Revisiting Stein's paradox: multi-task averaging

Revisiting Quotes from Educational Perspective: An Inquiry into the Multifarious Applications of Grand Quotes in English Language Pedagogy

Distributed Stochastic Multi-Task Learning with Graph Regularization

We propose methods for distributed graph-based multi-task learning that are based on weighted averaging of messages from other machines. Uniform averaging or diminishing stepsize in these methods would yield consensus (single task) learning. We show how simply skewing the averaging weights or controlling the stepsize allows learning different, but related, tasks on the different machines.

Revisiting Recurrent Networks for Paraphrastic Sentence Embeddings

We consider the problem of learning general-purpose, paraphrastic sentence embeddings, revisiting the setting of Wieting et al. (2016b). While they found LSTM recurrent networks to underperform word averaging, we present several developments that together produce the opposite conclusion. These include training on sentence pairs rather than phrase pairs, averaging states to represent sequences, ...

Multi-Task Averaging

We present a multi-task learning approach to jointly estimate the means of multiple independent data sets. The proposed multi-task averaging (MTA) algorithm results in a convex combination of the single-task averages. We derive the optimal amount of regularization, and show that it can be effectively estimated. Simulations and real data experiments demonstrate that MTA outperforms both maximum ...

Revisiting the 'Low BirthWeight paradox' using a model-based definition.

INTRODUCTION Immigrant mothers in Spain have a lower risk of delivering Low BirthWeight (LBW) babies in comparison to Spaniards (LBW paradox). This study aimed at revisiting this finding by applying a model-based threshold as an alternative to the conventional definition of LBW. METHODS Vital information data from Madrid was used (2005-2006). LBW was defined in two ways (less than 2500g and W...