(I'm a non native speaker - is it Hopkins' or Hopkins's? --Boaz) Sam Hopkins just completed a heroic 6 part blog post sequence on using the Sum of Squares algorithm for  unsupervised learning. The goal of unsupervised learning is to recover the underlying structure of a distribution $latex \mathcal{D}$ given samples $latex X_1,\ldots,X_n$ sampled from … Continue reading Sam Hopkins’s 6 part learning via SoS series

This is the 6th and final part of a series on clustering, Gaussian mixtures, and Sum of Squares (SoS) proofs. If you have not read them yet, I recommend starting with Part 1, Part 2, Part 3, Part 4, and Part 5. Also, if you find errors please mention them in the comments (or otherwise … Continue reading Clustering and Sum of Squares Proofs, Part 6

This is part 5 of a continuing series on clustering, Gaussian mixtures, and Sum of Squares (SoS) proofs. If you have not read them yet, I recommend starting with Part 1, Part 2, Part 3, and Part 4. Also, if you find errors please mention them in the comments (or otherwise get in touch with … Continue reading Clustering and Sum of Squares Proofs, Part 5

This is part 4 of a continuing series on clustering, Gaussian mixtures, and Sum of Squares (SoS) proofs. If you have not read them yet, I recommend starting with Part 1, Part 2, and Part 3. Also, if you find errors please mention them in the comments (or otherwise get in touch with me) and … Continue reading Clustering and Sum of Squares Proofs, Part 4

This is part 3 of a continuing series on clustering, Gaussian mixtures, and Sum of Squares (SoS) proofs. If you have not read them yet, I recommend starting with Part 1 and Part 2. Also, if you find errors please mention them in the comments (or otherwise get in touch with me) and I will … Continue reading Clustering and Sum of Squares Proofs, Part 3

This is part 2 of a series on clustering, Gaussian mixtures, and Sum of Squares (SoS) proofs. If you have not read it yet, I recommend starting with Part 1. Also, if you find errors please mention them in the comments (or otherwise get in touch with me) and I will fix them ASAP. Welcome … Continue reading Clustering and Sum of Squares Proofs, Part 2

Update (1/5/18): a pdf containing all six posts in this series is now available on my website. I am excited to (temporarily) join the Windows on Theory family as a guest blogger! This is the first post in a series which will appear on Windows on Theory in the coming weeks. The aim is to … Continue reading Clustering and Sum of Squares Proofs, Part 1

(In this post I am following the venerable tradition of bloggers opining about matters on which they don't really know much about. I hope I learn something from the feedback --Boaz). Nothing is impossible, Child, nothing is impossible. Every bridge is crossable. Every tooth is flossable. Every win is lossable. Every worker's bossable. Every cookie's … Continue reading On the (Im)possiblity of intelligence explosion

[Guest post by Robi Krauthgamer;  note that there is no conflict in nominating the same work/person to be highlighted in both HALG and TheoryFest. --Boaz] Call for Nominations  3rd Highlights of Algorithms conference (HALG 2018) Amsterdam, June 4-6, 2018 http://2018.highlightsofalgorithms.org/  The HALG 2018 conference seeks high-quality nominations for invited talks that will highlight recent advances … Continue reading HALG 2018 Call for Nominations

In his State of the Union address in January 1984, president Ronald Reagan announced that he directed his treasury secretary to simplify and reform the U.S., tax code. Thus began a process of 1.5 years until in June 1985, the house Ways and Means committee began formal discussion on the bill, which it voted on … Continue reading The GOP Tax plan and universities