Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Brukhim, Nataly"'
Autor:
Bressan, Marco, Brukhim, Nataly, Cesa-Bianchi, Nicolò, Esposito, Emmanuel, Mansour, Yishay, Moran, Shay, Thiessen, Maximilian
Cost-sensitive loss functions are crucial in many real-world prediction problems, where different types of errors are penalized differently; for example, in medical diagnosis, a false negative prediction can lead to worse consequences than a false po
Externí odkaz:
http://arxiv.org/abs/2412.08012
We study a generalization of boosting to the multiclass setting. We introduce a weak learning condition for multiclass classification that captures the original notion of weak learnability as being "slightly better than random guessing". We give a si
Externí odkaz:
http://arxiv.org/abs/2307.00642
We study an abstract framework for interactive learning called interactive estimation in which the goal is to estimate a target from its "similarity'' to points queried by the learner. We introduce a combinatorial measure called dissimilarity dimensi
Externí odkaz:
http://arxiv.org/abs/2306.06184
In the framework of online convex optimization, most iterative algorithms require the computation of projections onto convex sets, which can be computationally expensive. To tackle this problem HK12 proposed the study of projection-free methods that
Externí odkaz:
http://arxiv.org/abs/2211.12638
A seminal result in learning theory characterizes the PAC learnability of binary classes through the Vapnik-Chervonenkis dimension. Extending this characterization to the general multiclass setting has been open since the pioneering works on multicla
Externí odkaz:
http://arxiv.org/abs/2203.01550
Reducing reinforcement learning to supervised learning is a well-studied and effective approach that leverages the benefits of compact function approximation to deal with large-scale Markov decision processes. Independently, the boosting methodology
Externí odkaz:
http://arxiv.org/abs/2108.09767
Autor:
Brukhim, Nataly, Hazan, Elad
We consider the problem of online boosting for regression tasks, when only limited information is available to the learner. We give an efficient regret minimization method that has two implications: an online boosting algorithm with noisy multi-point
Externí odkaz:
http://arxiv.org/abs/2007.11975
Boosting is a widely used machine learning approach based on the idea of aggregating weak learning rules. While in statistical learning numerous boosting methods exist both in the realizable and agnostic settings, in online learning they exist only i
Externí odkaz:
http://arxiv.org/abs/2003.01150
We study the question of how to aggregate controllers for dynamical systems in order to improve their performance. To this end, we propose a framework of boosting for online control. Our main result is an efficient boosting algorithm that combines we
Externí odkaz:
http://arxiv.org/abs/1906.08720
We introduce a method for following high-level navigation instructions by mapping directly from images, instructions and pose estimates to continuous low-level velocity commands for real-time control. The Grounded Semantic Mapping Network (GSMN) is a
Externí odkaz:
http://arxiv.org/abs/1806.00047