no code implementations • 20 Feb 2020 • Nicholas J. A. Harvey, Christopher Liaw, Edwin Perkins, Sikander Randhawa
In the fixed-time setting, where the time horizon is known in advance, algorithms that achieve the optimal regret are known when there are two, three, or four experts or when the number of experts is large.
no code implementations • 2 Sep 2019 • Nicholas J. A. Harvey, Christopher Liaw, Sikander Randhawa
We consider a simple, non-uniform averaging strategy of Lacoste-Julien et al. (2011) and prove that it achieves the optimal $O(1/T)$ convergence rate with high probability.
no code implementations • 13 Dec 2018 • Nicholas J. A. Harvey, Christopher Liaw, Yaniv Plan, Sikander Randhawa
We prove that after $T$ steps of stochastic gradient descent, the error of the final iterate is $O(\log(T)/T)$ with high probability.