Optimization
Combinatorial Bayesian Optimization using the Graph Cartesian Product Changyong Oh1 Jakub M. T omczak
Applying BO with GPs on combinatorial spaces is, therefore, not straightforward.
Estimating Mixture Models via Mixtures of Polynomials
Sida Wang, Arun Tejasvi Chaganty, Percy S. Liang
Neural Information Processing Systems http://nips.cc/
Adaptive Gradient Quantization for Data-Parallel SGD
These schemes are often heuristic and fixed over the course of training.
Teaching Multiple Concepts to a Forgetful Learner
Anette Hunziker, Yuxin Chen, Oisin Mac Aodha, Manuel Gomez Rodriguez, Andreas Krause, Pietro Perona, Yisong Yue, Adish Singla
Teaching forgetful learners requires repetition.
Comparison to optimization methods (e.g., Wang et al.) using finite differences (Reviewers # 1, # 3)
Dear Reviewers: Thank you for the comments. We address the main issues and clarify some confusions below. With known external forces and labeled data, they used L-BFGS to optimize the parameters to fit the observed data. They used finite differences to estimate the gradient. For comparison, we run their optimization method in our environments, as requested.
Probabilistic Line Searches for Stochastic Optimization
Maren Mahsereci, Philipp Hennig
Existing approaches range from lightweight'diagonal preconditioning' approaches
Escaping from saddle points on Riemannian manifolds
Yue Sun, Nicolas Flammarion, Maryam Fazel
Neural Information Processing Systems http://nips.cc/
A Latent Variational Framework for Stochastic Optimization
Neural Information Processing Systems http://nips.cc/
Partial Optimal Transport with Applications on Positive-Unlabeled Learning
In this paper, we address the partial Wasserstein and Gromov-Wasserstein problems and propose exact algorithms to solve them.