6.3k citations · 20.9k across the 54 of their papers we have counts for
Showing 2013 · cs.LGShow all
2 papers · 2 filters
cs.LG2013★ 11 cited
Large-Scale Learning with Less RAM via Randomization
Daniel Golovin, D. Sculley, H. Brendan McMahan +1
We reduce the memory footprint of popular large-scale online learning methods by projecting our weight vector onto a coarse discrete set using randomized rounding. Compared to stan…
cs.LG2013★ 1 cited
Minimax Optimal Algorithms for Unconstrained Linear Optimization
H. Brendan McMahan
We design and analyze minimax-optimal algorithms for online linear optimization games where the player's choice is unconstrained. The player strives to minimize regret, the differe…