Collaborating Authors

Dynamic Neural Network Channel Execution for Efficient Training Machine Learning

Existing methods for reducing the computational burden of neural networks at run-time, such as parameter pruning or dynamic computational path selection, focus solely on improving computational efficiency during inference. On the other hand, in this work, we propose a novel method which reduces the memory footprint and number of computing operations required for training and inference. Our framework efficiently integrates pruning as part of the training procedure by exploring and tracking the relative importance of convolutional channels. At each training step, we select only a subset of highly salient channels to execute according to the combinatorial upper confidence bound algorithm, and run a forward and backward pass only on these activated channels, hence learning their parameters. Consequently, we enable the efficient discovery of compact models. We validate our approach empirically on state-of-the-art CNNs - VGGNet, ResNet and DenseNet, and on several image classification datasets. Results demonstrate our framework for dynamic channel execution reduces computational cost up to 4x and parameter count up to 9x, thus reducing the memory and computational demands for discovering and training compact neural network models.

Column Selection via Adaptive Sampling

Neural Information Processing Systems

Selecting a good column (or row) subset of massive data matrices has found many applications in data analysis and machine learning. We propose a new adaptive sampling algorithm that can be used to improve any relative-error column selection algorithm. Our algorithm delivers a tighter theoretical bound on the approximation error which we also demonstrate empirically using two well known relative-error column subset selection algorithms. Our experimental results on synthetic and real-world data show that our algorithm outperforms non-adaptive sampling as well as prior adaptive sampling approaches. Papers published at the Neural Information Processing Systems Conference.

Proximal algorithms for large-scale statistical modeling and optimal sensor/actuator selection Artificial Intelligence

Several problems in modeling and control of stochastically-driven dynamical systems can be cast as regularized semi-definite programs. We examine two such representative problems and show that they can be formulated in a similar manner. The first, in statistical modeling, seeks to reconcile observed statistics by suitably and minimally perturbing prior dynamics. The second seeks to optimally select a subset of available sensors and actuators for control purposes. To address modeling and control of large-scale systems we develop a unified algorithmic framework using proximal methods. Our customized algorithms exploit problem structure and allow handling statistical modeling, as well as sensor and actuator selection, for substantially larger scales than what is amenable to current general-purpose solvers. We establish linear convergence of the proximal gradient algorithm, draw contrast between the proposed proximal algorithms and alternating direction method of multipliers, and provide examples that illustrate the merits and effectiveness of our framework. Index Terms Actuator selection, sensor selection, sparsity-promoting estimation and control, method of multipliers, nonsmooth convex optimization, proximal algorithms, regularization for design, semi-definite programming, structured covariances. I. INTRODUCTION Convex optimization has had tremendous impact on many disciplines, including system identification and control design [1]-[7]. The present paper focuses on two representative control problems, statistical control-oriented modeling and sensor/actuator selection, that are cast as convex programs.

Algorithm selection by rational metareasoning as a model of human strategy selection

Neural Information Processing Systems

Selecting the right algorithm is an important problem in computer science, because the algorithm often has to exploit the structure of the input to be efficient. The human mind faces the same challenge. Therefore, solutions to the algorithm selection problem can inspire models of human strategy selection and vice versa. Here, we view the algorithm selection problem as a special case of metareasoning and derive a solution that outperforms existing methods in sorting algorithm selection. We apply our theory to model how people choose between cognitive strategies and test its prediction in a behavioral experiment.

Roku Channel Live TV Guide review: Hundreds of free channels, but there's a catch


Mindless channel surfing is a beautiful art form that's sort of been lost to time thanks to the rise of on-demand streaming. And Roku is as responsible for that as anyone. Last week, Roku added a bundle of new live TV broadcasts to the Roku Channel app, which is normally a hub for free, ad-supported content on the company's streaming devices. The addition of new channels wasn't the real news, though, as Roku also launched a live TV guide not unlike the ones you'd find on cable or satellite.