A python implementation of the algorithm used to generate optimal piecewise linear approximations of convex functions proposed by Imamoto and Tang [1]. The algorithm uses an iterative search to find ...

In this article, we introduce a convex combination-based distributed momentum method (CDM) for solving distributed optimization to minimize a sum of smooth and strongly convex local objective ...

be -convex and -convex functions respectively on with . Then the following inequality holds (2.3) for any and. Proof. Let, then we have . If then 1) when by the -convexity and -convexity of functions ...

Empirically verifying stochastic gradient descent's (SGD) theoretical error bound for convex functions via logistic regression loss function. The theoretical error bound for convex functions can be ...