Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Camilleri, Romain"'
In critical machine learning applications, ensuring fairness is essential to avoid perpetuating social inequities. In this work, we address the challenges of reducing bias and improving accuracy in data-scarce environments, where the cost of collecti
Externí odkaz:
http://arxiv.org/abs/2312.08559
We investigate the fixed-budget best-arm identification (BAI) problem for linear bandits in a potentially non-stationary environment. Given a finite arm set $\mathcal{X}\subset\mathbb{R}^d$, a fixed budget $T$, and an unpredictable sequence of parame
Externí odkaz:
http://arxiv.org/abs/2307.15154
Active learning methods have shown great promise in reducing the number of samples necessary for learning. As automated learning systems are adopted into real-time, real-world decision-making pipelines, it is increasingly important that such algorith
Externí odkaz:
http://arxiv.org/abs/2206.11183
Autor:
Mason, Blake, Camilleri, Romain, Mukherjee, Subhojyoti, Jamieson, Kevin, Nowak, Robert, Jain, Lalit
The level set estimation problem seeks to find all points in a domain ${\cal X}$ where the value of an unknown function $f:{\cal X}\rightarrow \mathbb{R}$ exceeds a threshold $\alpha$. The estimation is based on noisy function evaluations that may be
Externí odkaz:
http://arxiv.org/abs/2111.01768
This work considers the problem of selective-sampling for best-arm identification. Given a set of potential options $\mathcal{Z}\subset\mathbb{R}^d$, a learner aims to compute with probability greater than $1-\delta$, $\arg\max_{z\in \mathcal{Z}} z^{
Externí odkaz:
http://arxiv.org/abs/2110.14864
In recent years methods from optimal linear experimental design have been leveraged to obtain state of the art results for linear bandits. A design returned from an objective such as $G$-optimal design is actually a probability distribution over a po
Externí odkaz:
http://arxiv.org/abs/2105.05806