Derives vector-valued self-normalized concentration bounds for light-tailed processes beyond sub-Gaussianity, with applications to online linear regression and linear bandits.
16 Given thate u ≤2 cosh(u)for allu∈R, it follows from Theorem 1 that 1 2 exp λ(ρI+V t)−1/2Mt exp − tX i=1 ei(λ) ! is dominated bySt
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Vector-valued self-normalized concentration inequalities beyond sub-Gaussianity
Derives vector-valued self-normalized concentration bounds for light-tailed processes beyond sub-Gaussianity, with applications to online linear regression and linear bandits.