English
Related papers

Related papers: Debiasing a First-order Heuristic for Approximate …

200 papers

In this paper, we formalise order-robust optimisation as an instance of online learning minimising simple regret, and propose Vroom, a zero'th order optimisation algorithm capable of achieving vanishing regret in non-stationary…

Machine Learning · Computer Science 2019-10-23 Victor Gabillon , Rasul Tutunov , Michal Valko , Haitham Bou Ammar

In this paper, we consider both first- and second-order techniques to address continuous optimization problems arising in machine learning. In the first-order case, we propose a framework of transition from deterministic or…

Machine Learning · Computer Science 2021-11-30 Sanae Lotfi , Tiphaine Bonniot de Ruisselet , Dominique Orban , Andrea Lodi

Popular machine learning approaches forgo second-order information due to the difficulty of computing curvature in high dimensions. We present FOSI, a novel meta-algorithm that improves the performance of any base first-order optimizer by…

Machine Learning · Computer Science 2024-03-08 Hadar Sivan , Moshe Gabel , Assaf Schuster

Regularization techniques are crucial to improving the generalization performance and training efficiency of deep neural networks. Many deep learning algorithms rely on weight decay, dropout, batch/layer normalization to converge faster and…

Machine Learning · Computer Science 2025-05-23 Peng Lu , Ahmad Rashid , Ivan Kobyzev , Mehdi Rezagholizadeh , Philippe Langlais

Stochastic optimization methods have actively been playing a critical role in modern machine learning algorithms to deliver decent performance. While numerous works have proposed and developed diverse approaches, first-order and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Zhanhong Jiang , Md Zahid Hasan , Aditya Balu , Joshua R. Waite , Genyi Huang , Soumik Sarkar

Augmented Lagrangian Method (ALM) combined with Burer-Monteiro (BM) factorization, dubbed ALM-BM, offers a powerful approach for solving large-scale low-rank semidefinite programs (SDPs). Despite its empirical success, the theoretical…

Optimization and Control · Mathematics 2025-05-22 Lijun Ding , Haihao Lu , Jinwen Yang

Fine-tuning large language models (LLMs) using standard first-order (FO) optimization often drives training toward sharp, poorly generalizing minima. Conversely, zeroth-order (ZO) methods offer stronger exploratory behavior without relying…

Machine Learning · Computer Science 2026-01-12 Feihu Jin , Ying Tan

Training large language models (LLMs) relies on adaptive optimizers such as Adam, which introduce extra operations and require significantly more memory to maintain first- and second-order moments than SGD. While recent works such as…

Machine Learning · Computer Science 2026-05-22 Athanasios Glentis , Jiaxiang Li , Andi Han , Mingyi Hong

Bilevel optimization has recently attracted growing interests due to its wide applications in modern machine learning problems. Although recent studies have characterized the convergence rate for several such popular algorithms, it is still…

Machine Learning · Computer Science 2022-02-01 Kaiyi Ji , Yingbin Liang

Bilevel optimization is a popular hierarchical model in machine learning, and has been widely applied to many machine learning tasks such as meta learning, hyperparameter learning and policy optimization. Although many bilevel optimization…

Machine Learning · Computer Science 2022-11-15 Feihu Huang

Large Language Models (LLMs) suffer from order bias, where their performance is affected by the arrangement order of input elements. This unfairness limits the model's applications in scenarios such as in-context learning and…

Machine Learning · Computer Science 2026-05-13 Xu Chu , Guanyu Wang , Zhijie Tan , Xinrong Chen , Ziyu Li , Tong Mo , Weiping Li

We prove lower bounds for higher-order methods in smooth non-convex finite-sum optimization. Our contribution is threefold: We first show that a deterministic algorithm cannot profit from the finite-sum structure of the objective, and that…

Optimization and Control · Mathematics 2021-07-05 Nicolas Emmenegger , Rasmus Kyng , Ahad N. Zehmakan

Online bilevel optimization (OBO) is a powerful framework for machine learning problems where both outer and inner objectives evolve over time, requiring dynamic updates. Current OBO approaches rely on deterministic \textit{window-smoothed}…

Machine Learning · Computer Science 2026-05-20 Parvin Nazari , Bojian Hou , Davoud Ataee Tarzanagh , Li Shen , George Michailidis

In this paper, we propose a quantum algorithm that supports a real-valued higher-order unconstrained binary optimization (HUBO) problem. This algorithm is based on the Grover adaptive search that originally supported HUBO with integer…

Signal Processing · Electrical Eng. & Systems 2023-02-17 Masaya Norimoto , Ryuhei Mori , Naoki Ishikawa

Large Language Model-based Hyper Heuristic (LHH) has recently emerged as an efficient way for automatic heuristic design. However, most existing LHHs just perform well in optimizing a single function within a pre-defined solver. Their…

Artificial Intelligence · Computer Science 2026-04-15 Chuyang Xiang , Yichen Wei , Jiale Ma , Handing Wang , Junchi Yan

These notes focus on the minimization of convex functionals using first-order optimization methods, which are fundamental in many areas of applied mathematics and engineering. The primary goal of this document is to introduce and analyze…

Optimization and Control · Mathematics 2024-10-28 Charles Dossal , Samuel Hurault , Nicolas Papadakis

Bilevel Optimization has witnessed notable progress recently with new emerging efficient algorithms and has been applied to many machine learning tasks such as data cleaning, few-shot learning, and neural architecture search. However,…

Machine Learning · Computer Science 2022-05-04 Junyi Li , Feihu Huang , Heng Huang

It is well-known that the lower bound of iteration complexity for solving nonconvex unconstrained optimization problems is $\Omega(1/\epsilon^2)$, which can be achieved by standard gradient descent algorithm when the objective function is…

Optimization and Control · Mathematics 2022-11-02 Jiawei Zhang , Wenqiang Pu , Zhi-Quan Luo

Portfolio optimization is one of the most studied optimization problems at the intersection of quantum computing and finance. In this work, we develop the first quantum formulation for a portfolio optimization problem with higher-order…

Quantum Physics · Physics 2026-01-28 Valter Uotila , Julia Ripatti , Bo Zhao

In this paper, we consider an unconstrained stochastic optimization problem where the objective function exhibits high-order smoothness. Specifically, we propose a new stochastic first-order method (SFOM) with multi-extrapolated momentum,…

Optimization and Control · Mathematics 2025-04-09 Chuan He