Batches
• Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization
• A Stochastic Approximation Method
• Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm