Publications

Open Problems in Machine Unlearning for AI Safety
Fazl Barez
Tingchen Fu
Ameya Prabhu
Stephen Casper
Amartya Sanyal
Adel Bibi
Aidan O'Gara
Robert Kirk
Benjamin Bucknall
Timothy Fist
Luke Ong
Philip Torr
Kwok-Yan Lam
Robert Trager
David M. Krueger
Sören Mindermann
Jose Hernandez-Orallo
Mor Geva
Yarin Gal
As AI systems become more capable, widely deployed, and increasingly autonomous in critical areas such as cybersecurity, biological research… (voir plus), and healthcare, ensuring their safety and alignment with human values is paramount. Machine unlearning -- the ability to selectively forget or suppress specific types of knowledge -- has shown promise for privacy and data removal tasks, which has been the primary focus of existing research. More recently, its potential application to AI safety has gained attention. In this paper, we identify key limitations that prevent unlearning from serving as a comprehensive solution for AI safety, particularly in managing dual-use knowledge in sensitive domains like cybersecurity and chemical, biological, radiological, and nuclear (CBRN) safety. In these contexts, information can be both beneficial and harmful, and models may combine seemingly harmless information for harmful purposes -- unlearning this information could strongly affect beneficial uses. We provide an overview of inherent constraints and open problems, including the broader side effects of unlearning dangerous knowledge, as well as previously unexplored tensions between unlearning and existing safety mechanisms. Finally, we investigate challenges related to evaluation, robustness, and the preservation of safety features during unlearning. By mapping these limitations and open challenges, we aim to guide future research toward realistic applications of unlearning within a broader AI safety framework, acknowledging its limitations and highlighting areas where alternative approaches may be required.
2025-01-08
ArXiv (prépublication)
doi.org
arxiv.org
Soup to go: mitigating forgetting during continual learning with model averaging
Anat Kleiman
Gintare Karolina Dziugaite
Jonathan Frankle
Sham M. Kakade
Mansheej Paul
In continual learning, where task data arrives in a sequence, fine-tuning on later tasks will often lead to performance degradation on earli… (voir plus)er tasks. This is especially pronounced when these tasks come from diverse domains. In this setting, how can we mitigate catastrophic forgetting of earlier tasks and retain what the model has learned with minimal computational expenses? Inspired by other merging methods, and L2-regression, we propose Sequential Fine-tuning with Averaging (SFA), a method that merges currently training models with earlier checkpoints during the course of training. SOTA approaches typically maintain a data buffer of past tasks or impose a penalty at each gradient step. In contrast, our method achieves comparable results without the need to store past data, or multiple copies of parameters for each gradient step. Furthermore, our method outperforms common merging techniques such as Task Arithmetic, TIES Merging, and WiSE-FT, as well as other penalty methods like L2 and Elastic Weight Consolidation. In turn, our method offers insight into the benefits of merging partially-trained models during training across both image and language domains.
2025-01-08
ArXiv (prépublication)
doi.org
openreview.net
Adaptive Experiments Under Data Sparse Settings: Applications for Educational Platforms
Haochen Song
Ilya Musabirov
Ananya Bhattacharjee
Audrey Durand
Meredith Franklin
Anna Rafferty
Joseph Jay Williams
Adaptive experimentation is increasingly used in educational platforms to personalize learning through dynamic content and feedback. However… (voir plus), standard adaptive strategies such as Thompson Sampling often underperform in real-world educational settings where content variations are numerous and student participation is limited, resulting in sparse data. In particular, Thompson Sampling can lead to imbalanced content allocation and delayed convergence on which aspects of content are most effective for student learning. To address these challenges, we introduce Weighted Allocation Probability Adjusted Thompson Sampling (WAPTS), an algorithm that refines the sampling strategy to improve content-related decision-making in data-sparse environments. WAPTS is guided by the principle of lenient regret, allowing near-optimal allocations to accelerate learning while still exploring promising content. We evaluate WAPTS in a learnersourcing scenario where students rate peer-generated learning materials, and demonstrate that it enables earlier and more reliable identification of promising treatments.
