International Business Machines Corporation

Youssef Mroueh

Tom Sercu

Cicero Nogueira Dos Santos

Alper Buyuktosunoglu

Wei Zhang

Xiaodong Cui

Abdullah Kayi

Inkit Padhi

Pierre L Dognin

Igor Melnyk

Mattia Rigotti

Mingrui Liu

Tom D J Sercu

Jarret Ross

A method, system and apparatus of ensembling, including inputting a set of models that predict different sets of attributes, determining a source set of attributes and a target set of attributes using a barycenter with an optimal transport metric, and determining a consensus among the set of models whose predictions are defined on the source set of attributes.

Wasserstein barycenter model ensembling

Systems, computer-implemented methods, and computer program products to facilitate updating, such as averaging and/or training, of one or more statistical sets are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can include a computing component that averages a statistical set, provided by the system, with an additional statistical set, that is compatible with the statistical set, to compute an averaged statistical set, where the additional statistical set is obtained from a selected additional system of a plurality of additional systems. The computer executable components also can include a selecting component that selects the selected additional system according to a randomization pattern.

Updating of statistical sets for decentralized distributed training of a machine learning model

A machine learning system that implements Sobolev Independence Criterion (SIC) for feature selection is provided. The system receives a dataset including pairings of stimuli and responses. Each stimulus includes multiple features. The system generates a correctly paired sample of stimuli and responses from the dataset by pairing stimuli and responses according to the pairings of stimuli and responses in the dataset. The system generates an alternatively paired sample of stimuli and responses from the dataset by pairing stimuli and responses differently than the pairings of stimuli and responses in the dataset. The system determines a witness function and a feature importance distribution across the features that optimizes a cost function that is evaluated based on the correctly paired and alternatively paired samples of the dataset. The system selects one or more features based on the computed feature importance distribution.

Feature selection using Sobolev Independence Criterion

A computing device receives a data X and Y, each having N samples. A function f(x,y) is defined to be a trainable neural network based on the data X and the data Y. A permuted version of the data Y is created. A loss mean is computed based on the trainable neural network f(x,y), the permuted version of the sample data Y, and a trainable scalar variable &#x3b7;. A loss with respect to the scalar variable &#x3b7; and the trainable neural network is minimized. Upon determining that the loss is at or below the predetermined threshold, estimating a mutual information (MI) between a test data Xand Y. If the estimated MI is above a predetermined threshold, the test data Xand Yis deemed to be dependent. Otherwise, it is deemed to be independent.

Mutual information neural estimation with Eta-trick

A machine learning system receives a witness function that is determined based on an initial sample of a dataset comprising multiple pairs of stimuli and responses. Each stimulus includes multiple features. The system receives a holdout sample of the dataset comprising one or more pairs of stimuli and responses that are not used to determine the witness function. The system generates a simulated sample based on the holdout sample. Values of a particular feature of the stimuli of the simulated sample are predicted based on values of features other than the particular feature of the stimuli of the simulated sample. The system applies the holdout sample to the witness function to obtain a first result. The system applies the simulated sample to the witness function to obtain a second result. The system determines whether to select the particular feature based on a comparison between the first result and the second result.

False detection rate control with null-hypothesis

Systems, computer-implemented methods, and computer program products for transforming a source distribution to a target distribution. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a sampling component that receives a source distribution having a source sample and a target distribution having a target sample. The computer executable components can further comprise an optimizer component that employs a neural network to find a critic that dynamically discriminates between the source sample and the target sample, while constraining a gradient of the neural network. The computer executable components can further comprise a morphing component that generates a first product distribution by morphing the source distribution along the gradient of the neural network to the target distribution.

Growing community of inventors

New York, NY, United States of America

Youssef Mroueh