School of Electrical Engineering and Computer Science, KTH（KTH皇家理工学院电气工程与计算机科学学院）；CyberAgent（CyberAgent公司）；Department of Computer Science and Engineering, POSTECH（浦项科技大学计算机科学与工程系）；Graduate School of AI, KAIST（韩国科学技术院人工智能研究生院）
We study the problem of clustering a set of items from binary user feedback. Such a problem arises in crowdsourcing platforms solving large-scale labeling tasks with minimal effort put on the users. For example, in some of the recent reCAPTCHA systems, users clicks (binary answers) can be used to efficiently label images. In our inference problem, items are grouped into initially unknown non-overlapping clusters. To recover these clusters, the learner sequentially presents to users a finite list of items together with a question with a binary answer selected from a fixed finite set. For each of these items, the user provides a noisy answer whose expectation is determined by the item cluster and the question and by an item-specific parameter characterizing the {\it hardness} of classifying the item. The objective is to devise an algorithm with a minimal cluster recovery error rate. We derive problem-specific information-theoretical lower bounds on the error rate satisfied by any algorithm, for both uniform and adaptive (list, question) selection strategies. For uniform selection, we present a simple algorithm built upon the K-means algorithm and whose performance almost matches the fundamental limits. For adaptive selection, we develop an adaptive algorithm that is inspired by the derivation of the information-theoretical error lower bounds, and in turn allocates the budget in an efficient way. The algorithm learns to select items hard to cluster and relevant questions more often. We compare the performance of our algorithms with or without the adaptive selection strategy numerically and illustrate the gain achieved by being adaptive.
Improving clustering quality evaluation in noisy Gaussian mixtures
School of Computer Science and Electronic Engineering, University of Essex（埃塞克斯大学计算机科学与电子工程学院）；Département d’informatique, Université du Québec à Montréal（魁北克大学蒙特利尔分校计算机科学系）；Mila - Quebec AI Institute（魁北克AI研究院）
A flexible EM-like clustering algorithm for noisy data
Laboratoire des Signaux et Systèmes (L2S)（信号与系统实验室）；CentraleSupélec-CNRS-Université Paris-Sud（巴黎中央理工-高等电力学院-法国国家科学研究中心-巴黎第十一大学）；Université Paris-Saclay（巴黎萨克雷大学）；Instituto de Cálculo（计算研究所）；Universidad de Buenos Aires（布宜诺斯艾利斯大学）；IMAS-CONICET（阿根廷国家科学技术研究委员会数学应用研究所）
虽然EM for GMM算法非常流行，但众所周知，EM for GMM算法具有非高斯分布形状，离群值和高维性。在本文中，我们设计了一个新的强大的聚类算法，可以有效地处理不同的数据集的噪声和离群点。作为一种类EM算法，它同时基于聚类中心和协方差的估计。此外，使用半参数范例，该方法估计每个数据点的未知尺度参数。这使得算法能够适应较重的尾部分布和离群值，而不会在各种经典场景中显着降低效率。我们首先推导和分析所提出的算法的背景下，椭圆分布，特别是重要的不敏感性的基本数据分布。然后，我们研究的收敛性和精度的算法，考虑第一合成数据。然后，我们表明，该算法优于其他经典的无监督方法的文献，如k-均值，EM高斯混合模型及其最近的修改或谱聚类时，应用到真实的数据集MNIST，NORB，和20新闻组。
INRAE（法国国家农业食品与环境研究院）；Institut Agro（法国国家农业、食品与环境学院）；Univ Montpellier（蒙彼利埃大学）；Université Paris-Saclay（巴黎萨克雷大学）；Institut für Mathematik, Universität Potsdam（波茨坦大学数学研究所）
CleanRM: Reward Modeling from Noisy Feedback with a Few Clean Feedback for RLHF
Zhejiang University（浙江大学）；Xiaohongshu Inc（小红书公司）；National University of Singapore（新加坡国立大学）；New York University（纽约大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Institute of Operations Research and Analytics（运营研究与分析研究所）；National University of Singapore（新加坡国立大学）；Thrust of Data Science and Analytics（数据科学与分析中心）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Department of Mathematics（数学系）；Department of Electrical and Computer Engineering（电气与计算机工程系）
