Objective Functions

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, down 25% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 36

All topics

Robust Nash Alignment under Preference Uncertainty
Sep 30, 2026Shihab Ahmed, Debamita Ghosh, David Tang +3Preference Alignment Nash Equilibrium
University of Central Florida · Arizona State University · University of Colorado Boulder
Self-Supervised Combinatorial Optimization with Constraints via Frank-Wolfe
Sep 22, 2026Akbar Rafiey, Yifei Xu, Nikolaos KaraliasNeural Combinatorial Optimization Combinatorial Optimization
NYU · MIT
Revisiting the Objective of Echo Chamber Detection
Sep 16, 2026Abylaikhan Bexeit, Kushani Perera, Shanika Karunasekera +1Community Detection Network Science
CIS, The University of Melbourne
Implementing neural network mixed-effects models in Template Model Builder (TMB)
Aug 31, 2026Nan Zheng, Hoi Yiu Cheung, Vibhu Sharma +2Generalized Linear Model Neural Network
Department of Mathematics and Statistics, Memorial University of Newfoundland, Canada · Resource Ecology and Fisheries Management, Alaska Fisheries Science Center, National Marine Fisheries Service, National Oceanic and Atmospheric Administration, USA · Centre for Fisheries Ecosystems Research, Fisheries and Marine Institute of Memorial University of Newfoundland, Canada
Solving Robust POMDPs with Omega-regular Objectives via Partially Observable Stochastic Games
Aug 25, 2026Durgam Latha, Dion Reji, S. Akshay +2Partially Observable Markov Decision Process Observable Stochastic Game
Indian Institute of Technology Bombay Mumbai, India · Nanyang Technological University Singapore, Singapore
DACRI: Decision-Aware Causal Intervention Ranking for Critical Supply Chains
Aug 11, 2026Shiqi Huang, Jiani He, Dingyan Shang +4Supply Chain Optimization Causal Intervention
Independent Researcher
Distributed Optimization with Streaming Data: A Temporal Weighting Perspective
Aug 10, 2026Muhammad Faraz Ul Abrar, Nicolò Michelusi, Erik G. LarssonDecentralized Optimization Weight Decay
School of Electrical, Computer and Energy Engineering, Arizona State University · Department of Electrical Engineering (ISY), Linköping University, 58183 Linköping, Sweden
Multi-Agent Reinforcement Learning via Agent-Specific Preference
Aug 9, 2026Ni Mu, Yao Luan, Yiqin Yang +1Multi-Agent Reinforcement Learning Preference Alignment Learning
CFINS, Department of Automation, BNRist, Beijing Key Laboratory of Embodied Intelligence Systems, Institute for Embodied Intelligence and Robotics, Tsinghua University, Beijing 100084, China · Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
RenderMatte: Exact-Alpha Rendering and Group-Relative Alignment for Image Matting
Aug 9, 2026Zecheng Ren, Yafei Hu, Jianing Zhao +3Opacity Value Alignment
Waseda University · Shanghai Jiao Tong University · National University of Singapore
A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequences
Aug 8, 2026Jobst Heitzig, Ram PothamHuman-Centered Framework Artificial Intelligence Safety
Potsdam Institute for Climate Impact Research, Potsdam, Germany · Independent
Uncovering expert objectives in production planning via inverse optimization: An industrial case study
Aug 7, 2026Shivi Dixit, Rishabh Gupta, Adam Kelloway +2Objective Functions Industrial
Department of Chemical Engineering and Materials Science, University of Minnesota, Minneapolis, MN 55455, USA · The Dow Chemical Company, Midland, MI 48642, USA · Department of Chemical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Non-KKT Accumulation in Entropic Mirror Descent
Aug 3, 2026Kuangyu Ding, Kim-Chuan TohMirror Descent Descent
School of Industrial Engineering, Purdue University, West Lafayette, IN 47907, USA. · Department of Mathematics and Institute of Operations Research and Analytics, National University of Singapore, Singapore 119076.
Simple-regret rates and minimax optimality of fixed-prior expected improvement in Matérn and squared-exponential RKHSs
Jul 31, 2026Emmanuel Vazquez, Sébastien PetitReproducing Kernel Hilbert Spaces Minimax Rate
Université Paris-Saclay, CNRS, CentraleSupélec, Laboratoire des Signaux et Systèmes, 91190 Gif-sur-Yvette, France · Laboratoire national de métrologie et d’essais (LNE), 1 rue Gaston Boissier, 75724 Paris Cedex 15, France
SCOPE: Synthetic Conditional Objectives for Policy Evolution in Black-Box Combinatorial Optimization
Jul 30, 2026Nguyen Viet Tuan Kiet, Nguyen Huu Duc, Le Cong Bang +2Black-Box Optimization Objective Functions
1Hanoi University of Science and Techonology, Hanoi, Vietnam · University of Sydney, Sydney, Australia
SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups
Jul 29, 2026Yikun Bai, Binghang Lu, Yikai Liu +7Meanflow Generative Models
Department of Mathematics, Purdue University · School of Electrical and Computer Engineering, Purdue University · Department of Biochemistry, Purdue University +5
Explicit Iteration Complexity of Exact Data-Driven Inverse Optimization for Integer Linear Programs
Jul 24, 2026Akira KitaokaLinear Programming Optimal Sample Complexity
Profit-Based Counterfactual Explanations for Product Improvement: A Case Study of Manga Sales in Japan
Jul 2, 2026Keita Kinjo, Takeshi EbinaCounterfactual Explanation Shapley Additive Explanations
