174 citations · 991 across the 46 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.LG2020★ 3 cited
Gradient descent follows the regularization path for general losses
Ziwei Ji, Miroslav Dudík, Robert E. Schapire +1
Recent work across many machine learning disciplines has highlighted that standard descent methods, even without explicit regularization, do not merely minimize the training error,…
cs.LG2020★ 14 cited
Directional convergence and alignment in deep learning
Ziwei Ji, Matus Telgarsky
In this paper, we show that although the minimizers of cross-entropy and related classification losses are off at infinity, network weights learned by gradient flow converge in dir…