2025-01-06
ArXiv (prépublication)
arxiv.org
arxiv.org
L’appréhension empirique du leadership normatif d’une organisation internationale : l’exemple de l’Organisation mondiale de la Santé
Catherine Régis
Gaëlle Foucault
Pierre Larouche
Jean-Louis Denis
Miriam Cohen
En plein essor, la recherche empirique en droit participe à la création de nouvelles connaissances et ouvre aux juristes d’autres voies … (voir plus)pour étudier une question, un phénomène. Oser l’empirisme n’est pas chose aisée, mais les auteurs du présent article ont pris ce virage et proposent d’en exposer le récit. En construisant deux méthodes distinctes (pour deux projets), ils ont pu tester les possibilités qu’offre la recherche empirique pour appréhender l’enjeu du leadership normatif de l’Organisation mondiale de la Santé (OMS). Destiné à aiguiller à partir d’une expérience celles et ceux qui voudraient s’aventurer dans l’empirisme, cet article met en lumière les défis rencontrés, mais surtout les atouts d’une telle recherche. La richesse des informations obtenues a en effet grandement bonifié la compréhension de la trajectoire des normes de l’OMS et de leurs impacts sur les États.
2025-01-06
Lex Electronica (publié)
doi.org
The empirical apprehension of the normative leadership of an international organization: The example of the World Health Organization
Catherine Régis
Gaëlle Foucault
Pierre Larouche
Jean-Louis Denis
Miriam Cohen
2025-01-06
Lex Electronica (publié)
doi.org
A video-based approach to decipher intubation decisions for the critically ill
Guillaume Dumas
Jean-Rémi Lavillegrand
Elie Azoulay
2025-01-06
Intensive Care Medicine (publié)
doi.org
IRIS: A Bayesian Approach for Image Reconstruction in Radio Interferometry with expressive Score-Based priors
No'e Dia
M. J. Yantovski-Barth
Alexandre Adam
Micah Bowles
Laurence Perreault-Levasseur
Yashar Hezaveh
Anna M. M. Scaife
Inferring sky surface brightness distributions from noisy interferometric data in a principled statistical framework has been a key challeng… (voir plus)e in radio astronomy. In this work, we introduce Imaging for Radio Interferometry with Score-based models (IRIS). We use score-based models trained on optical images of galaxies as an expressive prior in combination with a Gaussian likelihood in the uv-space to infer images of protoplanetary disks from visibility data of the DSHARP survey conducted by ALMA. We demonstrate the advantages of this framework compared with traditional radio interferometry imaging algorithms, showing that it produces plausible posterior samples despite the use of a misspecified galaxy prior. Through coverage testing on simulations, we empirically evaluate the accuracy of this approach to generate calibrated posterior samples.
2025-01-04
ArXiv (prépublication)
doi.org
arxiv.org
JUNO sensitivity to invisible decay modes of neutrons
Juno Collaboration Angel Abusleme
Angel Abusleme
Thomas Adam
Kai Adamowicz
Shakeel Ahmad
Rizwan Ahmed
Sebastiano Aiello
Fengpeng An
Qi An
Giuseppe Andronico
Nikolay Anfimov
Vito Antonelli
Tatiana Antoshkina
João Pedro Athayde Marcondes de André
Didier Auguste
Weidong Bai
Nikita Balashov
Wander Baldini
Andrea Barresi
Davide Basilico … (voir 648 de plus)
Eric Baussan