Faculty of Business Studies, Kyoritsu Women’s University, 2-2-1, Hitotsubashi, Chiyoda-ku, Tokyo, 101-8437, Japan · School of Commerce, Meiji University, 1-1, Kanda-surugadai, Chiyoda-ku, Tokyo, 101-8301, Japan
Gradient boosting with vector-valued leafs
Jun 28, 2026David CortesGradient Boosted Decision Tree Decision Trees
Comparing Scalar Objective Functions for Multi-Criteria Engineering Optimization
Jun 26, 2026Olaf FrommannMulti-Objective Optimization Objective Functions
Institute for Aerospace Technology Hochschule Bremen, University of Applied Sciences Bremen, Germany
EvoFlock: evolved inverse design of multi-agent motion
Jun 24, 2026Craig ReynoldsSwarms Multi-Agent Evolution
unaffiliated researcher
Action-BED: Task-Driven Bayesian Experimental Design with Singly Intractable Objectives
Jun 22, 2026Tom Rossa, Angus Phillips, Tom RainforthBayesian Experimental Design Bayesian
Department of Statistics University of Oxford
Effects of Objective Normalization on Regions of Interest in Preference-Based Evolutionary Multi-Objective Optimization
Jun 15, 2026Ryuichi Mogami, Ryoji TanabeMulti-Objective Optimization Objective Functions
Yokohama National University, Yokohama, Japan
Qwen-Image-Flash: Rethinking the Training Recipe for Few-Step Distillation
Jun 2, 2026Tianhe Wu, Zikai Zhou, Kun Yan +23Image Editing Generative Models
Dynamic Objective Selection with Safeguards and LLM Oversight for Financial Decision-Making
Jun 2, 2026Keigo Sakurai, Takahiro Ogawa, Miki Haseyama +2Portfolio Construction Sequential Decision Making
Hokkaido University · Nomura Asset Management Co., Ltd. · Kobe University +1
How Much Is a Dataset Worth? Scaling Laws, the Vendi Score, and Matrix Spectral Functions
May 28, 2026Jeff A. Bilmes, Gantavya Bhatt, Arnav M. DasBenchmark Datasets Destination-Only Scoring
Department of Electrical & Computer Engineering 2Paul G. Allen School of Computer Science & Engineering University of Washington, Seattle Seattle, WA 98195
A Scalable Benchmark Test Suite for Dynamic Multi-Objective Optimization with a Changing Number of Objectives
May 25, 2026Ke Shang, Zhiyun Xiao, Yuxuan Liu +3Multi-Objective Optimization Objective Functions
School of Artificial Intelligence, Shenzhen University, Shenzhen 518060, China · National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen 518060, China · Tsinghua University, Beijing 100084, China +1
Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations
May 20, 2026Jacek Karolczak, Jerzy StefanowskiFeature Importance Interpretability
Institute of Computing Science Poznan University of Technology ul. Piotrowo 2, 60-965 Pozna´n, Poland
Decoupled Planning for Multiple Omega-Regular Objectives
May 13, 2026Guy Avni, Thomas A. Henzinger, Kaushik Mallik +2Classical Planning Objective Functions
Department of Computer Science, University of Haifa, Israel · Institute of Science and Technology Austria, Klosterneuberg, Austria · IMDEA Software Institute, Spain +2
PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding
May 9, 2026Zihao An, Taichi Liu, Ziqiong Liu +3Speculative Decoding Objective Functions
Advanced Micro Devices, Inc. · Rutgers University · Michigan State University
Bandits attack function optimization
May 5, 2026Philippe Preux, Rémi Munos, Michal ValkoBandits Objective Functions
Université de Lille, LIFL (UMR 8022 CNRS), and INRIA, France · INRIA, and LIFL, Lille, France
Characterizing Admissible Objective Functions for Hierarchical Clustering
Apr 26, 2026Ryuki Tsukuba, Kazutoshi AndoClustering Objective Functions
Graduate School of Integrated Science and Technology, Shizuoka University,Jun Hamamatsu, Shizuoka 432-8561, Japan · Faculty of Engineering, Shizuoka University, Johoku 3-5-1, 432-8561 Hamamatsu, Japan
An Efficient Spatial Branch-and-Bound Algorithm for Global Optimization of Gaussian Process Posterior Mean Functions
Apr 21, 2026Wei-Ting Tang, Akshay Kudva, Calvin Tsay +1Gaussian Process Posterior
Department of Chemical and Biological Engineering, University of Wisconsin-Madison, 1415 Engineering Drive, Madison, 53706, Wisconsin, USA. · Department of Chemical and Biomolecular Engineering, The Ohio State University, 151 W. Woodruf Avenue, Columbus, 43210, Ohio, USA. · Department of Computing, Imperial College London, Exhibition Rd, South Kensington, SW7 2AZ, London, United Kingdom.
GraphAllocBench: A Flexible Benchmark for Preference-Conditioned Multi-Objective Policy Learning
Jan 28, 2026Zhiheng Jiang, Yunzhe Wang, Ryan Marr +3Multi-Objective Reinforcement Learning Objective Functions
University of California, Los Angeles · USC Institute for Creative Technologies · U.S. Army DEVCOM Army Research Laboratory
Subjective functions
Dec 17, 2025Samuel J. GershmanSubjectivity Objective Functions
Department of Psychology and Center for Brain Science · Kempner Institute for the Study of Natural and Artificial Intelligence · Harvard University
Steering Noncooperative Games Through Conjecture Design
Nov 12, 2025Francesco Morri, Hélène Le Cadre, David Salas +1Equilibrium Incentives
Inria, Univ. Lille CNRS, Centrale Lille · Instituto de Ciencias de la Ingeniería Universidad de O’Higgins · Laboratoire PROMESUPR 8521 Université de Perpignan, Tecnosud
SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence
Dec 6, 2024Bowei Tian, Yexiao He, Ziyao Wang +3Algorithmic Fairness Causal Inferences
University of Maryland, College Park, MD 20742, USA · Clemson University, Clemson, SC 29634, USA

