暂无分享,去创建一个
We prove non-asymptotic lower bounds on the expectation of the maximum of $d$ independent Gaussian variables and the expectation of the maximum of $d$ independent symmetric random walks. Both lower bounds recover the optimal leading constant in the limit. A simple application of the lower bound for random walks is an (asymptotically optimal) non-asymptotic lower bound on the minimax regret of online learning with expert advice.
[1] Gábor Lugosi,et al. Prediction, learning, and games , 2006 .
[2] Brendan D. Mckay. On Littlewood's estimate for the binomial distribution , 1989, Advances in Applied Probability.
[3] H. Robbins. A Remark on Stirling’s Formula , 1955 .
[4] Francesco Orabona,et al. Dimension-Free Exponentiated Gradient , 2013, NIPS.