A k-secretary algorithm achieving the optimal 1-O(1/sqrt(k)) competitive ratio with O(log k) memory via a reduction to a new O(log k)-memory quantile estimator with O(sqrt(k)) expected rank error.
Fast learning requires good memory: A time-space lower bound for parity learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
unclear 1representative citing papers
A polylog-sized quantum computer achieves exponential advantage over classical machines in classification and dimension reduction of massive classical data using quantum oracle sketching combined with classical shadows.
citing papers explorer
-
Optimal $k$-Secretary with Logarithmic Memory
A k-secretary algorithm achieving the optimal 1-O(1/sqrt(k)) competitive ratio with O(log k) memory via a reduction to a new O(log k)-memory quantile estimator with O(sqrt(k)) expected rank error.
-
Exponential quantum advantage in processing massive classical data
A polylog-sized quantum computer achieves exponential advantage over classical machines in classification and dimension reduction of massive classical data using quantum oracle sketching combined with classical shadows.