Marco Bellato
Marco Beretta
Antonio Bergnoli
Daniel Bick
Lukas Bieger
Svetlana Biktemerova
Thilo Birkenfeld
Iwan Blake
Simon Blyth
Anastasia Bolshakova
Mathieu Bongrand
Dominique Breton
Augusto Brigatti
Riccardo Brugnera
Riccardo Bruno
Antonio Budano
Jose Busto
Anatael Cabrera
Barbara Caccianiga
Hao Cai
Xiao Cai
Yanke Cai
Zucong Cai
Zhiyan Cai
Stéphane Callier
Steven Calvez
Antonio Cammi
Agustin Campeny
Chuanya Cao
Guofu Cao
Jun Cao
Rossella Caruso
Cédric Cerna
Vanessa Cerrone
Jinfan Chang
Yun Chang
Auttakit Chatrabhuti
Chao Chen
Guoming Chen
Pingping Chen
Shaomin Chen
Xin Chen
Yiming Chen
Yixue Chen
Yu Chen
Zelin Chen
Zhangming Chen
Zhiyuan Chen
Zikang Chen
Jie Cheng
Yaping Cheng
Yu Chin Cheng
Yuanyuan Zhang
Alexander Chepurnov
Alexey Chetverikov
Davide Chiesa
Pietro Chimenti
Yen-Ting Chin
Po-Lin Chou
Ziliang Chu
Artem Chukanov
Gérard Claverie
Catia Clementi
Barbara Clerbaux
Marta Colomer Molla
Selma Conforti Di Lorenzo
Alberto Coppi
Daniele Corti
Simon Csakli
Chenyang Cui
Flavio Dal Corso
Olivia Dalager
Jaydeep Datta
Christophe De La Taille
C. Taille
Zhi Deng
Ziyan Deng
Xiaoyu Ding
Xuefeng Ding
Yayun Ding
Bayu Dirgantara
Carsten Dittrich
Sergey Dmitrievsky
Tadeas Dohnal
Dmitry Dolzhikov
Georgy Donchenko
Jianmeng Dong
Evgeny Doroshkevich
Wei Dou
Marcos Dracos
Frédéric Druillole
Ran Du
S. X. Du
Yujie Duan
Katherine Dugas
Stefano Dusini
Hongyue Duyang
Jessica Eck
Timo Enqvist
Andrea Fabbri
Ulrike Fahrendholz
Lei Fan
Jian Fang
W. X. Fang
Dmitry Fedoseev
Haiping Peng
Li-Cheng Feng
Qichun Feng
Federico Ferraro
Amélie Fournier
Fritsch Fritsch
Haonan Gan
Feng Gao
Alberto Garfagnini
Arsenii Gavrikov
Marco Giammarchi
Nunzio Giudice
Maxim Gonchar
G. Gong
Hui Gong
Guanghua Gong
Yuri Gornushkin
Marco Grassi
Maxim Gromov
Vasily Gromov
Minghao Gu
Xiang Zhou
Xiaofei Gu
Yunting Gu
Mengyun Guan
Yu Gu
Yuduo Guan
Nunzio Guardone
Rosa Maria Guizzetti
Cong Guo
Wanlei Guo
Caren Hagner
Hechong Han
Ran Han
Yang Han
Jinhong He
Miao He
Wei He
Xinhai He
Tobias Heinz
Patrick Hellmuth
Rafael Herrera
Yuenkeung Hor
Shaojing Hou
Yee Hsiung
Bei-Zhen Hu
Hang Hu
Jun Hu
Peng Hu
Shouyang Hu
T. Hu
Yuxiang Hu
Zhuojun Hu
Guihong Huang
Hanxiong Huang
Jinhao Huang
Jun-Hao Huang
Xin Huang
Kaixuan Huang
Shengheng Huang
Wenhao Huang
X. T. Huang
Yongbo Huang
Jiaqi Hui
Lei Huo
Wenju Huo
Cédric Huss
Safeer Hussain
Leonard Imbert
Ara Ioannisian
Roberto Isocrate
Arshak Jafar
Beatrice Jelmini
Ignacio Jeria
Xiaolu Ji
Huihui Jia
Junji Jia
Siyu Jian
Cailian Jiang
Di Jiang
Guangzheng Jiang
Wei Jiang
Xiaoshan Jiang
Xiaozhao Jiang
Yixuan Jiang
Xiang Jing
Cécile Jollet
Li Kang
Rebin Karaparabil
Narine Kazarian
Ali Khan
Amina Khatun
Khanchai Khosonthongkee
Denis Korablev
Konstantin Kouzakov
Alexey Krasnoperov
Sergey Kuleshov
Sindhujha Kumaran
Nikolay Kutovskiy
Loïc Labit
Tobias Lachenmaier
Haojing Lai
Cecilia Landini
Sébastien Leblanc
Frederic Lefevre
Rupert Leitner
Jason Leung
Demin Li
Yi Wang
Fule Li
Fei Li
Gaosong Li
Hongjian Li
Huang Li
Jiajun Li
Min Li
Nan Li
Qingjiang Li
Ruhui Li
Rui Li
Shanfeng Li
Shuo Li
Tao Li
Teng Li
Weidong Li
Weiguo Li
Xiaomei Li
Xiao-Nan Li
Xinglong Li
Yi Li
Yichen Li
Yufeng Li
Zhaohan Li
Zhibing Li
Ziyuan Li
Zonghai Li
An-An Liang
Hao Liang
Jiaming Yan
Yilin Liao
Jiajun Liao
Y. P. Liao
Ayut Limphirat
