Abstract: A technique for generating a performance prediction of a machine learning model with uncertainty intervals includes obtaining a first model configured to perform a task and a production dataset. At least one metric predicting a performance of the first model at performing the task on the production dataset is generated using a second model. The second model is a meta-model associated with the first model. At least one value predicting an uncertainty of the at least one metric predicting the performance of the first model at performing the task on the production dataset is generated using a third model. The third model is a meta-meta-model associated with the second model. An indication of the at least one metric and the at least one value is provided.

Abstract: A computer-implemented method, a computer program product, and a system for reducing labeled sample quantities required to update test sets. The computer-implemented method includes inputting a portion of unlabeled production data into a base model and generating labeled output relating to the unlabeled production data. The computer-implemented method also includes inputting the labeled output into a performance predictor. The performance predictor is a meta model of the base model that is trained with another portion of the unlabeled production data, a training set used to train the base model, and a test set portioned from the training set. The computer-implemented method further includes outputting, by the performance predictor, a performance metric relating to the labeled output produced by the trained base model. The performance metric can be any metric capable of measuring the output performance of the base model.

Abstract: Hybrid on-policy/off-policy techniques are provided for improving the estimation of quality (reward) of a control policy for decision making by combining the on-policy and off-policy data from multiple estimators into a single metric. In one aspect, a method for estimating a reward of a policy for decision making in a computer system includes: computing multiple reward estimates of the policy using estimators, wherein at least a subset of the estimators compute reward estimates with prediction intervals; and combining the multiple reward estimates using a combiner to produce a new reward estimate. Thus, some of the estimators might compute the reward estimates without prediction intervals. A method for estimating a reward of a policy when another one or more of the estimators compute reward estimates without prediction intervals is also provided.

Abstract: A computer implemented method of performing large-scale machine learning experiments includes expanding on one or more input datasets by systematically generating several data set drift splits. A set of experimental jobs corresponding to the generated data set drift splits are executed to generate experimental results. The experimental results are processed, consolidated, and clustered according to the generated data set drift splits.

Abstract: A computer-implemented method, a computer program product, and a system for reducing labeled sample quantities required to update test sets. The computer-implemented method includes inputting a portion of unlabeled production data into a base model and generating labeled output relating to the unlabeled production data. The computer-implemented method also includes inputting the labeled output into a performance predictor. The performance predictor is a meta model of the base model that is trained with another portion of the unlabeled production data, a training set used to train the base model, and a test set portioned from the training set. The computer-implemented method further includes outputting, by the performance predictor, a performance metric relating to the labeled output produced by the trained base model. The performance metric can be any metric capable of measuring the output performance of the base model.

Abstract: A technique for generating a performance prediction of a machine learning model with uncertainty intervals includes obtaining a first model configured to perform a task and a production dataset. At least one metric predicting a performance of the first model at performing the task on the production dataset is generated using a second model. The second model is a meta-model associated with the first model. At least one value predicting an uncertainty of the at least one metric predicting the performance of the first model at performing the task on the production dataset is generated using a third model. The third model is a meta-meta-model associated with the second model. An indication of the at least one metric and the at least one value is provided.