Neural Information Processing Systems http://nips.cc/

We consider the regime where nd. We propose randomized Newton-type algorithms that exploit non-uniform sub-sampling of { 2fi(w)}ni=1, as well as inexact updates, as means to reduce the computational complexity, and are applicable to a wide range of problems in machine learning. Two non-uniform sampling distributions based on block norm squares and block partial leverage scores are considered. Under certain assumptions, we show that our algorithms inherit a linear-quadratic convergence rate in w and achieve a lower computational complexity compared to similar existing methods. In addition, we show that our algorithms exhibit more robustness and better dependence on problem specific quantities, such as the condition number. We empirically demonstrate that our methods are at least twice as fast as Newton's methods on several real datasets.

Neural Information Processing Systems http://nips.cc/

This easy-to-use, Wi-Fi-enabled bean-to-cup brewer is good, but not quite great. App is simple and works well. "Smart" features only work with Amazon Alexa and Google Assistant. Integrating with HomeKit via third-party apps is not worth the effort. Pricey for what's essentially an auto-drip machine that works with an app, which is no longer novel or futuristic.

Our information estimator uses only these noisy measurements and a noise model to quantify how well measurements distinguish objects. Many imaging systems produce measurements that humans never see or cannot interpret directly. Your smartphone processes raw sensor data through algorithms before producing the final photo. MRI scanners collect frequency-space measurements that require reconstruction before doctors can view them. Self-driving cars process camera and LiDAR data directly with neural networks.

Neural Information Processing Systems http://nips.cc/

We propose an online convex optimization algorithm (RESCALEDEXP) that achieves optimal regret in the unconstrained setting without prior knowledge of any bounds on the loss functions. We prove a lower bound showing an exponential separation between the regret of existing algorithms that require a known bound on the loss functions and any algorithm that does not require such knowledge. RESCALEDEXP matches this lower bound asymptotically in the number of iterations. RESCALEDEXP is naturally hyperparameter-free and we demonstrate empirically that it matches prior optimization algorithms that require hyperparameter optimization.

Unsupervised learning of structured predictors has been a long standing pursuit in machine learning. Recently a conditional random field auto-encoder has been proposed in a two-layer setting, allowing latent structured representation to be automatically inferred. Aside from being nonconvex, it also requires the demanding inference of normalization. In this paper, we develop a convex relaxation of two-layer conditional model which captures latent structure and estimates model parameters, jointly and optimally. We further expand its applicability by resorting to a weaker form of inference--maximum a-posteriori. The flexibility of the model is demonstrated on two structures based on total unimodularity--graph matching and linear chain. Experimental results confirm the promise of the method.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/