paper-with-me

Papers

Maxing and Ranking with Few Assumptions

2017-12-01 · NeurIPS 2017 12 · Moein Falahatgar, Yi Hao, Alon Orlitsky, Venkatadheeraj Pichapati, Vaishakh Ravindrakumar

PAC maximum selection (maxing) and ranking of $n$ elements via random pairwise comparisons have diverse applications and have been studied under many models and assumptions. With just one simple natural assumption: strong stochastic transitivity, we show that maxing can be performed with linearly many comparisons yet ranking requires quadratically many. With no assumptions at all, we show that for the Borda-score metric, maximum selection can be performed with linearly many comparisons and ranking can be performed with $\mathcal{O}(n\log n)$ comparisons.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The Limits of Maxing, Ranking, and Preference Learning

2018-07-01 · ICML 2018 7 · Moein Falahatgar, Ayush Jain, Alon Orlitsky, Venkatadheeraj Pichapati 외

We present a comprehensive understanding of three important problems in PAC preference learning: maximum selection (maxing), ranking, and estimating all pairwise preference probabilities, in the adaptive setting. Wi…

What the F*ck Is Artificial General Intelligence?

2025-03-31 · Michael Timothy Bennett

Artificial general intelligence (AGI) is an established field of research. Yet Melanie Mitchell and others have questioned if the term still has meaning. AGI has been subject to so much hype and speculation it has become…

Proximal Ranking Policy Optimization for Practical Safety in Counterfactual Learning to Rank

2024-09-15 · Shashank Gupta, Harrie Oosterhuis, Maarten de Rijke

Counterfactual learning to rank (CLTR) can be risky and, in various circumstances, can produce sub-optimal models that hurt performance when deployed. Safe CLTR was introduced to mitigate these risks when using inverse p…

counterfactualLearning-To-Rank

The Harness Effect: How Orchestration Design Sets the Token Economics of Enterprise Agentic AI

2026-07-08 · Muayad Sayed Ali, Aliaksandra Novik, Anji Boddupally, Artem Yavorskyi 외 arxiv

Agentic AI development today runs on token maxing: buying capability with tokens -- longer reasoning traces, more turns, wider tool payloads, bigger replayed contexts -- so tokens per task grow faster than task value. Fa…

Judging LLMs on a Simplex

2025-05-28 · Patrick Vossler, Fan Xia, Yifan Mai, Jean Feng

Automated evaluation of free-form outputs from large language models (LLMs) is challenging because many distinct answers can be equally valid. A common practice is to use LLMs themselves as judges, but the theoretical pr…

Bayesian InferenceUncertainty Quantification