Statistical Learning
Metric on Nonlinear Dynamical Systems with Perron-Frobenius Operators
Isao Ishikawa, Keisuke Fujii, Masahiro Ikeda, Yuka Hashimoto, Yoshinobu Kawahara
Neural Information Processing Systems http://nips.cc/
Towards Understanding Acceleration Tradeoff between Momentum and Asynchrony in Nonconvex Stochastic Optimization
Tianyi Liu, Shiyang Li, Jianping Shi, Enlu Zhou, Tuo Zhao
Neural Information Processing Systems http://nips.cc/
A Practical Algorithm for Distributed Clustering and Outlier Detection
Jiecao Chen, Erfan Sadeqi Azer, Qin Zhang
The rise of big data has brought the design of distributed learning algorithm to the forefront.
Improved Network Robustness with Adversary Critic
Alexander Matyasko, Lap-Pui Chau
Ideally, what confuses neural network should be confusing to humans.
Adversarially Robust Generalization Requires More Data
Even small perturbations can cause state-of-the-art classifiers with high "standard" accuracy to produce an incorrect prediction with high confidence.
Adaptive Negative Curvature Descent with Applications in Non-convex Optimization
Mingrui Liu, Zhe Li, Xiaoyu Wang, Jinfeng Yi, Tianbao Yang
When the function is non-degenerate (i.e., strict saddle or the Hessian at all
Communication Efficient Parallel Algorithms for Optimization on Manifolds
However, the existing literature on parallel inference almost exclusively focuses on Euclidean data and parameters.
Neural Architecture Search with Bayesian Optimisation and Optimal Transport
The goal is to find the model, i.e. hyper-parameters, with the highest validation accuracy.
Optimization over Continuous and Multi-dimensional Decisions with Observational Data
Dimitris Bertsimas, Christopher McCord
We consider the optimization of an uncertain objective over continuous and multidimensional decision spaces in problems in which we are only provided with observational data.
Online Structured Laplace Approximations for Overcoming Catastrophic Forgetting
Creating an agent that performs well across multiple tasks and continuously incorporates new knowledge has been a longstanding goal of research on artificial intelligence.