119 citations · 244 across the 26 of their papers we have counts for
Showing 2016Show all
3 papers · 1 filter
cs.LG2016★ 1 cited
CompAdaGrad: A Compressed, Complementary, Computationally-Efficient Adaptive Gradient Method
Nishant A. Mehta, Alistair Rendell, Anish Varghese +1
The adaptive gradient online learning method known as AdaGrad has seen widespread use in the machine learning community in stochastic and adversarial online learning problems and m…
cs.LG2016★ 9 cited
Fast rates with high probability in exp-concave statistical learning
Nishant A. Mehta
We present an algorithm for the statistical learning setting with a bounded exp-concave loss in dimensions that obtains excess risk with probability at least…
cs.LG2016★ 54 cited
Fast Rates for General Unbounded Loss Functions: from ERM to Generalized Bayes
Peter D. Grünwald, Nishant A. Mehta
We present new excess risk bounds for general unbounded loss functions including log loss and squared loss, where the distribution of the losses may be heavy-tailed. The bounds hol…