Sep 30, 2026, cs.AIJ/K move · Enter open · S save

Robust Nash Alignment under Preference Uncertainty

Shihab Ahmed, Debamita Ghosh, David Tang, Yudan Wang+2

University of Central Florida · Arizona State University · University of Colorado Boulder

Preference Alignment Nash Equilibrium Preference Alignment Learning Objective Functions Uncertainty

Open paper AskPDF arXiv

Preference-based alignment methods typically optimize against a single preference model, and can therefore be brittle when pairwise preferences are uncertain: noisy, heterogeneous, or shift after deployment. To address these issues, we propose Robust Nash Alignment, a game-theoretic framework for alignment to uncertain pairwise preferences. Our formulation has a major learner seeking a policy with a large worst-case win rate against both an adversarial competitor and any preference kernel lying in an ambiguity set around a nominal preference. When the ambiguity set captures the uncertainty in preferences, the resulting robust objective of the game directly yields a certified lower bound on worst-case performance. However, we note this problem is computationally challenging to optimize, and to address this, we introduce a four-player primal-dual proxy game involving the leader policy, follower policy, adversarial kernel, and dual variable, and develop a single-loop optimistic mirror descent-ascent algorithm for it. We show that the proxy always lower-bounds the truncated hard-constrained objective, quantify the proxy-to-hard gap, and characterize an exactness condition under which the proxy recovers the robust objective. We then prove an

\mathcal{O}(1/\sqrt{T})

average-iteration convergence for the proxy-game duality gap, which implies a near-optimal robust policy for the original robust objective. Experiments on controlled tabular games and LLM alignment with uncertain preference further validate the convergence theory and show improved performance over nominal baselines.

Momentum

Related topics

Latest papers 36