2 problems

0 votes0 replies0 views
Folklore conjecture that subgaussian mixtures are harder to cluster than Gaussian mixtures
A subgaussian distribution is a distribution whose one-dimensional marginals have uniformly subgaussian tails, and a mixture-clustering regime is specified by the separation betwee…
Conjectureopencomputational-statistics mixture-models subgaussian-distributionsarXiv posted 2 days ago
0 votes0 replies0 views
Nie-Gollakota-Srivastava's computational lower-bound conjecture for robust subgaussian mean estimation
Nie-Gollakota-Srivastava's conjecture. No polynomial-time algorithm achieves optimal error for $\mathcal{P}_{\mathrm{subgaussian}}$ .
Conjectureopencomputational-complexity robust-estimation subgaussian-distributionsarXiv posted 2 days ago

Folklore conjecture that subgaussian mixtures are harder to cluster than Gaussian mixtures