Abstract | ||
---|---|---|
An algorithm for stochastic (convex or nonconvex) optimization is presented. The algorithm is variable-metric in the sense that, in each iteration, the step is computed through the product of a symmetric positive definite scaling matrix and a stochastic (mini-batch) gradient of the objective function, where the sequence of scaling matrices is updated dynamically by the algorithm. A key feature of the algorithm is that it does not overly restrict the manner in which the scaling matrices are updated. Rather, the algorithm exploits fundamental self-correcting properties of BFGS-type updating--properties that have been overlooked in other attempts to devise quasi-Newton methods for stochastic optimization. Numerical experiments illustrate that the method and a limited memory variant of it are stable and outperform (mini-batch) stochastic gradient and other quasi-Newton methods when employed to solve a few machine learning problems. |
Year | Venue | Field |
---|---|---|
2016 | ICML | Mathematical optimization,Stochastic optimization,Matrix (mathematics),Computer science,Positive-definite matrix,Algorithm,Regular polygon,Artificial intelligence,Scaling,Population-based incremental learning,Machine learning |
DocType | Citations | PageRank |
Conference | 5 | 0.43 |
References | Authors | |
12 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Frank E. Curtis | 1 | 432 | 25.71 |