Ease.ml/snoopy in Action: Towards Automatic Feasibility Analysis for Machine Learning Application Development

The following Demo has been accepted at the 46th International Conference on Very Large Data Bases (VLDB 2020):

"Ease.ml/snoopy in Action: Towards Automatic Feasibility Analysis for Machine Learning Application Development" by Cedric Renggli (ETH Zurich), Luka Rimanic (ETH Zurich), Luka Kolar ( ETH Zurich), Wentao Wu (Microsoft Research), Ce Zhang (ETH).

Abstract:

We demonstrate ease.ml/snoopy, a data analytics system that performs feasibility analysis for machine learning (ML) applications before they are developed. Given a performance target of an ML application (e.g., accuracy above 0.95), ease.ml/snoopy provides a decisive answer to ML developers regarding whether the target is achievable or not. We formulate the feasibility analysis problem as an instance of Bayes error estimation. That is, for a data (distribution) on which the ML application should be performed, ease.ml/snoopy provides an estimate of the Bayes error -- the minimum error rate that can be achieved by any classifier. It is well-known that estimating the Bayes error is a notoriously hard task. In ease.ml/snoopy we explore and employ estimators based on the combination of (1) nearest neighbor (NN) classifiers and (2) pre-trained feature transformations. To the best of our knowledge, this is the first work on Bayes error estimation that combines (1) and (2). In today's cost-driven business world, feasibility of an ML project is an ideal piece of information for ML application developers -- ease.ml/snoopy plays the role of a reliable ''consultant''.