885 citations · 2.1k across the 60 of their papers we have counts for
3 papers · 1 filter
Approximate Gradient Coding via Sparse Random Graphs
Zachary Charles, Dimitris Papailiopoulos, Jordan Ellenberg
Distributed algorithms are often beset by the straggler effect, where the slowest compute nodes in the system dictate the overall running time. Coding-theoretic techniques have bee…
Stability and Generalization of Learning Algorithms that Converge to Global Optima
Zachary Charles, Dimitris Papailiopoulos
We establish novel generalization bounds for learning algorithms that converge to global minima. We do so by deriving black-box stability results that only depend on the convergenc…
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…