Everything you care about in one place

Follow feeds: blogs, news, RSS and more. An effortless way to read and digest content of your choice.

Get Feeder

offconvex.org

Off the convex path

Get the latest updates from Off the convex path directly as they happen.

Follow now 217 followers

Latest posts

Last updated 3 months ago

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

3 months ago

In effort to understand implicit regularization in deep learning, a lot of...

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

6 months ago

Can you trust a model whose designer had access to the test/holdout...

When are Neural Networks more powerful than Neural Tangent Kernels?

6 months ago

The empirical success of deep learning has posed significant challenges to machine...

Beyond log-concave sampling (Part 3)

7 months ago

In the first post of this series, we introduced the challenges of...

Beyond log-concave sampling (Part 2)

7 months ago

In our previous blog post, we introduced the challenges of sampling distributions...

Can implicit regularization in deep learning be explained by norms?

10 months ago

This post is based on my recent paper with Noam Razin (to...

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

11 months ago

Today’s online world and the emerging internet of things is built around...

Mismatches between Traditional Optimization Analyses and Modern Deep Learning

11 months ago

You may remember our previous blog post showing that it is possible...

Beyond log-concave sampling

about 1 year ago

layout: post title: Beyond log-concave sampling date: 2020-09-18 14:00:00 summary: Beyond log-concave...

Training GANs - From Theory to Practice

about 1 year ago

GANs, originally discovered in the context of unsupervised learning, have had far...

An equilibrium in nonconvex-nonconcave min-max optimization

over 1 year ago

While there has been incredible progress in convex and nonconvex minimization, a...

Exponential Learning Rate Schedules for Deep Learning (Part 1)

over 1 year ago

This blog post concerns our ICLR20 paper on a surprising discovery about...