Key features of linear graphs are: gradient or slope: Represents the steepness and direction of the line \(x\)- and \(y\)-axes intercepts: The points where the line crosses the \(x\)-axis and ...

Karimi, S. , & Vavasis, S. A. . (Accepted). Nonlinear conjugate gradient for smooth convex functions. Mathematical Programming - Computation. Retrieved from https ...

where the objective is to optimize a global function formed by a sum of local functions, using only local computation and communication. We develop an Accelerated Distributed Nesterov Gradient Descent ...

Abstract: We demonstrate a programmable analog opto-electronic (OE) circuit that can be configured to provide a range of nonlinear activation functions for incoherent ... that utilize an ideal ReLU ...

The submission contains report.pdf, this readme file, gd.py and sgd.py which contain the main logic for batch gradient descent and stochastic gradient descent respectively, util.py which contains util ...

We then develop scalable stochastic gradient descent solvers for non-decomposable loss functions. We show that for loss functions satisfying a certain uniform convergence property (that includes ...