Timezone: »

Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy
Edward Moroshko · Blake Woodworth · Suriya Gunasekar · Jason Lee · Nati Srebro · Daniel Soudry

Wed Dec 09 07:50 AM -- 08:00 AM (PST) @ Orals & Spotlights: Deep Learning

We provide a detailed asymptotic study of gradient flow trajectories and their implicit optimization bias when minimizing the exponential loss over "diagonal linear networks". This is the simplest model displaying a transition between "kernel" and non-kernel ("rich" or "active") regimes. We show how the transition is controlled by the relationship between the initialization scale and how accurately we minimize the training loss. Our results indicate that some limit behavior of gradient descent only kick in at ridiculous training accuracies (well beyond 10^-100). Moreover, the implicit bias at reasonable initialization scales and training accuracies is more complex and not captured by these limits.

Author Information

Edward Moroshko (Technion)
Blake Woodworth (TTIC)
Suriya Gunasekar (Microsoft Research Redmond)
Jason Lee (Princeton University)
Nati Srebro (TTI-Chicago)
Daniel Soudry (Technion)

I am an assistant professor in the Department of Electrical Engineering at the Technion, working in the areas of Machine learning and theoretical neuroscience. I am especially interested in all aspects of neural networks and deep learning. I did my post-doc (as a Gruss Lipper fellow) working with Prof. Liam Paninski in the Department of Statistics, the Center for Theoretical Neuroscience the Grossman Center for Statistics of the Mind, the Kavli Institute for Brain Science, and the NeuroTechnology Center at Columbia University. I did my Ph.D. (2008-2013, direct track) in the Network Biology Research Laboratory in the Department of Electrical Engineering at the Technion, Israel Institute of technology, under the guidance of Prof. Ron Meir. In 2008 I graduated summa cum laude with a B.Sc. in Electrical Engineering and a B.Sc. in Physics, after studying in the Technion since 2004.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors