GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning

Entity Resolution and Federated Learning get a Federated Resolution

Consider two data providers, each maintaining records of different feature sets about common entities. They aim to learn a linear model over the whole set of features. This problem of federated learning over vertically partitioned data includes a crucial upstream issue: entity resolution, i.e. finding the correspondence between the rows of the datasets. It is well known that entity resolution, ...

Overdetermined Causation Cases, Contribution and the Shapley Value

Accurate and Efficient Expression Evaluation and Linear Algebra

We survey and unify recent results on the existence of accurate algorithms for evaluating multivariate polynomials, and more generally for accurate numerical linear algebra with structured matrices. By ‘accurate’ we mean that the computed answer has relative error less than 1, i.e., has some correct leading digits. We also address efficiency, by which we mean algorithms that run in polynomial t...

Accurate and efficient evaluation of Schur and Jack functions

We present new algorithms for computing the values of the Schur sλ(x1, x2, . . . , xn) and Jack J α λ (x1, x2, . . . , xn) functions in floating point arithmetic. These algorithms deliver guaranteed high relative accuracy for positive data (xi, α > 0) and run in time that is only linear in n.

Federated Multi-Task Learning

Federated learning poses new statistical and systems challenges in training machinelearning models over distributed networks of devices. In this work, we show thatmulti-task learning is naturally suited to handle the statistical challenges of thissetting, and propose a novel systems-aware optimization method, MOCHA, that isrobust to practical systems issues. Our method and theor...