Bayesian Coresets: Revisiting the Nonconvex Optimization Perspective
It addresses scalable Bayesian inference for data-intensive applications, representing an incremental improvement over existing coreset methods.
The paper tackles the Bayesian coreset selection problem by proposing a novel algorithm based on sparsity constrained optimization, achieving superior speed and accuracy compared to state-of-the-art methods on benchmark datasets.
Bayesian coresets have emerged as a promising approach for implementing scalable Bayesian inference. The Bayesian coreset problem involves selecting a (weighted) subset of the data samples, such that the posterior inference using the selected subset closely approximates the posterior inference using the full dataset. This manuscript revisits Bayesian coresets through the lens of sparsity constrained optimization. Leveraging recent advances in accelerated optimization methods, we propose and analyze a novel algorithm for coreset selection. We provide explicit convergence rate guarantees and present an empirical evaluation on a variety of benchmark datasets to highlight our proposed algorithm's superior performance compared to state-of-the-art on speed and accuracy.