We propose a new exact minibatch MH method, TunaMH, which exposes a tunable trade-off between its batch size and its theoretically guaranteed convergence rate.

An example is the graph convolutional kernel support vector machine (GCKSVM) for node classification, for which we analyze the generalization error bound and discuss the impact of the graph structure.

Given a convex function f: Rd R, the problem of sampling from a distribution e f(x) is called log-concave sampling. This task has wide applications in machine learning, physics, statistics, etc.

In this work, we empirically investigate the impact of neural parameter symmetries by introducing new neural network architectures that have reduced parameter space symmetries.

Federated learning (FL) "involves training statistical models over remote devices or siloed data centers,suchasmobile phones orhospitals, whilekeepingdatalocalized"[56]because ofprivacy concerns orlimitedcommunication resources. Hence, clients only communicate with apotentially far-away (e.g., in another continent) orchestrator and do not Recent experimental and theoretical work suggests that, in practice,the first effect has been over-estimated by classic worst-caseconvergencebounds.