Guey-Lin Lin
Yuzhong Liao
Shengxin Lin
Tao Lin
Jiajie Ling
Xin Ling
Ivano Lippi
Caimei Liu
Yang Liu
Fengcheng Liu
Haidong Liu
Haotian Liu
Hongbang Liu
Hongjuan Liu
Hongtao Liu
Hongyang Liu
Jianglai Liu
Jiaxi Liu
Jinchang Liu
Min Liu
Qian Liu
Qin Liu
Runxuan Liu
Sheng Liu
Shubin Liu
Shulin Liu
Xiaowei Liu
Xiwen Liu
Xuewei Liu
Yankai Liu
Zhen Liu
Lorenzo Loi
Alexey Lokhov
Paolo Lombardi
Claudio Lombardo
Kai Loo
Chuan Lu
Haoqi Lu
Jingbin Lu
Junguang Lu
Meishu Lu
Peizhi Lu
Shuxian Du
Xianguo Lu
Bayarto Lubsandorzhiev
Sultim Lubsandorzhiev
Livia Ludhova
Arslan Lukanov
Feng Luo
Guang Luo
Fengjiao Luo
Jianyi Luo
Shu Luo
Wuming Luo
Xiaojie Luo
Vladimir Lyashuk
Biao Ma
Bing Ma
Qiumei Ma
Bangzheng Ma
Si Ma
Xiaoyan Ma
Xubo Ma
Jihane Maalmi
Jingyu Mai
Marco Malabarba
Yury Malyshkin
Roberto Carlos Mandujano
Fabio Mantovani
Xin Mao
Yajun Mao
S. Mari
Filippo Marini
Stefano M. Mari
Agnese Martini
Matthias Mayer
Davit Mayilyan
Ints Mednieks
Yu Meng
Anita Meraviglia
Anselmo Meregaglia
Emanuela Meroni
Lino Miramonti
Nikhil Mohan
Michele Montuschi
Cristobal Morales Reveco
Massimiliano Nastasi
Dmitry V. Naumov
Elena Naumova
Diana Navas-Nicolas
Igor Nemchenok
Minh Thuan Nguyen Thi
Alexey Nikolaev
Feipeng Ning
Zhe Ning
Hiroshi Nunokawa
Lothar Oberauer
Juan Pedro Ochoa-Ricoux
Alexander Olshevskiy
Domizia Orestano
Fausto Ortica
Rainer Othegraven
Alessandro Paoloni
George Parker
Sergio Parmeggiano
Achilleas Patsias
Y. P. Pei
Luca Pelicci
Yatian Pei
Anguo Peng
Zhaoyuan Peng
Elisa Percalli
Willy Perrin
Frédéric Perrot
P. Petitjean
Fabrizio Petrucci
Pierre-Alexandre Petitjean
Oliver Pilarczyk
Luis Felipe Piñeres Rico
Artyom Popov
Pascal Poussot
Ezio Previtali
Fazhi Qi
M. Qi
Xiaohui Qi
Sen Qian
Xiangyang Qian
Zhen Qian
Hao Qiao
Xiaohui Qian
Zhonghua Qin
Shoukang Qiu
Manhao Qu
Z. Qu
Gioacchino Ranucci
A. Re
Zhenning Qu
Abdel Rebii
Mariia Redchuk
Alessandra Re
Gioele Reina
Bin Ren
Jie Ren
Yuhan Ren
Barbara Ricci
Komkrit Rientong
Mariam Rifai
Mathieu Roche
Narongkiat Rodphai
Aldo Romani
Bedřich Roskovec
Xichao Ruan
Arseniy Rybnikov
Andrey Sadovsky
Paolo Saggese
Deshan Sandanayake
Anut Sangka
Giuseppe Sava
Utane Sawangwit
Michaela Schever
Cédric Schwab
Konstantin Schweizer
Alexandr Selyunin
Andrea Serafini
Mariangela Settimo
Junyu Shao
Vladislav Sharov
Hexi Shi
Jingyan Shi
Yanan Shi
Vitaly Shutov
Andrey Sidorenkov
Fedor Šimkovic
Apeksha Singhal
Chiara Sirignano
Jaruchit Siripak
Monica Sisti
Mikhail Smirnov
Oleg Smirnov
Sergey Sokolov
Julanan Songwadhana
Boonrucksar Soonthornthum
Albert Sotnikov
Warintorn Sreethawong
Achim Stahl
Luca Stanco
Konstantin Stankevich
Hans Steiger
Jochen Steinmann
Tobias Sterr
M. Stock
Virginia Strati
Matthias Raphael Stock
Michail Strizh
Alexander Studenikin
Aoqi Su
Jun Su
G. X. Sun
Shifeng Sun
Xilei Sun
Yongjie Sun
Guangbao Sun
Yongzhao Sun
Zhengyang Sun
Narumon Suwonjandee
Akira Takenaka
Xiaohan Tan
Jian Tang
Jing-Yu Tang
Qiang Tang
Quan Tang
Jingzhe Tang
Xiao Tang
Vidhya Thara Hariharan
Igor Tkachev
Tomas Tmej
M. Torri
Andrea Triossi
Wladyslaw Trzaska
Marco Danilo Claudio Torri
Y. Tung
Cristina Tuve
Nikita Ushakov
Vadim Vedin
Yu-Chen Tung
Carlo Venettacci
Giuseppe Verde
Maxim Vialkov
Benoit Viaud
Cornelius Moritz Vollbrecht
Katharina von Sturm
Vit Vorobel
Dmitriy Voronin
