Presentation | 2013-11-13 Stochastic Dual Coordinate Ascent with Alternating Direction Multiplier Method Taiji SUZUKI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose a new stochastic dual coordinate ascent technique that can be applied to a wide range of regularized learning problems. Our method is based on Alternating Direction Multiplier Method (ADMM) to deal with complex regularization functions such as structured regularizations. Although the original ADMM is a batch method, the proposed method offers a stochastic update rule where each iteration requires only one or few sample observations. Moreover, our method can naturally afford mini-batch update and it gives speed up of convergence. We show that, under mild assumptions, our method converges exponentially. The numerical experiments show that our method actually performs efficiently. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Stochastic Dual Coordinate Ascent / Alternating Direction Multiplier Method / Exponential Convergence / Structured Sparsity |
Paper # | IBISML2013-63 |
Date of Issue |
Conference Information | |
Committee | IBISML |
---|---|
Conference Date | 2013/11/5(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Information-Based Induction Sciences and Machine Learning (IBISML) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Stochastic Dual Coordinate Ascent with Alternating Direction Multiplier Method |
Sub Title (in English) | |
Keyword(1) | Stochastic Dual Coordinate Ascent |
Keyword(2) | Alternating Direction Multiplier Method |
Keyword(3) | Exponential Convergence |
Keyword(4) | Structured Sparsity |
1st Author's Name | Taiji SUZUKI |
1st Author's Affiliation | Department of Mathematical and Computing Sciences() |
Date | 2013-11-13 |
Paper # | IBISML2013-63 |
Volume (vol) | vol.113 |
Number (no) | 286 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |