paper-with-me

Papers

Optimal Learning for Multi-pass Stochastic Gradient Methods

2016-12-01 · NeurIPS 2016 12 · Junhong Lin, Lorenzo Rosasco

We analyze the learning properties of the stochastic gradient method when multiple passes over the data and mini-batches are allowed. In particular, we consider the square loss and show that for a universal step-size choice, the number of passes acts as a regularization parameter, and optimal finite sample bounds can be achieved by early-stopping. Moreover, we show that larger step-sizes are allowed when considering mini-batches. Our analysis is based on a unifying approach, encompassing both batch and stochastic gradient methods as special cases.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Optimal Rates for Multi-pass Stochastic Gradient Methods

2016-05-28 · Junhong Lin, Lorenzo Rosasco

We analyze the learning properties of the stochastic gradient method when multiple passes over the data and mini-batches are allowed. We study how regularization properties are controlled by the step-size, the number of …

Optimal Rates for Learning with Nyström Stochastic Gradient Methods

2017-10-21 · Junhong Lin, Lorenzo Rosasco

In the setting of nonparametric regression, we propose and study a combination of stochastic gradient methods with Nystr\"om subsampling, allowing multiple passes over the data and mini-batches. Generalization error boun…

regression

Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes

2018-05-25 · NeurIPS 2018 12 · Loucas Pillaud-Vivien, Alessandro Rudi, Francis Bach

We consider stochastic gradient descent (SGD) for least-squares regression with potentially several passes over the data. While several passes have been widely reported to perform practically better in terms of predictiv…

Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods

2018-07-01 · ICML 2018 7 · Junhong Lin, Volkan Cevher

We study generalization properties of distributed algorithms in the setting of nonparametric regression over a reproducing kernel Hilbert space (RKHS). We investigate distributed stochastic gradient methods (SGM), w…

regression

Stochastic Composite Mirror Descent: Optimal Bounds with High Probabilities

2018-12-01 · NeurIPS 2018 12 · Yunwen Lei, Ke Tang

We study stochastic composite mirror descent, a class of scalable algorithms able to exploit the geometry and composite structure of a problem. We consider both convex and strongly convex objectives with non-smooth loss …

Generalization BoundsVocal Bursts Intensity Prediction