A note on concentration inequality for vector-valued martingales with weak exponential-type tails
We present novel martingale concentration inequalities for martingale differences with finite Orlicz-$\psi_\alpha$ norms. Such martingale differences with weak exponential-type tails scatters in many statistical applications and can be heavier than sub-exponential distributions. In the case of one dimension, we prove in general that for a sequence of scalar-valued supermartingale difference, the tail bound depends solely on the sum of squared Orlicz-$\psi_\alpha$ norms instead of the maximal Orlicz-$\psi_\alpha$ norm, generalizing the results of Lesigne & Voln\'y (2001) and Fan et al. (2012). In the multidimensional case, using a dimension reduction lemma proposed by Kallenberg & Sztencel (1991) we show that essentially the same concentration tail bound holds for vector-valued martingale difference sequences.
Code (0)
등록된 구현이 없습니다.
Tasks
Dimensionality ReductionLEMMASimilar Papers 제목 키워드 기반
On Kernelized Multi-armed Bandits
We consider the stochastic bandit problem with a continuous set of arms, with the expected reward function over the arms assumed to be fixed but unknown. We provide two new Gaussian process-based algorithms for continuou…
Multi-Armed BanditsNeural Logistic Bandits
We study the problem of neural logistic bandits, where the main task is to learn an unknown reward function within a logistic link function using a neural network. Existing approaches either exhibit unfavorable dependenc…
Concentration inequalities under sub-Gaussian and sub-exponential conditions
We prove analogues of the popular bounded difference inequality (also called McDiarmid's inequality) for functions of independent random variables under sub-gaussian and sub-exponential conditions. Applied to vector-valu…
regressionSharp Finite-Time Iterated-Logarithm Martingale Concentration
We give concentration bounds for martingales that are uniform over finite times and extend classical Hoeffding and Bernstein inequalities. We also demonstrate our concentration bounds to be optimal with a matching anti-c…
Optimal Sample Complexity of Subgradient Descent for Amplitude Flow via Non-Lipschitz Matrix Concentration
We consider the problem of recovering a real-valued $n$-dimensional signal from $m$ phaseless, linear measurements and analyze the amplitude-based non-smooth least squares objective. We establish local convergence of sub…