Skip to main content
Ryan Orban

Ryan Orban

Subject
6 entries

Online Learning

Bookmarks

  1. Monolith: Real Time Recommendation System With Collisionless Embedding Table

    Monolith is ByteDance's production recommendation system purpose-built for online training with dynamic sparse features, featuring a collisionless embedding table with expirable embeddings and frequency filtering. It demonstrates that general-purpose ML frameworks like TensorFlow are ill-suited for industrial recommendation with non-stationary data distributions.

  2. Online Skills Are Hot, But Will They Land You a Job?

    A WSJ report on the gap between online skill acquisition (MOOCs, Coursera, Udacity) and actual employment outcomes — asking whether employers recognize and value credentials from online platforms versus traditional degrees. Saved during the peak MOOC-to-employment hype cycle.

  3. Multi-Armed Bandit Experiments

    Analytics blog post on multi-armed bandit experiments as a replacement for static A/B testing in website optimization — covers epsilon-greedy, UCB, and Thompson Sampling with practical framing for product teams.

  4. Sebastian Thrun, Godfather of Free Online Education, Changes Course

    Fast Company's profile of Sebastian Thrun pivoting Udacity away from MOOCs after low completion rates — toward vocational nanodegrees with employer partnerships. A candid acknowledgment that free online university-style education wasn't working as imagined.

  5. Vowpal Wabbit Tutorial for the Uninitiated

    Zinkov's beginner tutorial for Vowpal Wabbit — the fast online learning library from Microsoft Research. Shows the input format, basic invocation, and when VW's out-of-core learning beats batch methods.

  6. An Easy Way to Bridge Between Python and Vowpal Wabbit

    Steve's Machine Learning Blog post on using Python to feed data to Vowpal Wabbit via subprocess — a simple bridge for calling VW from Python workflows without a native binding.

All bookmarks