English
Related papers

Related papers: AMO: Adaptive Muon Orthogonalization

200 papers

Recent developments in deep learning optimization have brought about radically new algorithms based on the Linear Minimization Oracle (LMO) framework, such as $\sf Muon$ and $\sf Scion$. After over a decade of $\sf Adam$'s dominance, these…

Machine Learning · Computer Science 2025-05-20 Artem Riabinin , Egor Shulgin , Kaja Gruntkowska , Peter Richtárik

Aligning large language models (LLMs) with diverse and multifaceted user preferences is a fundamental challenge in personalized AI systems. Existing multi-objective alignment methods either rely on costly training or require pre-trained…

Computation and Language · Computer Science 2026-05-26 Linhao Luo , Thuy-Trang Vu , Van-Anh Nguyen , Junae Kim , Gholamreza Haffari , Dinh Phung

Geometry-aware optimization algorithms, such as Muon, have achieved remarkable success in training deep neural networks (DNNs). These methods leverage the underlying geometry of DNNs by selecting appropriate norms for different layers and…

Machine Learning · Computer Science 2026-02-04 Jie Hao , Xiaochuan Gong , Jie Xu , Zhengdao Wang , Mingrui Liu

Topology Optimization (TO) provides a systematic approach for obtaining structure design with optimum performance of interest. However, the process requires numerical evaluation of objective function and constraints at each iteration, which…

Machine Learning · Computer Science 2022-03-22 Ren Kai Tan , Chao Qian , Dan Xu , Wenjing Ye

Training a modern machine learning architecture on a new task requires extensive learning-rate tuning, which comes at a high computational cost. Here we develop new Polyak-type adaptive learning rates that can be used on top of any momentum…

Machine Learning · Computer Science 2024-06-06 Fabian Schaipp , Ruben Ohana , Michael Eickenberg , Aaron Defazio , Robert M. Gower

Modern adaptive optimization methods, such as Adam and its variants, have emerged as the most widely used tools in deep learning over recent years. These algorithms offer automatic mechanisms for dynamically adjusting the update step based…

Machine Learning · Computer Science 2025-02-12 Son Nguyen , Bo Liu , Lizhang Chen , Qiang Liu

This work presents UNO, a unified monocular visual odometry framework that enables robust and adaptable pose estimation across diverse environments, platforms, and motion patterns. Unlike traditional methods that rely on deployment-specific…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Wentao Zhao , Yihe Niu , Yanbo Wang , Tianchen Deng , Shenghai Yuan , Zhenli Wang , Rui Guo , Jingchuan Wang

Algorithms for learning distributions over weight-vectors, such as AROW were recently shown empirically to achieve state-of-the-art performance at various problems, with strong theoretical guaranties. Extending these algorithms to matrix…

Machine Learning · Computer Science 2012-06-22 Koby Crammer , Gal Chechik

Neural networks are susceptible to artificially designed adversarial perturbations. Recent efforts have shown that imposing certain modifications on classification layer can improve the robustness of the neural networks. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2021-09-27 Cong Xu , Xiang Li , Min Yang

Proximal Policy Optimization (PPO) dominates reinforcement learning and LLM alignment but relies on a "hard clipping" mechanism that discards valuable gradients. Conversely, unconstrained methods like SPO expose the optimization to…

Artificial Intelligence · Computer Science 2026-05-07 Yiheng Zhang , Yiming Wang , Kaiyan Zhao , Zhenglin Wan , Jiayu Chen , Leong Hou U

Adversarial training has emerged as a highly effective way to improve the robustness of deep neural networks (DNNs). It is typically conceptualized as a min-max optimization problem over model weights and adversarial perturbations, where…

Machine Learning · Computer Science 2026-03-03 Gaojie Jin , Xinping Yi , Wei Huang , Sven Schewe , Xiaowei Huang

AdamW has long been the dominant optimizer in language model pretraining, despite numerous claims that alternative optimizers offer 1.4 to 2x speedup. We posit that two methodological shortcomings have obscured fair comparisons and hindered…

Machine Learning · Computer Science 2025-09-08 Kaiyue Wen , David Hall , Tengyu Ma , Percy Liang

Optimizing large-scale nonconvex problems, common in deep learning, demands balancing rapid convergence with computational efficiency. First-order (FO) optimizers, which serve as today's baselines, provide fast convergence and good…

Machine Learning · Computer Science 2025-09-30 Jiahe Chen , Ziye Ma

Multi-objective optimization (MOO) is a prevalent challenge for Deep Learning, however, there exists no scalable MOO solution for truly deep neural networks. Prior work either demand optimizing a new network for every point on the Pareto…

Machine Learning · Computer Science 2021-10-15 Michael Ruchte , Josif Grabocka

Recent work by Xia et al. leveraged the continuous-limit of the classical momentum accelerated gradient descent and proposed heavy-ball neural ODEs. While this model offers computational efficiency and high utility over vanilla neural ODEs,…

Machine Learning · Computer Science 2022-07-14 Suneghyeon Cho , Sanghyun Hong , Kookjin Lee , Noseong Park

One predominant challenge in additive manufacturing (AM) is to achieve specific material properties by manipulating manufacturing process parameters during the runtime. Such manipulation tends to increase the computational load imposed on…

Machine Learning · Computer Science 2023-10-24 Mahmoud Yaseen , Dewen Yushu , Peter German , Xu Wu

The rapid development of large language models (LLMs) has driven the demand for more efficient optimization techniques. Among these, the Lookahead family of optimizers employs a two-loop framework, maintaining fast and slow sets of model…

Machine Learning · Computer Science 2025-10-20 Dominik Kallusky , Vinay Rao , Vishal Nandavanam , Hao-Jun Michael Shi

This paper presents a new view of multi-user (MU) hybrid massive multiple-input and multiple-output (MIMO) systems from array signal processing perspective. We first show that the instantaneous channel vectors corresponding to different…

Information Theory · Computer Science 2022-10-18 Hai Lin , Feifei Gao , Shi Jin , Geoffrey Ye Li

Today's wireless networks allocate radio resources to users based on the orthogonal multiple access (OMA) principle. However, as the number of users increases, OMA based approaches may not meet the stringent emerging requirements including…

Signal Processing · Electrical Eng. & Systems 2019-02-28 Mahmoud Aldababsa , Mesut Toka , Selahattin Gokceli , Gunes Karabulut Kurt , Oguz Kucur

Non-orthogonal multiple access (NOMA) systems have the potential to deliver higher system throughput, compared to contemporary orthogonal multiple access techniques. For a linearly precoded multiple-input multiple-output (MISO) system, we…

Information Theory · Computer Science 2015-12-08 Muhammad Fainan Hanif , Zhiguo Ding , Tharmalingam Ratnarajah , George K. Karagiannidis