Off the convex path offconvex.org

Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Networks

offconvex.org·200w

Predicting Generalization using GANs

offconvex.org·206w

Does Gradient Flow Over Neural Networks Really Represent Gradient Descent?

offconvex.github.io·228w

Does Gradient Flow Over Neural Networks Really Represent Gradient Descent?

offconvex.org·228w

Implicit Regularization in Tensor Factorization: Can Tensor Rank Shed Light on Generalization in Deep Learning?

offconvex.github.io·254w

Implicit Regularization in Tensor Factorization: Can Tensor Rank Shed Light on Generalization in Deep Learning?

offconvex.org·254w

Rip van Winkle's Razor, a Simple New Estimate for Adaptive Data Analysis

offconvex.github.io·267w

Rip van Winkle's Razor, a Simple New Estimate for Adaptive Data Analysis

offconvex.org·267w

When are Neural Networks more powerful than Neural Tangent Kernels?

offconvex.github.io·269w

When are Neural Networks more powerful than Neural Tangent Kernels?

offconvex.org·269w

Beyond log-concave sampling (Part 3)

offconvex.github.io·270w

Beyond log-concave sampling (Part 3)

offconvex.org·270w

Beyond log-concave sampling (Part 2)

offconvex.github.io·272w

Beyond log-concave sampling (Part 2)

offconvex.org·272w

Can implicit regularization in deep learning be explained by norms?

offconvex.github.io·285w

Can implicit regularization in deep learning be explained by norms?

offconvex.org·285w

How to allow deep learning on your data without revealing the data

offconvex.org·288w

Log in to enable infinite scrolling