Develops a McDiarmid-type concentration inequality for causal autoregressive processes that preserves sparsity to achieve O(1) variance proxies instead of O(N).
Bounding d-distance by informational divergence: A method to prove measure concentration.The Annals of Probability, 24(2):857–866
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Matrix-Decoupled Concentration for Autoregressive Sequences: Dimension-Free Guarantees for Sparse Long-Context Rewards
Develops a McDiarmid-type concentration inequality for causal autoregressive processes that preserves sparsity to achieve O(1) variance proxies instead of O(N).