Abstract | ||
---|---|---|
Quasi-Newton methods are widely used in practise for convex loss minimization problems. These methods exhibit good empirical performance on a wide variety of tasks and enjoy super-linear convergence to the optimal solution. For large-scale learning problems, stochastic Quasi-Newton methods have been recently proposed. However, these typically only achieve sub-linear convergence rates and have not been shown to consistently perform well in practice since noisy Hessian approximations can exacerbate the effect of high-variance stochastic gradient estimates. In this work we propose Vite, a novel stochastic Quasi-Newton algorithm that uses an existing first-order technique to reduce this variance. Without exploiting the specific form of the approximate Hessian, we show that Vite reaches the optimum at a geometric rate with a constant step-size when dealing with smooth strongly convex functions. Empirically, we demonstrate improvements over existing stochastic Quasi-Newton and variance reduced stochastic gradient methods. |
Year | Venue | Field |
---|---|---|
2015 | CoRR | Convergence (routing),Mathematical optimization,Stochastic optimization,Hessian matrix,Regular polygon,Convex function,Loss minimization,Mathematics,Exponential growth,Newton's method |
DocType | Volume | Citations |
Journal | abs/1503.08316 | 6 |
PageRank | References | Authors |
0.43 | 10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Aurelien Lucchi | 1 | 2419 | 89.45 |
Brian McWilliams | 2 | 8 | 2.81 |
Thomas Hofmann | 3 | 30 | 8.97 |