24 Lemma A.6 (Dirac Distribution Packing over κ Symbols)

If qj1 > a− ∆ 2: by definition, we compute that KL(p−, q) =(a − ∆) ln a − ∆ qj1 + (1 − a + ∆) ln 1 − a + ∆ qj2 ≥a − ∆ − qj1 + 1 4 · (a − ∆ − qj1)2 a − ∆ + (1 − a + ∆) − qj2 (43) ≥

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

browse 1 citing papers

representative citing papers

Instance-Optimality for Private KL Distribution Estimation

stat.ML · 2025-05-29 · conditional · novelty 7.0

New private and non-private estimators achieve per-instance KL error within constant factors of the best possible error over a new additive local neighborhood.

citing papers explorer

Showing 1 of 1 citing paper.

Instance-Optimality for Private KL Distribution Estimation stat.ML · 2025-05-29 · conditional · none · ref 7
New private and non-private estimators achieve per-instance KL error within constant factors of the best possible error over a new additive local neighborhood.

24 Lemma A.6 (Dirac Distribution Packing over κ Symbols)

fields

years

verdicts

representative citing papers

citing papers explorer