Optimization
Lookahead Bayesian Optimization with Inequality Constraints
Bayesian optimization (BO) is a popular way to tackle optimization problems with expensive objective function evaluations, but has mostly been applied to unconstrained problems.
Online Dynamic Programming
Holakou Rahmanian, Manfred K. K. Warmuth
Neural Information Processing Systems http://nips.cc/
Safe Model-based Reinforcement Learning with Stability Guarantees
In this paper, we present a learning algorithm that explicitly considers safety, defined in terms of stability guarantees.
On Frank-Wolfe and Equilibrium Computation
Jacob D. Abernethy, Jun-Kun Wang
Neural Information Processing Systems http://nips.cc/
Smooth Primal-Dual Coordinate Descent Algorithms for Nonsmooth Convex Optimization
Ahmet Alacaoglu, Quoc Tran Dinh, Olivier Fercoq, Volkan Cevher
Our analysis relies on a novel combination of four ideas applied to the primal-dual gap function: smoothing, acceleration, homotopy, and coordinate descent with non-uniform sampling.
Accelerated First-order Methods for Geodesically Convex Optimization on Riemannian Manifolds
Yuanyuan Liu, Fanhua Shang, James Cheng, Hong Cheng, Licheng Jiao
However, none of these three works provided a global convergence rate analysis for their algorithms.
Straggler Mitigation in Distributed Optimization Through Data Encoding
Can Karakus, Yifan Sun, Suhas Diggavi, Wotao Yin
Solving large-scale optimization problems has become feasible through distributed implementations.
Bayesian Optimization with Gradients
Jian Wu, Matthias Poloczek, Andrew G. Wilson, Peter Frazier
Bayesian optimization has been successful at global optimization of expensive-to-evaluate multimodal objective functions.
Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees
Francesco Locatello, Michael Tschannen, Gunnar Raetsch, Martin Jaggi
Neural Information Processing Systems http://nips.cc/
Asynchronous Parallel Coordinate Minimization for MAP Inference
Neural Information Processing Systems http://nips.cc/