Deterministic and Stochastic Primal-Dual Subgradient Algorithms for Uniformly Convex Minimization

By Anatoli B. Juditsky, Yurii E. Nesterov. 2014

96 citations recorded by the source corpus.

We discuss non-Euclidean deterministic and stochastic algorithms for optimization problems with strongly and uniformly convex objectives. We provide accuracy bounds for the performance of these alg...

Subfields: Artificial Intelligence, Computational Mechanics, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hongseok Namkoong
2. John C. Duchi
3. Percy Liang
4. Michael I. Jordan
5. Yoshua Bengio
6. Christopher D. Manning
7. Tong Zhang
8. Ruslan Salakhutdinov

In Computational Mechanics

1. Hongseok Namkoong
2. John C. Duchi
3. Ji Liu
4. Nati Srebro
5. Mu Li
6. Tianbao Yang
7. Tong Zhang
8. Michael I. Jordan

In Management Science and Operations Research

1. Hongseok Namkoong
2. John C. Duchi
3. Percy Liang
4. Tatsunori B. Hashimoto
5. Christopher D. Manning
6. Nicolai Meinshausen
7. Elad Hazan
8. Francis R. Bach

Citations in the corpus

• Variance-based Regularization with Convex Objectives (2016, background): “gence substantially faster than 1/ √ n; this been well-studied in the strongly convex case in the machine learning and optimization literature [17, 15], as well as more general uniformly convex cases [19], which guarantee rates of convergence spanning n−β for β ∈ [1 2,1]. In cases in which the minim”