activity
20182023
most citedCharacterizing Implicit Bias in Terms of Optimization Geometry

168 citations · 361 across the 47 of their papers we have counts for

collaborators
Showing 2018Show all

2 papers · 1 filter

cs.LG2018★ 35 cited

Implicit Bias of Gradient Descent on Linear Convolutional Networks

Suriya Gunasekar, Jason Lee, Daniel Soudry +1

We show that gradient descent on full-width linear convolutional networks of depth converges to a linear predictor related to the bridge penalty in the frequency d…

stat.ML2018★ 168 cited

Characterizing Implicit Bias in Terms of Optimization Geometry

Suriya Gunasekar, Jason Lee, Daniel Soudry +1

We study the implicit bias of generic optimization methods, such as mirror descent, natural gradient descent, and steepest descent with respect to different potentials and norms, w…