Explore >> Select a destination

You are here

 francisbach.com
Rethinking SGD's noise - Machine Learning Research Blog
| | fa.bianp.net
On the Convergence of the Unadjusted Langevin Algorithm
2.8 parsecs away

Travel
| | The Langevin algorithm is a simple and powerful method to sample from a probability distribution. It's a key ingredient of some machine learning methods such as diffusion models and differentially private learning. In this post, I'll derive a simple convergence analysis of this method in the special case when the ...
| | bdtechtalks.com
A simple guide to gradient descent in machine learning - TechTalks
3.3 parsecs away

Travel
| | Gradient descent is the main technique for training machine learning and deep learning models. Read all about it.
| | windowsontheory.org
A blitz through classical statistical learning theory - Windows On Theory
3.3 parsecs away

Travel
| | Previous post: ML theory with bad drawings Next post: What do neural networks learn and when do they learn it, see also all seminar posts and course webpage. Lecture video (starts in slide 2 since I hit record button 30 seconds too late - sorry!) - slides (pdf) - slides (Powerpoint with ink and animation)...
| | fa.bianp.net
On the Link Between Polynomials and Optimization, Part 1
23.6 parsecs away

Travel
| There's a fascinating link between minimization of quadratic functions and polynomials. A link that goes deep and allows to phrase optimization problems in the language of polynomials and vice versa. Using this connection, we can tap into centuries of research in the theory of polynomials and shed new light on ...