continual learning 1fine-tuning 1game theory 1kl-regularization 1model auditing 1reinforcement learning 1
From the 1 of 14 linked papers with an AI index.
Showing math.PRShow all
3 papers · 1 filter
math.PR2025
Concentration inequalities for strong laws and laws of the iterated logarithm
Johannes Ruf, Ian Waudby-Smith
We derive concentration inequalities for sums of independent and identically distributed random variables that yield non-asymptotic generalizations of several strong laws of large…
math.PR2025
Nonasymptotic and distribution-uniform Komlós-Major-Tusnády approximation
Ian Waudby-Smith, Martin Larsson, Aaditya Ramdas
We present nonasymptotic concentration inequalities for sums of independent and identically distributed random variables that yield asymptotic strong Gaussian approximations of Kom…
math.PR2024
Distribution-uniform strong laws of large numbers
Ian Waudby-Smith, Martin Larsson, Aaditya Ramdas
We revisit the question of whether the strong law of large numbers (SLLN) holds uniformly in a rich family of distributions, culminating in a distribution-uniform generalization of…