20 citations · 66 across the 30 of their papers we have counts for
Showing 2017 · cs.LGShow all
2 papers · 2 filters
cs.LG2017★ 13 cited
Worst-case vs Average-case Design for Estimation from Fixed Pairwise Comparisons
Ashwin Pananjady, Cheng Mao, Vidya Muthukumar +2
Pairwise comparison data arises in many domains, including tournament rankings, web search, and preference elicitation. Given noisy comparisons of a fixed subset of pairs of items,…
cs.LG2017★ 20 cited
Gradient Diversity: a Key Ingredient for Scalable Distributed Learning
Dong Yin, Ashwin Pananjady, Max Lam +3
It has been experimentally observed that distributed implementations of mini-batch stochastic gradient descent (SGD) algorithms exhibit speedup saturation and decaying generalizati…