Linear-Epoch Gradual-Warmup (LEGW)
Large-batch training approaches have enabled researchers to utilize large-scale distributed processing and greatly accelerate deep-neural net (DNN) training. For example, by scaling the batch size from 256 to 32K, researchers have been able to reduce the training time of ResNet50 on ImageNet from 29 hours to 2.2 minutes (Ying et al., 2018). In this paper, we propose a new approach called linear-epoch gradual-warmup (LEGW) for better large-batch training. With LEGW, we are able to conduct large-batch training for both CNNs and RNNs with the Sqrt Scaling scheme. LEGW enables Sqrt Scaling scheme to be useful in practice and as a result we achieve much better results than the Linear Scaling learning rate scheme. For LSTM applications, we are able to scale the batch size by a factor of 64 without losing accuracy and without tuning the hyper-parameters. For CNN applications, LEGW is able to achieve the same accuracy even as we scale the batch size to 32K. LEGW works better than previous large-batch auto-tuning techniques. LEGW achieves a 5.3X average speedup over the baselines for four LSTM-based applications on the same hardware. We also provide some theoretical explanations for LEGW. …

Lord’s Paradox
In statistics, Lord’s paradox raises the issue of when it is appropriate to control for baseline status. In three papers, Frederic Lord noted that different results obtain if researchers adjust for pre-existing differences. The paradox was resolved by Paul Holland and Donald Rubin using the Rubin causal model. The most famous formulation of Lord’s paradox was in his 1967 paper and was phrased in terms of weight change over freshman year of college in two different dormitories because Lord did not want readers to assume that measurement error was responsible for the paradox. ‘A large university is interested in investigating the effects on the students of the diet provided in the university dining halls and any sex differences in these effects. Various types of data are gathered. In particular, the weight of each student at the time of his arrival in September and his weight the following June are recorded.’ (Lord 1967, p. 304)
Resolving the Lord’s Paradox …

PeyeDF
PeyeDF is a Portable Document Format (PDF) reader with eye tracking support, available as free and open source software. It is especially useful to researchers investigating reading and learning phenomena, as it integrates PDF reading-related behavioural data with gaze-related data. It is suitable for short and long-term research and supports multiple eye tracking systems. We utilised it to conduct an experiment which demonstrated that features obtained from both gaze and reading data collected in the past can predict reading comprehension which takes place in the future. PeyeDF also provides an integrated means for data collection and indexing using the DiMe personal data storage system. It is designed to collect data in the background without interfering with the reading experience, behaving like a modern lightweight PDF reader. Moreover, it supports annotations, tagging and collaborative work. A modular design allows the application to be easily modified in order to support additional eye tracking protocols and run controlled experiments. We discuss the implementation of the software and report on the results of the experiment which we conducted with it. …

Quasi-Monte Carlo Variational Inference (QMC)
Many machine learning problems involve Monte Carlo gradient estimators. As a prominent example, we focus on Monte Carlo variational inference (MCVI) in this paper. The performance of MCVI crucially depends on the variance of its stochastic gradients. We propose variance reduction by means of Quasi-Monte Carlo (QMC) sampling. QMC replaces N i.i.d. samples from a uniform probability distribution by a deterministic sequence of samples of length N. This sequence covers the underlying random variable space more evenly than i.i.d. draws, reducing the variance of the gradient estimator. With our novel approach, both the score function and the reparameterization gradient estimators lead to much faster convergence. We also propose a new algorithm for Monte Carlo objectives, where we operate with a constant learning rate and increase the number of QMC samples per iteration. We prove that this way, our algorithm can converge asymptotically at a faster rate than SGD. We furthermore provide theoretical guarantees on QMC for Monte Carlo objectives that go beyond MCVI, and support our findings by several experiments on large-scale data sets from various domains. …