3 papers
stat.ML2026
Beyond Worst-Case Coreset Bounds for -Clustering via Determinantal Sampling
Diptarka Chakraborty, Satyaki Mukherjee, Gaurav Vallabhdas Revankar +1
Massive datasets in modern machine learning have made data reduction a central challenge, particularly for clustering tasks where memory and computational constraints demand compac…
stat.ML2026
Determinantal sampling on general spaces: fast approximation via diffusion geometry
Hoang-Son Tran, Pranav Gupta, Subhroshekhar Ghosh
Determinantal point processes (DPPs) have recently emerged as a kernel-based alternative to standard independent sampling for constructing efficient minibatches, coresets, and othe…
stat.ML2024
Small coresets via negative dependence: DPPs, linear statistics, and concentration
Rémi Bardenet, Subhroshekhar Ghosh, Hugo Simon-Onfroy +1
Determinantal point processes (DPPs) are random configurations of points with tunable negative dependence. Because sampling is tractable, DPPs are natural candidates for subsamplin…