- 博客(4)
- 收藏
- 关注
RSS订阅原创 Projection-free Online Learning
IntroductionAs a computational bottleneck when applying online learning to massive datasets, the projection-step always restricts the application. This paper provides a projection-free algorithm (OFW) for online learning with three advantages: the first
2021-03-31 15:22:09
212
原创 Competing in the Dark: An Efficient Algorithm for Bandit Linear Optimization
IntroductionThe paper introduces an algorithm for bandit linear optimization problem. The problem of sequential decision making with stochastic reward and unknown loss function can be generalized as “multi-armed bandit problem”, which presents a model de
2021-02-27 22:29:12
199
原创 Making Gradient Descent Optimal for Strongly Convex Stochastic Optimizatio
Making Gradient Descent Optimal for Strongly Convex Stochastic OptimizationBrief Introduction and BackgroundIn the practice of online learning in industrial, stochastic gradient descend is a common method to solve optimization problems. To be specif.
2021-02-17 21:38:13
215
原创 Online Convex Programming and Generalized Infinitesimal Gradient Ascent
Brief Introduction and backgroundThe paper presents an algorithm for general convex functions based on gradient descent, motivated by infinitesimal gradient ascent. It uses a framing example to illustrate the problem of online convex programming. Then...
2021-01-28 00:18:38
535
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人