Timezone: »

Implicit Regularization in Deep Matrix Factorization
Sanjeev Arora · Nadav Cohen · Wei Hu · Yuping Luo

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #245

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the implicit regularization of gradient descent over deep linear neural networks for matrix completion and sensing, a model referred to as deep matrix factorization. Our first finding, supported by theory and experiments, is that adding depth to a matrix factorization enhances an implicit tendency towards low-rank solutions, oftentimes leading to more accurate recovery. Secondly, we present theoretical and empirical arguments questioning a nascent view by which implicit regularization in matrix factorization can be captured using simple mathematical norms. Our results point to the possibility that the language of standard regularizers may not be rich enough to fully encompass the implicit regularization brought forth by gradient-based optimization.

Author Information

Sanjeev Arora (Princeton University)
Nadav Cohen (Tel Aviv University)
Wei Hu (Princeton University)
Yuping Luo (Princeton University)

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

More from the Same Authors