miscellaneous
Stochastic Optimization
3260 papers • 126 benchmarks • 313 datasets
Stochastic Optimization is the task of optimizing certain objective functional by generating and using stochastic random variables. Usually the Stochastic Optimization is an iterative process of generating random variables that progressively finds out the minima or the maxima of the objective functional. Stochastic Optimization is usually applied in the non-convex functional spaces where the usual deterministic optimization such as linear or quadratic programming or their variants cannot be used. Source: ASOC: An Adaptive Parameter-free Stochastic Optimization Techinique for Continuous Variables
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in stochastic-optimization
Trend
Dataset
Best Model
Actions
CIFAR-10 WRN-28-10 - 200 Epochs
CIFAR-10 WRN-28-10 - 200 Epochs
CIFAR-100 WRN-28-10 - 200 Epochs
CIFAR-100 WRN-28-10 - 200 Epochs
Libraries
iUse these libraries to find stochastic-optimization models and implementations
2 papers 31,398
Datasets
Subtasks
Most implemented papers
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba•Sun Dec 21 2014
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
162510
