COLA: Decentralized Linear Learning

1 code implementation • NeurIPS 2018 • Lie He, An Bian, Martin Jaggi

Decentralized machine learning is a promising emerging paradigm in view of global challenges of data ownership and privacy.

BIG-bench Machine Learning CoLA +2

A Distributed Second-Order Algorithm You Can Trust

no code implementations • ICML 2018 • Celestine Dünner, Aurelien Lucchi, Matilde Gargiani, An Bian, Thomas Hofmann, Martin Jaggi

Due to the rapid growth of data and computational resources, distributed optimization has become an active research area in recent years.

Distributed Optimization Second-order methods

Optimal DR-Submodular Maximization and Applications to Provable Mean Field Inference

no code implementations • 19 May 2018 • An Bian, Joachim M. Buhmann, Andreas Krause

Mean field inference in probabilistic models is generally a highly nonconvex problem.

Continuous DR-submodular Maximization: Structure and Algorithms

1 code implementation • NeurIPS 2017 • An Bian, Kfir. Y. Levy, Andreas Krause, Joachim M. Buhmann

Concretely, we first devise a "two-phase" algorithm with $1/4$ approximation guarantee.

Point Processes

Parallel Coordinate Descent Newton Method for Efficient $\ell_1$-Regularized Minimization

1 code implementation • 18 Jun 2013 • An Bian, Xiong Li, Yuncai Liu, Ming-Hsuan Yang

We show that: (1) PCDN is guaranteed to converge globally despite increasing parallelism; (2) PCDN converges to the specified accuracy $\epsilon$ within the limited iteration number of $T_\epsilon$, and $T_\epsilon$ decreases with increasing parallelism (bundle size $P$).