In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning

Cryptographic limitations on learning boolean formulae and finite automata

Kearns, Michael and Valiant, Leslie · 1994

Earlier work this paper cites.

Maximum-margin matrix factorization

Srebro, Nathan, Rennie, Jason, and Jaakkola, Tommi S · 1994

Earlier work this paper cites.

Neural network learning: Theoretical foundations

Anthony, Martin and Bartlett, Peter L · 1999

Earlier work this paper cites.

A rank minimization heuristic with application to minimum order system approximation

Fazel, Maryam, Hindi, Haitham, and Boyd, Stephen P · 2001

Earlier work this paper cites.

Weighted low-rank approximations

Srebro, Nathan and Jaakkola, Tommi S · 2003

Earlier work this paper cites.

Convex neural networks

Bengio, Yoshua, Roux, Nicolas L., Vincent, Pascal, Delalleau, Olivier, and Marcotte, Patrice · 2005

Earlier work this paper cites.

Fast maximum margin matrix factorization for collaborative prediction

Rennie, Jasson DM and Srebro, Nathan · 2005

Cited alongside, same era.

Computational enhancements in low-rank semidefinite programming

Burer, Samuel and Choi, Changhui · 2006

Cited alongside, same era.

Cryptographic hardness for learning intersections of halfspaces

Sherstov, Adam R Klivansand Alexander A · 2006

Cited alongside, same era.

Introduction to the Theory of Computation

Sipser, Michael · 2006

Cited alongside, same era.

Multi-task feature learning

Argyriou, Andreas, Evgeniou, Theodoros, and Pontil, Massimiliano · 2007

Cited alongside, same era.

ℓ 1 \ell_{1} regularization in infinite dimensional feature spaces

Rosset, Saharon, Swirszcz, Grzegorz, and Srebro, Nathan · 2007

Cited alongside, same era.

Kernel methods for deep learning

Cho, Youngmin and Saul, Lawrence K · 2009

Later among the works it cites.

Collaborative filtering in a non-uniform world: Learning with the weighted trace norm

Srebro, Nathan and Salakhutdinov, Ruslan · 2010

Later among the works it cites.

Breaking the curse of dimensionality with convex neural networks

Bach, Francis · 2014

Closest in time.

From average case complexity to improper learning complexity

Daniely, Amit, Linial, Nati, and Shalev-Shwartz, Shai · 2014

Closest in time.

On the computational efficiency of training neural networks

Livni, Roi, Shalev-Shwartz, Shai, and Shamir, Ohad · 2014

Closest in time.

How to scale up kernel methods to be as good as deep neural nets

Original

Lu, Zhiyun, May, Avner, Liu, Kuan, Garakani, Alireza Bagheri, Guo, Dong, Bellet, AurŽlien, Fan, Linxi, Collins, Michael, Kingsbury, Brian, Picheny, Michael, and Sha, Fei · 2014