Deschide articolul original într-un tab nou Schimbarea acestei opțiuni se aplică imediat și reîncarcă pagina.
LECTURA
Înapoi la articole →

Parameter-free Learning and Optimization Algorithms

parameterfree.com/feed/
Vizitează site-ul

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 10

  1. Multi-scale Expert Algorithm to Tune Learning Rates

    (Parameter-free Learning and Optimization Algorithms)

    This time we consider an application of Online Mirror Descent (OMD) to the problem of prediction with multi-scale expert advice.

  2. From Online Learning to Non-convex Non-smooth Optimization

    (Parameter-free Learning and Optimization Algorithms)

    This is the last post in this series to show that online learning is more than online learning.

  3. From Online Learning to PAC-Bayes

    (Parameter-free Learning and Optimization Algorithms)

    This is the second post in my series of “From Online Learning to X”.

  4. From Online Learning to Rademacher Complexity

    (Parameter-free Learning and Optimization Algorithms)

    This is the first of three posts to show that online learning is more than just online learning!

  5. Better Optimistic Bounds and Delays as Bad Hints

    (Parameter-free Learning and Optimization Algorithms)

    We now consider online learning with delayed feedback.

  6. The Gaptron Algorithm

    (Parameter-free Learning and Optimization Algorithms)

    This time I will describe an online algorithm that is better than the Percetron algorithm.

  7. The Aggregating Algorithm

    (Parameter-free Learning and Optimization Algorithms)

    We continue our journey into algorithms that predicts distributions and this time we talk about the Aggregating Algorithm. 1.

  8. The Weighted Average Algorithm

    (Parameter-free Learning and Optimization Algorithms)

    This time we will introduce the Weighted Average Algorithm (WAA).

  9. Strongly Adaptive Regret and CBCE

    (Parameter-free Learning and Optimization Algorithms)

    In this post, we introduce yet another way to quantify the ability of online learning algorithms to compete with a different comparators, besides the dynamic regret that we saw last time. 1.

  10. Dynamic regret and ADER

    (Parameter-free Learning and Optimization Algorithms)

    In this post, we will see how to extend the notion of regret to a sequence of comparators instead of a single one.