CoinRun
In this paper, we investigate the problem of overfitting in deep reinforcement learning. Among the most common benchmarks in RL, it is customary to use the same environments for both training and testing. This practice offers relatively little insight into an agent’s ability to generalize. We address this issue by using procedurally generated environments to construct distinct training and test sets. Most notably, we introduce a new environment called CoinRun, designed as a benchmark for generalization in RL. Using CoinRun, we find that agents overfit to surprisingly large training sets. We then show that deeper convolutional architectures improve generalization, as do methods traditionally found in supervised learning, including L2 regularization, dropout, data augmentation and batch normalization. …

Randomized Principal Component Analysis (RPCA)
Recently popularized randomized methods for principal component analysis (PCA) efficiently and reliably produce nearly optimal accuracy – even on parallel processors – unlike the classical (deterministic) alternatives. We adapt one of these randomized methods for use with data sets that are too large to be stored in random-access memory (RAM). (The traditional terminology is that our procedure works efficiently out-of-core.) We illustrate the performance of the algorithm via several numerical examples. For example, we report on the PCA of a data set stored on disk that is so large that less than a hundredth of it can fit in our computer’s RAM. Read More: https://…/100804139 …

SFIEGARCH
Here we develop the theory of seasonal FIEGARCH processes, denoted by SFIEGARCH, establishing conditions for the existence, the invertibility, the stationarity and the ergodicity of these processes. We analyze their asymptotic dependence structure by means of the autocovariance and autocorrelation functions. We also present some properties regarding their spectral representation. All properties are illustrated through graphical examples and an application of SFIEGARCH models to describe the volatility of the S&P500 US stock index log-return time series in the period from December 13, 2004 to October 10, 2009 is provided. …

Paraphrase Adversaries from Word Scrambling (PAWS)
Existing paraphrase identification datasets lack sentence pairs that have high lexical overlap without being paraphrases. Models trained on such data fail to distinguish pairs like flights from New York to Florida and flights from Florida to New York. This paper introduces PAWS (Paraphrase Adversaries from Word Scrambling), a new dataset with 108,463 well-formed paraphrase and non-paraphrase pairs with high lexical overlap. Challenging pairs are generated by controlled word swapping and back translation, followed by fluency and paraphrase judgments by human raters. State-of-the-art models trained on existing datasets have dismal performance on PAWS (<40% accuracy); however, including PAWS training data for these models improves their accuracy to 85% while maintaining performance on existing tasks. In contrast, models that do not capture non-local contextual information fail even with PAWS training examples. As such, PAWS provides an effective instrument for driving further progress on models that better exploit structure, context, and pairwise comparisons. …