We can also see this visually. We can verify the convergence of the chains formally using the Gelman Rubin test. Values close to 1.0 mean convergence. We can also test for correlation between samples in the chains. We are aiming for zero auto-correlation to get "random" samples from the posterior distribution. From these plots we see that the auto-correlation is not problematic.
Last night on the train I read this nice paper by David Duvenaud and colleagues. So I thought it's time for a David Duvenaud birthday special (don't get too excited David, I won't make it an annual tradition...) I recently covered iMAML: the meta-learning algorithm that makes use of implicit gradients to sidestep backpropagating through the inner loop optimization in meta-learning/hyperparameter tuning. The method presented in (Lorraine et al, 2019) uses the same high-level idea, but introduces a different - on the surface less fiddly - approximation to the crucial inverse Hessian. I won't spend a lot of time introducing the whole meta-learning setup from scratch, you can use the previous post as a starting point. Many - though not all - meta-learning or hyperparameter optimization problems can be stated as nested optimization problems.
Patients in intensive care units (ICU) are acutely ill and have the highest mortality rates for hospitalized patients. Predictive models and planning system could forecast and guide interventions to prevent the hazardous deterioration of patients’ physiologies, thereby giving the opportunity of employing machine learning and inference to assist with the care of ICU patients. We report on the construction of a prediction pipeline that estimates the probability of death by inferring rates of hazard over time, based on patients’ physiological measurements. The inferred model provided the contribution of each variable and information about the influence of sets of observations on the overall risks and expected trajectories of patients.
Qubole is announcing the availability of a working implementation of Apache Spark on AWS Lambda. This prototype has been able to show a successful scan of 1 TB of data and sort 100 GB of data from AWS Simple Storage Service (S3). This article dives into the technical details of how we built this prototype and the code changes required on top of Apache Spark 2.1.0.
Adequate evaluation of an information retrieval system to estimate future performance is a crucial task. Area under the ROC curve (AUC) is widely used to evaluate the generalization of a retrieval system. However, the objective function optimized in many retrieval systems is the error rate and not the AUC value. This paper provides an efficient and effective non-linear approach to optimize AUC using additive regression trees, with a special emphasis on the use of multi-class AUC (MAUC) because multiple relevance levels are widely used in many ranking applications. Compared to a conventional linear approach, the performance of the non-linear approach is comparable on binary-relevance benchmark datasets and is better on multi-relevance benchmark datasets.