Stochastic gradient descent algorithms for strongly convex functions at O(1/T) convergence rates

Stochastic gradient descent algorithms for strongly convex functions at   O(1/T) convergence rates
Notice: This research summary and analysis were automatically generated using AI technology. For absolute accuracy, please refer to the [Original Paper Viewer] below or the Original ArXiv Source.

With a weighting scheme proportional to t, a traditional stochastic gradient descent (SGD) algorithm achieves a high probability convergence rate of O({\kappa}/T) for strongly convex functions, instead of O({\kappa} ln(T)/T). We also prove that an accelerated SGD algorithm also achieves a rate of O({\kappa}/T).


💡 Research Summary

The paper investigates stochastic gradient descent (SGD) for smooth, strongly convex objectives of the form
 f(x)=E_ξ


Comments & Academic Discussion

Loading comments...

Leave a Comment