Tag: math.OC
arXiv:2602.21255v1 Announce Type: cross Abstract: We establish a general equilibrium theory for systems of large language model (LLM) agents operating under centralized orchestration. The framework …
arXiv:2602.21321v1 Announce Type: new Abstract: Analog in-memory computing (AIMC) performs computation directly within resistive crossbar arrays, offering an energy-efficient platform to scale large vision and …
arXiv:2602.21429v1 Announce Type: new Abstract: Flow-based generative models, such as diffusion models and flow matching models, have achieved remarkable success in learning complex data distributions. …
arXiv:2602.20175v1 Announce Type: new Abstract: We present an application of the tensor network generator-enhanced optimization (TN-GEO) framework to address the traveling salesman problem (TSP), a …
arXiv:2602.20271v1 Announce Type: new Abstract: Accurate delivery delay prediction is critical for maintaining operational efficiency and customer satisfaction across modern supply chains. Yet the increasing …
arXiv:2602.20403v1 Announce Type: new Abstract: We study distributionally robust online learning, where a risk-averse learner updates decisions sequentially to guard against worst-case distributions drawn from …
arXiv:2602.20567v1 Announce Type: new Abstract: Push-Sum-based decentralized learning enables optimization over directed communication networks, where information exchange may be asymmetric. While convergence properties of such …
arXiv:2602.20578v1 Announce Type: new Abstract: We study online maximization of non-monotone Diminishing-Return(DR)-submodular functions over down-closed convex sets, a regime where existing projection-free online methods suffer …
arXiv:2602.17679v1 Announce Type: new Abstract: Bayesian optimization (BO) is a powerful method for optimizing black-box manufacturing processes, but its performance is often limited when dealing …
arXiv:2602.16012v1 Announce Type: new Abstract: Neural solvers have achieved impressive progress in addressing simple routing problems, particularly excelling in computational efficiency. However, their advantages under …
arXiv:2602.16796v1 Announce Type: new Abstract: Fine-tuning pre-trained diffusion and flow models to optimize downstream utilities is central to real-world deployment. Existing entropy-regularized methods primarily maximize …
arXiv:2602.16849v1 Announce Type: new Abstract: We present a comprehensive analysis of how two-layer neural networks learn features to solve the modular addition task. Our work …
