978 citations · 1.6k across the 24 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
stat.ML2017
High-dimensional dynamics of generalization error in neural networks
Madhu S. Advani, Andrew M. Saxe
We perform an average case analysis of the generalization dynamics of large neural networks trained using gradient descent. We study the practically-relevant "high-dimensional" reg…
cs.AI2017★ 5 cited
Hierarchical Subtask Discovery With Non-Negative Matrix Factorization
Adam C. Earle, Andrew M. Saxe, Benjamin Rosman
Hierarchical reinforcement learning methods offer a powerful means of planning flexible behavior in complicated domains. However, learning an appropriate hierarchical decomposition…