A simple subgaussian argument lets the Sparsitron algorithm recover SK model parameters in polynomial time for all beta <= sqrt(log n), breaking the beta=1 barrier.
A very simple proof of the lsi for high temperature spin systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning the Sherrington-Kirkpatrick Model Even at Low Temperature
A simple subgaussian argument lets the Sparsitron algorithm recover SK model parameters in polynomial time for all beta <= sqrt(log n), breaking the beta=1 barrier.