发明名称 |
Systems and methods for large-scale randomized optimization for problems with decomposable loss functions |
摘要 |
Systems and methods directed toward processing optimization problems using loss functions, wherein a loss function is decomposed into at least one stratum loss function, a loss is decreased for each stratum loss function to a predefined stratum loss threshold individually using gradient descent, and the overall loss is decreased to a predefined threshold for the loss function by appropriately ordering the processing of the strata and spending appropriate processing time in each stratum. Other embodiments and aspects are also described herein. |
申请公布号 |
US8983879(B2) |
申请公布日期 |
2015.03.17 |
申请号 |
US201213595618 |
申请日期 |
2012.08.27 |
申请人 |
International Business Machines Corporation |
发明人 |
Gemulla Rainer;Haas Peter Jay;Sismanis John |
分类号 |
G06F15/18;G06F15/78;G06F7/58;G06F9/06;G06F17/10;G06F17/11 |
主分类号 |
G06F15/18 |
代理机构 |
Ference & Associates LLC |
代理人 |
Ference & Associates LLC |
主权项 |
1. A method comprising:
decomposing a primary loss function into stratum loss functions, each of the stratum loss functions having a non-zero weight applied thereto; decreasing a stratum loss to a predefined stratum loss threshold for each of the stratum loss functions by processing each of the stratum loss functions individually using gradient descent, the non-zero weights remaining as non-zero weights throughout said decreasing; and decreasing a primary loss to a predefined primary loss threshold of the primary loss function by processing each of the stratum loss functions according to a stratum sequence, the sequence being chosen to establish convergence to at least one of: stationary points of the primary loss function, and chain-recurrent points of the primary loss function. |
地址 |
Armonk NY US |