random_reshuffling
RR, SO, IG and SGD with logistic regression loss.
view repo
Random Reshuffling (RR) is an algorithm for minimizing finite-sum functions that utilizes iterative gradient descent steps in conjunction with data reshuffling. Often contrasted with its sibling Stochastic Gradient Descent (SGD), RR is usually faster in practice and enjoys significant popularity in convex and non-convex optimization. The convergence rate of RR has attracted substantial attention recently and, for strongly convex and smooth functions, it was shown to converge faster than SGD if 1) the stepsize is small, 2) the gradients are bounded, and 3) the number of epochs is large. We remove these 3 assumptions, improve the dependence on the condition number from κ^2 to κ (resp. from κ to √(κ)) and, in addition, show that RR has a different type of variance. We argue through theory and experiments that the new variance type gives an additional justification of the superior performance of RR. To go beyond strong convexity, we present several results for non-strongly convex and non-convex objectives. We show that in all cases, our theory improves upon existing literature. Finally, we prove fast convergence of the Shuffle-Once (SO) algorithm, which shuffles the data only once, at the beginning of the optimization process. Our theory for strongly-convex objectives tightly matches the known lower bounds for both RR and SO and substantiates the common practical heuristic of shuffling once or only a few times. As a byproduct of our analysis, we also get new results for the Incremental Gradient algorithm (IG), which does not shuffle the data at all.
READ FULL TEXT
We consider the fundamental problem in non-convex optimization of effici...
read it
Here we study non-convex composite optimization: first, a finite-sum of
...
read it
We study stochastic gradient descent without replacement () for
smooth ...
read it
Adaptive gradient methods have attracted much attention of machine learn...
read it
We propose a family of lossy integer compressions for Stochastic Gradien...
read it
We study the minimization of a convex function f(X) over the set of
n× n...
read it
Many classical algorithms are found until several years later to outlive...
read it
RR, SO, IG and SGD with logistic regression loss.
Comments
There are no comments yet.