Projected Stochastic Primal-Dual Method for Constrained Online Learning With Kernels | Zendy

Alec Koppel | Zendy; Kaiqing Zhang | Zendy; Hao Zhu | Zendy; Tamer Başar | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Projected Stochastic Primal-Dual Method for Constrained Online Learning With Kernels

Author(s) -

Alec Koppel,

Kaiqing Zhang,

Hao Zhu,

Tamer Başar

Publication year - 2019

Publication title -

ieee transactions on signal processing

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 1.638

H-Index - 270

eISSN - 1941-0476

pISSN - 1053-587X

DOI - 10.1109/tsp.2019.2907265

Subject(s) - reproducing kernel hilbert space , mathematics , projection (relational algebra) , stochastic gradient descent , hilbert space , function (biology) , kernel (algebra) , discrete mathematics , combinatorics , algorithm , computer science , pure mathematics , artificial intelligence , evolutionary biology , artificial neural network , biology

We consider the problem of stochastic optimization with nonlinear constraints, where the decision variable is not vector-valued but instead a function belonging to a reproducing Kernel Hilbert Space (RKHS). Currently, there exist solutions to only special cases of this problem. To solve this constrained problem with kernels, we first generalize the Representer Theorem to a class of saddle-point pr...

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research