Lucia Votano
Pablo Walker
Caishen Wang
Chung-Hsiang Wang
En Wang
Guoli Wang
Yuekun Heng
Jian Wang
Jun Wang
Li Wang
Lucinda W. Wang
Meng Wang
Mingyuan Wang
Qianchuan Wang
Lu Wang
Ruiguang Wang
Sibo Wang
Siguang Wang
Wei Wang
Wenshuai Wang
Xi Wang
Xiangyue Wang
Yangfu Wang
Yaoguang Wang
Yifang Wang
Yong Wang
Yuyi Wang
Zhe Wang
Z. Wang
Zhimin Wang
Apimook Watcharangkool
Wei Wei
Wenlu Wei
Yadong Wei
Yuehuan Wei
Liangjian Wen
Jun Weng
Christopher Wiebusch
Rosmarie Wirth
Chengxin Wu
Diru Wu
Qun Wu
Yinhui Wu
Yiyang Wu
Zhi Wu
Michael Wurm
Jacques Wurtz
Christian Wysotzki
Yufei Xi
Dongmei Xia
Shishen Xian
Ziqian Xiang
Fei Xiao
Xiang Xiao
Xiaochuan Xie
Yijun Xie
Yuguang Xie
Zhao Xin
Zhizhong Xing
Benda Xu
Cheng Xu
Donglian Xu
Fanrong Xu
Hangkun Xu
Jiayang Xu
Jilei Xu
Jing Xu
Jinghuan Xu
Meihang Xu
Xunjie Xu
Yin Xu
Yu Xu
Baojun Yan
Qiyu Yan
Taylor Yan
Xiongbo Yan
Yupeng Yan
Changgen Yang
Chengfeng Yang
Fengfan Yang
Jie Yang
Lei Yang
Pengfei Yang
Xiaoyu Yang
Yifan Yang
Yixiang Yang
Zekun Yang
Haifeng Yao
Jiaxuan Ye
Mei Ye
Ziping Ye
Frédéric Yermia
Zhengyun You
Boxiang Yu
Chiye Yu
Chunxu Yu
Guojun Yu
Hongzhao Yu
Miao Yu
Xianghui Yu
Zeyuan Yu
Zezhong Yu
Cenxi Yuan
Chengzhuo Yuan
Zhenxiong Yuan
Baobiao Yue
Noman Zafar
Kirill Zamogilnyi
Vitalii Zavadskyi
Fanrui Zeng
Shan Zeng
Tingxuan Zeng
Yuda Zeng
Liang Zhan
Aiqiang Zhang
Bin Zhang
Binting Zhang
Feiyang Zhang
Hangchang Zhang
Haosen Zhang
Honghao Zhang
Jiawen Zhang
Jie Zhang
Jingbo Zhang
Jinnan Zhang
Junwei Zhang
Lei Zhang
Ping Zhang
Qingmin Zhang
Shiqi Zhang
Shu Zhang
Shuihan Zhang
Siyuan Zhang
Tao Zhang
Xiaomei Zhang
Xin Zhang
Xuantong Zhang
Yibing Zhang
Yinhong Zhang
Yiyu Zhang
Yongpeng Zhang
Yu Zhang
Yumei Zhang
Zhenyu Zhang
Zhijian Zhang
Jie Zhao
Rong Zhao
Runze Zhao
Shujun Zhao
Tianhao Zhao
Hua Zheng
Yangheng Zheng
Jing Zhou
Li Zhou
Nan Zhou
Shun Zhou
Tong Zhou
Xing Zhou
Jingsen Zhu
Kangfu Zhu
Kejun Zhu
Zhihang Zhu
Bo Zhuang
Honglin Zhuang
Liang Zong
Jiaheng Zou
2025-01-03
The European Physical Journal C (publié)
doi.org
arxiv.org
A hierarchical Bayesian brain parcellation framework for fusion of functional imaging datasets
Da Zhi
Ladan Shahshahani
Caroline Nettekoven
Ana Lúısa Pinho
Danilo Bzdok
Jörn Diedrichsen
2025-01-01
Imaging Neuroscience (publié)
doi.org
Abstract: Würstchen - An Efficient Architecture for Large-scale Text-to-image Diffusion Models
Pablo Pernias
Dominic Rampas
Mats L. Richter
Christopher Pal
Marc Aubreville
2024-12-31
Bildverarbeitung für die Medizin (publié)
doi.org
Access Inequality in LEO Satellite Networks: A Case Study of High-Latitude Coverage in Northern Québec
Mohammed Almekhlafi
Antoine Lesage-Landry
Gunes Karabulut Kurt
Low Earth orbit (LEO) satellite networks play a crucial role in bridging the digital divide, particularly in remote and high-latitude region… (voir plus)s. However, access inequality remains a significant challenge, limiting broadband connectivity for communities in northern areas compared to mid-latitude urban regions. This study reviews recent advancements in non-terrestrial networks (NTNs). We conduct a detailed analysis of coverage disparities in LEO satellite networks considering LEO networks, namely Starlink, Telesat-like, Kuiper-like, and OneWeb, with a specific focus on