Optimization
Translation Synchronization via Truncated Least Squares Xiangru Huang
Where the constraint ensures that the solution is unique.
Certified Defenses for Data Poisoning Attacks
Jacob Steinhardt, Pang Wei W. Koh, Percy S. Liang
Traditionally, computer security seeks to ensure a system's integrity against attackers by creating clear boundaries between the system and the outside world ( Bishop, 2002).
Fast Black-box Variational Inference through Stochastic Trust-Region Optimization
Jeffrey Regier, Michael I. Jordan, Jon McAuliffe
The former is based on stochastic first-order optimization.
Decomposition-Invariant Conditional Gradient for General Polytopes with Line Search
Mohammad Ali Bashiri, Xinhua Zhang
In this paper, we show that by employing an away-step update, similar rates can be generalized to arbitrary polytopes with strong empirical performance.
Scalable Planning with Tensorflow for Hybrid Nonlinear Domains
Ga Wu, Buser Say, Scott Sanner
RMSProp avoids both the vanishing and exploding gradient problems.
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.