Approximate MDL with additive slack C guarantees finite expected squared prediction error for λ ≥ 1 via telescoping and stopping-time arguments, but fails for λ < 1 or multiplicative approximations.
Léonard Blier and Yann Ollivier
1 Pith paper cite this work, alongside 12 external citations. Polarity classification is still indexing.
1
Pith paper citing it
12
external citations · external index
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Prediction Under Imperfect Compression: A Theory of Approximate MDL
Approximate MDL with additive slack C guarantees finite expected squared prediction error for λ ≥ 1 via telescoping and stopping-time arguments, but fails for λ < 1 or multiplicative approximations.