arXiv:2609. 30501v1 Announce Type: new Abstract: Although bilevel optimization (BLO) has emerged as a powerful framework for addressing many complex and nested machine learning problems in recent years, most existing studies are confined to the lower-level strongly convex (LLSC) or lower-level generally convex (LLGC) settings (i.
By Zhiyao Zhang, Menglu Yu, Alvaro Velasquez, Nathaniel D. Bastian, Jia Liu
arXiv:2602.14506v2 Announce Type: replace
Abstract: We explore the use of transformers for solving quadratic programs and how this capability benefits decision-making problems that involve covariance...
By Kutay Tire, Yufan Zhang, Ege Onur Taga, Samet Oymak
arXiv:2508. 00775v2 Announce Type: replace-cross Abstract: The design of many classical optimization algorithms is driven by the certification of linear convergence rates over classes of optimization problems.
By Andrea Martin, Ian R. Manchester, Luca Furieri
arXiv:2607. 20769v1 Announce Type: new Abstract: Learning-enabled decision systems often use offline data or computation to reduce online compute cost.
By Shijie Pan, Agustin Castellano, Zeyu Shen, Enrique Mallada
arXiv:2606. 08797v1 Announce Type: cross Abstract: Decision-focused learning has shown great promise for addressing predict-then-optimize problems, particularly in the presence of under-specified models.
By St\'ephane Eilles-Chan Way, Hugo Percot, Quentin Cappart, Tias Guns, Louis-Martin Rousseau
arXiv:2406. 13041v3 Announce Type: replace Abstract: Lower-bound analyses for nonconvex strongly-concave minimax optimization problems have shown that stochastic first-order algorithms require at least $\mathcal{O}(\varepsilon^{-4})$ sample complexity to find an $\varepsilon$-stationary point.
By Haoyuan Cai, Sulaiman A. Alghunaim, Ali H. Sayed
arXiv:2606. 01764v1 Announce Type: cross Abstract: We revisit the convergence guarantees of the Extragradient (EG) method for unconstrained biaffine min-max optimization.
By Yue Wu, Weiqiang Zheng, Yang Cai, Haipeng Luo
The paper introduces a decision‑focused learning framework for mean‑variance portfolio optimization that embeds the Karush‑Kuhn‑Tucker optimality conditions of the lower‑level optimization into a single‑level learning problem. This approach preserves budget and short‑sale constraints while remaining tractable for standard nonlinear solvers. Experiments on real‑world ETF data across two asset universes demonstrate superior performance on multiple investment metrics and highlight the benefits of the proposed regularization.
By Kensei Nosaka, Shunnosuke Ikeda, Yuichi Takano
arXiv:2602. 21436v2 Announce Type: replace-cross Abstract: In this paper, we study last-iterate convergence of learning algorithms in bilinear saddle-point problems, a preferable notion of convergence that captures the day-to-day behavior of learning dynamics.
By Arnab Maiti, Claire Jie Zhang, Kevin Jamieson, Jamie Heather Morgenstern, Ioannis Panageas, Lillian J. Ratliff
arXiv:2606. 01521v1 Announce Type: new Abstract: A central problem in machine learning is that models can achieve near-perfect training performance while generalizing substantially less well to unseen examples.
By Luca Muscarnera, Silas Ruhrberg Est\'evez, Yuanzhang Xiao, Mihaela Van der Schaar
arXiv:2606. 15832v1 Announce Type: new Abstract: Empirical risk minimization on massive datasets naturally exhibits a nested double finite-sum structure, where $N=nm$ total samples are logically or physically partitioned into $n$ blocks of size $m$ (e.
By Igor Sokolov, Laurent Condat, Peter Richt\'arik
The paper introduces RanSOM, a second‑order momentum algorithm that eliminates the need for a Lipschitz Hessian or auxiliary forward/backward passes by randomizing the step length. By sampling the step from an exponential distribution and using a Stein‑type identity, the method obtains an unbiased estimate of the gradient change with a single Hessian‑vector product that also serves the next gradient computation. RanSOM-E achieves optimal oracle‑complexity exponents for heavy‑tailed noise without clipping, while RanSOM-B preserves feasibility for Frank‑Wolfe iterates, and experiments on CIFAR‑10 show comparable accuracy to existing methods with lower update time.
By El Mahdi Chayti, Mohamad Fakhouri