Feature Sampling google
Deep Neural Networks (DNNs) thrive in recent years in which Batch Normalization (BN) plays an indispensable role. However, it has been observed that BN is costly due to the reduction operations. In this paper, we propose alleviating this problem through sampling only a small fraction of data for normalization at each iteration. Specifically, we model it as a statistical sampling problem and identify that by sampling less correlated data, we can largely reduce the requirement of the number of data for statistics estimation in BN, which directly simplifies the reduction operations. Based on this conclusion, we propose two sampling strategies, ‘Batch Sampling’ (randomly select several samples from each batch) and ‘Feature Sampling’ (randomly select a small patch from each feature map of all samples), that take both computational efficiency and sample correlation into consideration. Furthermore, we introduce an extremely simple variant of BN, termed as Virtual Dataset Normalization (VDN), that can normalize the activations well with few synthetical random samples. All the proposed methods are evaluated on various datasets and networks, where an overall training speedup by up to 20% on GPU is practically achieved without the support of any specialized libraries, and the loss on accuracy and convergence rate are negligible. Finally, we extend our work to the ‘micro-batch normalization’ problem and yield comparable performance with existing approaches at the case of tiny batch size. …

Grid Search google
The de facto standard way of performing hyperparameter optimization is grid search, which is simply an exhaustive searching through a manually specified subset of the hyperparameter space of a learning algorithm. A grid search algorithm must be guided by some performance metric, typically measured by cross-validation on the training set or evaluation on a held-out validation set. Since the parameter space of a machine learner may include real-valued or unbounded value spaces for certain parameters, manually set bounds and discretization may be necessary before applying grid search. …

SHAnnon DEcay (SHADE) google
Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The originality of the approach is to define a prior based on conditional entropy, which explicitly decouples the learning of invariant representations in the regularizer and the learning of correlations between inputs and labels in the data fitting term. Our second contribution is to derive a stochastic version of the regularizer compatible with deep learning, resulting in a tractable training scheme. We empirically validate the efficiency of our approach to improve classification performances compared to standard regularization schemes on several standard architectures. …