TopRank+: A Refinement of TopRank Algorithm

01/21/2020
by   Victor de la Pena, et al.
0

Online learning to rank is a core problem in machine learning. In Lattimore et al. (2018), a novel online learning algorithm was proposed based on topological sorting. In the paper they provided a set of self-normalized inequalities (a) in the algorithm as a criterion in iterations and (b) to provide an upper bound for cumulative regret, which is a measure of algorithm performance. In this work, we utilized method of mixtures and asymptotic expansions of certain implicit function to provide a tighter, iterated-log-like boundary for the inequalities, and as a consequence improve both the algorithm itself as well as its performance estimation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/07/2017

Online Learning to Rank in Stochastic Click Models

Online learning to rank is a core problem in information retrieval and m...
research
03/20/2018

Online Learning: Sufficient Statistics and the Burkholder Method

We uncover a fairly general principle in online learning: If regret can ...
research
09/05/2019

√(n)-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank

In this paper, we consider the problem of online learning of Markov deci...
research
10/26/2018

Accumulating Knowledge for Lifelong Online Learning

Lifelong learning can be viewed as a continuous transfer learning proced...
research
08/15/2023

Simple online learning with consistency oracle

We consider online learning in the model where a learning algorithm can ...
research
02/12/2018

PRIL: Perceptron Ranking Using Interval Labeled Data

In this paper, we propose an online learning algorithm PRIL for learning...
research
06/30/2021

Koopman Spectrum Nonlinear Regulator and Provably Efficient Online Learning

Most modern reinforcement learning algorithms optimize a cumulative sing...

Please sign up or login with your details

Forgot password? Click here to reset