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


Off the convex path

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

Follow now 184 followers

Latest posts

Last updated 1 day ago

Beyond log-concave sampling

3 days 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

3 months ago

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

An equilibrium in nonconvex-nonconcave min-max optimization

3 months ago

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

Exponential Learning Rate Schedules for Deep Learning (Part 1)

5 months ago

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

Ultra-Wide Deep Nets and Neural Tangent Kernel (NTK)

12 months ago

(Crossposted at CMU ML.) Traditional wisdom in machine learning holds that there...

Understanding implicit regularization in deep learning by analyzing trajectories of gradient descent

about 1 year ago

Sanjeev’s recent blog post suggested that the conventional view of optimization is...

Landscape Connectivity of Low Cost Solutions for Multilayer Nets

over 1 year ago

A big mystery about deep learning is how, in a highly nonconvex...

Is Optimization a Sufficient Language for Understanding Deep Learning?

over 1 year ago

In this Deep Learning era, machine learning usually boils down to defining...

Contrastive Unsupervised Learning of Semantic Representations: A Theoretical Framework

over 1 year ago

Semantic representations (aka semantic embeddings) of complicated data types (e.g. images, text...

The search for biologically plausible neural computation: A similarity-based approach

almost 2 years ago

This is the second post in a series reviewing recent progress in...

Understanding optimization in deep learning by analyzing trajectories of gradient descent

almost 2 years ago

Neural network optimization is fundamentally non-convex, and yet simple gradient-based algorithms seem...

Simple and efficient semantic embeddings for rare words, n-grams, and language features

about 2 years ago

Distributional methods for capturing meaning, such as word embeddings, often require observing...