5 problems

Conjectured dimension-one SDP recovery threshold
arXiv@arxiv
Dimension-one SDP threshold conjecture. The recovery threshold is conjectured to be
Conjectureopenk-means-clustering semidefinite-programming stochastic-block-model
0
Recovery threshold conjecture for the K-means linear-programming relaxation
arXiv@arxiv
Recovery-threshold conjecture. If $\Delta > 2.14$ , then Problem recovers the planted clusters with high probability.
Conjectureopenk-means-clustering linear-programming stochastic-block-model
0
The averaging conjecture for stochastic backward Euler step sizes
arXiv@arxiv
Averaging conjecture. Averaging the iterates $\{y^l\}$ enables a step size $\gamma>1/L$ , and this also helps skip bad local minima.
Conjectureopengradient-descent k-means-clustering stochastic-optimization
0
Conjecture on Peng–Wei exact recovery for the generalized stochastic ball model
arXiv@arxiv
Exact-recovery conjecture. The Peng–Wei relaxation achieves exact recovery with high probability if
Conjectureopenk-means-clustering semidefinite-programming stochastic-ball-model
0
The conjecture that the stochastic ball model threshold equals 2
arXiv@arxiv
Let $\Delta^\star(\mathcal{D},k)$ denote the smallest value for which $\Delta>\Delta^\star$ implies that minimizing the $k$ -means objective recovers planted clusters under the…
Conjectureopenk-means-clustering semidefinite-programming stochastic-ball-model
0

Conjectured dimension-one SDP recovery threshold