Timezone: »

Implicit Regularization in Matrix Factorization
Suriya Gunasekar · Blake Woodworth · Srinadh Bhojanapalli · Behnam Neyshabur · Nati Srebro

Tue Dec 05 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #162
We study implicit regularization when optimizing an underdetermined quadratic objective over a matrix $X$ with gradient descent on a factorization of X. We conjecture and provide empirical and theoretical evidence that with small enough step sizes and initialization close enough to the origin, gradient descent on a full dimensional factorization converges to the minimum nuclear norm solution.

Author Information

Suriya Gunasekar (TTI Chicago)
Blake Woodworth (TTI-Chicago)
Srinadh Bhojanapalli (Google Research)
Behnam Neyshabur (New York University)

I am a staff research scientist at Google. Before that, I was a postdoctoral researcher at New York University and a member of Theoretical Machine Learning program at Institute for Advanced Study (IAS) in Princeton. In summer 2017, I received a PhD in computer science at TTI-Chicago where I was fortunate to be advised by Nati Srebro.

Nati Srebro (TTI-Chicago)

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

More from the Same Authors