Mode Estimation with Partial Feedback
Not on the map. Why?
Abstract (arXiv)
The combination of lightly supervised pre-training and online fine-tuning has played a key role in recent AI developments. These new learning pipelines call for new theoretical frameworks. In this paper, we formalize core aspects of weakly supervised and active learning with a simple problem: the estimation of the mode of a distribution using partial feedback. We show how entropy coding allows for optimal information acquisition from partial feedback, develop coarse sufficient statistics for mode identification, and adapt bandit algorithms to our new setting. Finally, we combine those contributions into a statistically and computationally efficient solution to our problem.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 8 of its 33 references that are in the map. First posted on arXiv 20 Feb 2024.
Builds on
8 of 33 references.
References · 8
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
- 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
- 2023Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisonscited by 247
- 2019Sequential Experimental Design for Transductive Linear Banditscited by 91
- 2014Combinatorial Multi-Armed Bandit and Its Extension to Probabilistically Triggered Armscited by 79
- 2018Dynamic Pricing with Finitely Many Unknown Valuationscited by 23
- 2019Sorted Top-k in Roundscited by 4
- 2022Active Labeling: Streaming Stochastic Gradientscited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.
- 2026Sequence prediction under a lying oraclecited by 0
- 2026Sequence prediction under a lying oracle14 Aug 2026