TACC algorithm for adaptive multi-fidelity bandits with improving proxies achieves instance-dependent regret by replacing logarithmic high-fidelity pulls with bounded low-fidelity continuation for intermediate arms.
Put cash on bandits: A max k-armed problem for automated machine learning.arXiv preprint arXiv:2505.05226
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
PS-PFN extends posterior sampling to the max k-armed bandit setup using PFNs for in-context posterior estimation of maximal pipeline performance, outperforming other bandit and AutoML strategies on benchmarks.
citing papers explorer
-
Beyond Static Bias: Adaptive Multi-Fidelity Bandits with Improving Proxies
TACC algorithm for adaptive multi-fidelity bandits with improving proxies achieves instance-dependent regret by replacing logarithmic high-fidelity pulls with bounded low-fidelity continuation for intermediate arms.
-
In-Context Decision Making for Optimizing Complex AutoML Pipelines
PS-PFN extends posterior sampling to the max k-armed bandit setup using PFNs for in-context posterior estimation of maximal pipeline performance, outperforming other bandit and AutoML strategies on benchmarks.