Search Results for author: Robert Busa-Fekete

Found 7 papers, 1 papers with code

On the computational complexity of the probabilistic label tree algorithms

no code implementations1 Jun 2019 Robert Busa-Fekete, Krzysztof Dembczynski, Alexander Golovnev, Kalina Jasinska, Mikhail Kuznetsov, Maxim Sviridenko, Chao Xu

First, we show that finding a tree with optimal training cost is NP-complete, nevertheless there are some tractable special cases with either perfect approximation or exact solution that can be obtained in linear time in terms of the number of labels $m$.

Multi-class Classification

Learning to Crawl

no code implementations29 May 2019 Utkarsh Upadhyay, Robert Busa-Fekete, Wojciech Kotlowski, David Pal, Balazs Szorenyi

Web crawling is the problem of keeping a cache of webpages fresh, i. e., having the most recent copy available when a page is requested.

Preference-based Online Learning with Dueling Bandits: A Survey

no code implementations30 Jul 2018 Viktor Bengs, Robert Busa-Fekete, Adil El Mesaoudi-Paul, Eyke Hüllermeier

The aim of this paper is to provide a survey of the state of the art in this field, referred to as preference-based multi-armed bandits or dueling bandits.

Multi-Armed Bandits Survey

Ranking Distributions based on Noisy Sorting

no code implementations ICML 2018 Adil El Mesaoudi-Paul, Eyke Hüllermeier, Robert Busa-Fekete

We also introduce a generalization of the model, in which the constraints on pairwise preferences are relaxed, and for which maximum likelihood estimation can be carried out based on a variation of the generalized iterative scaling algorithm.

Distributed Stochastic Optimization via Adaptive SGD

no code implementations NeurIPS 2018 Ashok Cutkosky, Robert Busa-Fekete

Scaling up the training process of these models is crucial, but the most popular algorithm, Stochastic Gradient Descent (SGD), is a serial method that is surprisingly hard to parallelize.

Stochastic Optimization

Multi-objective Bandits: Optimizing the Generalized Gini Index

no code implementations ICML 2017 Robert Busa-Fekete, Balazs Szorenyi, Paul Weng, Shie Mannor

We study the multi-armed bandit (MAB) problem where the agent receives a vectorial feedback that encodes many possibly competing objectives to be optimized.

Cannot find the paper you are looking for? You can Submit a new open access paper.