Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer
School of Computing(计算学院);Fédération ENAC(ENAC联合会);ISAE-SUPAERO;ONERA;National University of Singapore(新加坡国立大学);Université de Toulouse(图卢兹大学);Agency for Science, Technology and Research(科技研究局);Institute for Infocomm Research(信息通信研究所)
Yannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi
A learning-to-defer (L2D) system decides, for each input, whether to predict on its own or to hand it to one of several available experts. The very well established recipe trains classifier and router jointly by treating the $K$ classes and $J$ experts as competing actions in one shared $(K{+}J)$-action geometry. Subsequent work has proposed a series of incremental fixes within this geometry; we show that each still suffers, to varying severity, from an optimization-level pathology (target distortion, gradient amplification, winner-take-all starvation, set-mass collapse, or class-expert coupling) even under statistical consistency. We step outside the augmented-action family entirely and propose a decoupled surrogate: a softmax classifier head and an independent sigmoid head per expert, mirroring the two natural objects of the problem. We show that per-sample updates are then coordinatewise and the class-expert Hessian block is identically zero, and prove an excess-risk bound with calibration constant $\max\{2\sqrt{2},\sqrt{2J/λ}\}$ -- to our knowledge the first multi-expert L2D guarantee whose constant does not grow with the expert pool when the per-expert weight is held fixed. On controlled synthetic studies and on CIFAR-10, CIFAR-10H, and Covertype, it is the only method in our comparison that remains stable as the expert pool grows, preserves rare specialists, and improves over a standalone classifier on every real-data benchmark.
Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts
School of Computing, National University of Singapore(新加坡国立大学计算机学院);Fédération ENAC, ISAE-SUPAERO, ONERA, Université de Toulouse(ENAC联合会、ISAE-SUPAERO、ONERA、图卢兹大学);Agency for Science, Technology and Research, Institute for Infocomm Research(科技研究局、信息通信研究所)
A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
School of Computing, National University of Singapore, Singapore(新加坡国立大学计算机学院);IRIT, Université de Toulouse, CNRS, Toulouse INP, Toulouse, France(图卢兹大学IRIT研究所,法国国家科学研究中心,图卢兹INP);Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore(新加坡资讯与通信研究院,新加坡科技研究局)
Adversarial Robustness in One-Stage Learning-to-Defer
School of Computing, National University of Singapore(新加坡国立大学计算机学院);Fédération ENAC ISAE-SUPAERO ONERA, Université de Toulouse, France(法国图卢兹大学ENAC ISAE-SUPAERO ONERA联合体);Institute for Infocomm Research, A*STAR , Singapore(新加坡星展研究所);IPAL, IRL 2955, Singapore(新加坡IPAL实验室)
School of Computing, National University of Singapore(新加坡国立大学计算机学院);Fédération ENAC ISAE-SUPAERO ONERA, Université de Toulouse, France(法国图卢兹大学ENAC ISAE-SUPAERO ONERA联合体);Institute for Infocomm Research, A*STAR , Singapore(新加坡A*STAR信息通信研究所);IPAL, IRL 2955, Singapore(新加坡IPAL实验室);Department of Mathematics, National University of Singapore(新加坡国立大学数学系)
Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees
School of Computing, National University of Singapore, Singapore(新加坡国立大学计算机学院);IRIT, Université de Toulouse, CNRS, Toulouse INP, Toulouse, France(图卢兹大学IRIT研究所、法国国家科学研究中心、图卢兹INP);Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore(新加坡科技研究局信息与通信研究所)
Multifidelity-Augmented Gaussian Process Inputs for Surrogate Modeling from Scarce Data
School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA(航空航天工程学院,佐治亚理工学院,亚特兰大,GA);School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, GA(计算科学与工程学院,佐治亚理工学院,亚特兰大,GA);Air Force Research Lab, Wright-Patterson AFB, Dayton, Ohio(空军研究实验室,威格伍德-帕特森空军基地,代顿,俄亥俄)
Consistent Learning-to-Defer with Expert-Conditional Advice
School of Computing(计算学院);Département de Mathématiques(数学系);National University of Singapore(新加坡国立大学);Sorbonne University(索邦大学);Fédération ENAC(ENAC联合会);ISAE-SUPAERO;ONERA;Agency for Science, Technology and Research(科技研究局);Université de Toulouse(图卢兹大学);Institute for Infocomm Research(信息与通信研究所)