Québec, Canada versus urban centers in New York City, USA. Our findings highlight a significant disparity in the number of visible satellites resulting in increased transmission delays and reduced network reliability in high-latitude regions. Additionally, we observe that higher elevation angles, more accessible in mid-latitude regions especially for Starlink and Kuiper, contribute to superior signal quality and transmission rates. To mitigate this gap, we propose an inter-constellation/orbit roaming mechanism that enables ground users to be served by different LEO constellations—leveraging OneWeb's and Telesat's strong polar coverage along with the high satellite density of Starlink and Kuiper at mid-latitudes. Jointly, terrestrial network (TN) expansion can enhance signal quality and transmission efficiency, particularly in underserved areas where NTNs act as edge computing and backhaul infrastructures. Additionally, the associated challenges—such as roaming handovers, and radio resource and network slicing management are discussed in detail, where designing a unified management and control entity to ensure seamless interoperability is not a trivial task. Furthermore, we envision wireless power transfer through either relay-based (ground-to-satellite-to-ground) or direct (satellite-to-ground) power beaming as a sustainable approach to energize TN components in remote regions. These strategies collectively support the scalability and resilience of NTNs in bridging the global access inequality.
2024-12-31
IEEE Open Journal of Vehicular Technology (publié)
doi.org
Adaptation, Comparison and Practical Implementation of Fairness Schemes in Kidney Exchange Programs
William St-Arnaud
Margarida Carvalho
Golnoosh Farnadi
In Kidney Exchange Programs (KEPs), each participating patient is registered together with an incompatible donor. Donors without an incompat… (voir plus)ible patient can also register. Then, KEPs typically maximize overall patient benefit through donor exchanges. This aggregation of benefits calls into question potential individual patient disparities in terms of access to transplantation in KEPs. Considering solely this utilitarian objective may become an issue in the case where multiple exchange plans are optimal or near-optimal. In fact, current KEP policies are all-or-nothing, meaning that only one exchange plan is determined. Each patient is either selected or not as part of that unique solution. In this work, we seek instead to find a policy that contemplates the probability of patients of being in a solution. To guide the determination of our policy, we adapt popular fairness schemes to KEPs to balance the usual approach of maximizing the utilitarian objective. Different combinations of fairness and utilitarian objectives are modelled as conic programs with an exponential number of variables. We propose a column generation approach to solve them effectively in practice. Finally, we make an extensive comparison of the different schemes in terms of the balance of utility and fairness score, and validate the scalability of our methodology for benchmark instances from the literature.
2024-12-31
European Journal of Operational Research (publié)
doi.org
arxiv.org