Develops a McDiarmid-type concentration inequality for causal autoregressive processes that preserves sparsity to achieve O(1) variance proxies instead of O(N).
Inequalities for sums of dependent random variables and applications to sampling.Probability Theory and Related Fields, 118:163–191
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).