English
Related papers

Related papers: Preference-based Teaching

200 papers

This paper studies human preference learning based on partially revealed choice behavior and formulates the problem as a generalized Bradley-Terry-Luce (BTL) ranking model that accounts for heterogeneous preferences. Specifically, we assume…

Methodology · Statistics 2025-09-03 Jianqing Fan , Hyukjun Kwon , Xiaonan Zhu

We consider learning problems of an intuitive and concise preference model, called lexicographic preference lists (LP-lists). Given a set of examples that are pairwise ordinal preferences over a universe of objects built of attributes of…

Artificial Intelligence · Computer Science 2019-09-20 Ahmed Moussa , Xudong Liu

Intransitivity is a critical issue in pairwise preference modeling. It refers to the intransitive pairwise preferences between a group of players or objects that potentially form a cyclic preference chain and has been long discussed in…

Machine Learning · Computer Science 2024-10-01 Jiuding Duan , Jiyi Li , Yukino Baba , Hisashi Kashima

Human-in-the-loop reinforcement learning allows the training of agents through various interfaces, even for non-expert humans. Recently, preference-based methods (PbRL), where the human has to give his preference over two trajectories,…

Artificial Intelligence · Computer Science 2024-08-06 Jakob Karalus

We propose a class of semimetrics for preference relations any one of which is an alternative to the classical Kemeny-Snell-Bogart metric. (We take a fairly general viewpoint about what constitutes a preference relation, allowing for any…

Combinatorics · Mathematics 2022-03-10 Hiroki Nishimura , Efe A. Ok

Recently, enhancing the numerical and logical reasoning capability of Large Language Models (LLMs) has emerged as a research hotspot. Existing methods face several limitations: inference-phase techniques (e.g., Chain of Thoughts) rely on…

Artificial Intelligence · Computer Science 2025-02-20 Hao Yi , Qingyang Li , Yulan Hu , Fuzheng Zhang , Di Zhang , Yong Liu

We initiate the study of differentially private learning in the proportional dimensionality regime, in which the number of data samples $n$ and problem dimension $d$ approach infinity at rates proportional to one another, meaning that…

Machine Learning · Computer Science 2025-02-20 Cynthia Dwork , Pranay Tankala , Linjun Zhang

Patterns provide a concise, syntactic way of describing a set of strings, but their expressive power comes at a price: a number of fundamental decision problems concerning (erasing) pattern languages, such as the membership problem and…

Formal Languages and Automata Theory · Computer Science 2019-05-21 Ziyuan Gao

Decision-making problems often feature uncertainty stemming from heterogeneous and context-dependent human preferences. To address this, we propose a sequential learning-and-optimization pipeline to learn preference distributions and…

Machine Learning · Computer Science 2026-03-19 Benjamin Hudson , Laurent Charlin , Emma Frejinger

Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories, rather than explicit reward signals. While PbRL has demonstrated…

Machine Learning · Computer Science 2024-04-18 Wenhao Zhan , Masatoshi Uehara , Wen Sun , Jason D. Lee

Modeling human preferences is crucial for aligning foundation models with human values. Traditional reward modeling methods, such as the Bradley-Terry (BT) reward model, fall short in expressiveness, particularly in addressing intransitive…

Artificial Intelligence · Computer Science 2025-06-12 Yifan Zhang , Ge Zhang , Yue Wu , Kangping Xu , Quanquan Gu

Mathematical psychology has a long tradition of modeling probabilistic choice via distribution-free random utility models and associated random preference models. For such models, the predicted choice probabilities often form a bounded and…

Optimization and Control · Mathematics 2017-10-10 Clintin P. Davis-Stober , Jean-Paul Doignon , Samuel Fiorini , François Glineur , Michel Regenwetter

Preference-based many-objective optimization faces two obstacles: an expanding space of trade-offs and heterogeneous, context-dependent human value structures. Towards this, we propose a Bayesian framework that learns a small set of latent…

Machine Learning · Computer Science 2026-03-31 Manisha Dubey , Sebastiaan De Peuter , Wanrong Wang , Samuel Kaski

Reinforcement learning is a general method for learning in sequential settings, but it can often be difficult to specify a good reward function when the task is complex. In these cases, preference feedback or expert demonstrations can be…

Machine Learning · Computer Science 2025-08-20 Jason R Brown , Carl Henrik Ek , Robert D Mullins

Prompt-tuning has emerged as a promising method for adapting pre-trained models to downstream tasks or aligning with human preferences. Prompt learning is widely used in NLP but has limited applicability to RL due to the complex physical…

Machine Learning · Computer Science 2023-05-17 Shengchao Hu , Li Shen , Ya Zhang , Dacheng Tao

Transductive learning is a supervised machine learning task in which, unlike in traditional inductive learning, the unlabelled data that require labelling are a finite set and are available at training time. Similarly to inductive learning…

Machine Learning · Computer Science 2025-07-31 Lorenzo Volpi , Alejandro Moreo , Fabrizio Sebastiani

If you tell a learning model that you prefer an alternative $a$ over another alternative $b$, then you probably expect the model to be monotone, that is, the valuation of $a$ increases, and that of $b$ decreases. Yet, perhaps surprisingly,…

Statistics Theory · Mathematics 2025-10-23 Julien Fageot , Peva Blanchard , Gilles Bareilles , Lê-Nguyên Hoang

This paper explores a new class of incomplete preferences -- termed ``connected preferences'' -- in which maximal domains of comparability are topologically connected. We provide necessary and sufficient conditions for continuous…

Theoretical Economics · Economics 2026-05-01 Leandro Gorno , Alessandro Rivello

Hierarchical methods in reinforcement learning have the potential to reduce the amount of decisions that the agent needs to perform when learning new tasks. However, finding reusable useful temporal abstractions that facilitate fast…

Machine Learning · Computer Science 2023-04-05 David Kuric , Herke van Hoof

Ranking or assessing centrality in multivariate and non-Euclidean data is difficult because there is no canonical order and many depth notions become computationally fragile in high-dimensional or structured settings. We introduce a…

Methodology · Statistics 2026-02-24 Lingfeng Lyu , Doudou Zhou