Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
Batch Normalization is quite effective at accelerating and improving the training of deep models. However, its effectiveness diminishes when the training minibatches are small, or do not consist of independent samples. We hypothesize that this is due to the dependence of model layer inputs on all the examples in the minibatch, and different activations being produced between training and inference. We propose Batch Renormalization, a simple and effective extension to ensure that the training and inference models generate the same outputs that depend on individual examples rather than the entire minibatch. Models trained with Batch Renormalization perform substantially better than batchnorm when training with small or non-i.i.d. minibatches. At the same time, Batch Renormalization retains the benefits of batchnorm such as insensitivity to initialization and training efficiency.
Code (5)
Similar Papers 제목 키워드 기반
An Even More Optimal Stochastic Optimization Algorithm: Minibatching and Interpolation Learning
We present and analyze an algorithm for optimizing smooth and convex or strongly convex objectives using minibatch stochastic gradient estimates. The algorithm is optimal with respect to its dependence on both the miniba…
Stochastic OptimizationPoisson-Minibatching for Gibbs Sampling with Convergence Rate Guarantees
Gibbs sampling is a Markov chain Monte Carlo method that is often used for learning and inference on graphical models. Minibatching, in which a small random subset of the graph is used at each iteration, can help make Gi…
Faster SGD training by minibatch persistency
It is well known that, for most datasets, the use of large-size minibatches for Stochastic Gradient Descent (SGD) typically leads to slow convergence and poor generalization. On the other hand, large minibatches are of g…
GPUExtreme normalization: approximating full-data batch normalization with single examples
While batch normalization has been successful in speeding up the training of neural networks, it is not well understood. We cast batch normalization as an approximation of the limiting case where the entire dataset is no…
Determinantal point processes based on orthogonal polynomials for sampling minibatches in SGD
Stochastic gradient descent (SGD) is a cornerstone of machine learning. When the number N of data items is large, SGD relies on constructing an unbiased estimator of the gradient of the empirical risk using a small subse…
Point Processes