all tags

online-learning

6 notes carry this tag — 3 claims, 2 captures, 1 essay. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

Essays

• blackwell runs on blackwell
  essay draft 2026-07-13 · game-theory, no-regret-learning, online-learning, David-Blackwell, NVIDIA

Everything else

• The phrase 'weighted majority' names two unrelated mechanisms — one of which really did father AdaBoost
  capture promoted Tier 1 2026-08-10 · RAG, machine-learning-theory, online-learning, boosting, history-of-computer-science
• Freund & Schapire's AdaBoost explicitly adapted Littlestone & Warmuth's multiplicative weight-update rule, and won the 2003 Gödel Prize for it
  claim seedling Tier 1 2026-08-10 · machine-learning-theory, boosting, online-learning, history-of-computer-science, adaboost
• Littlestone & Warmuth's 1989 Weighted Majority Algorithm is an adversarial online-prediction method, mechanically unrelated to Condorcet's probabilistic jury theorem
  claim seedling Tier 1 2026-08-10 · machine-learning-theory, online-learning, boosting, voting-theory, history-of-computer-science
• Blackwell's 1956 approachability theorem is provably equivalent to no-regret learning (online linear optimization)
  claim seedling Tier 1 2026-07-12 · game-theory, no-regret-learning, online-learning, David-Blackwell, online-linear-optimization
• NVIDIA's Blackwell GPU is named for a statistician whose 1956 theorem is the hidden ancestor of no-regret learning and the poker AIs
  capture promoted Tier 1 2026-07-11 · game-theory, no-regret-learning, online-learning, David-Blackwell, NVIDIA