English
Related papers

Related papers: High dimensional theory of two-phase optimizers

200 papers

We consider centralized distributed optimization in the classical federated learning setup, where $n$ workers jointly find an $\varepsilon$-stationary point of an $L$-smooth, $d$-dimensional nonconvex function $f$, having access only to…

Optimization and Control · Mathematics 2026-03-31 Alexander Tyurin

Scaling distributed training of Large Language Models (LLMs) requires not only algorithmic advances but also efficient utilization of heterogeneous hardware resources. While existing methods such as DiLoCo have demonstrated promising…

Signal Temporal Logic (STL) has gained popularity in recent years as a specification language for cyber-physical systems, especially in robotics. Beyond being expressive and easy to understand, STL is appealing because the synthesis…

Robotics · Computer Science 2020-11-17 Vince Kurtz , Hai Lin

We identify and formalize an underexplored phenomenon in deep learning optimization: directional alignment and loss convergence can be decoupled. An optimizer can exhibit near-perfect directional consistency (cc_t -> 1, measured via…

Machine Learning · Computer Science 2026-05-08 Victor Daniel Gera

Deep learning has shown that learned functions can dramatically outperform hand-designed functions on perceptual tasks. Analogously, this suggests that learned optimizers may similarly outperform current hand-designed optimizers, especially…

Neural and Evolutionary Computing · Computer Science 2019-06-11 Luke Metz , Niru Maheswaranathan , Jeremy Nixon , C. Daniel Freeman , Jascha Sohl-Dickstein

Physiological networks are usually made of a large number of biological oscillators evolving on a multitude of different timescales. Phase oscillators are particularly useful in the modelling of the synchronization dynamics of such systems.…

Adaptation and Self-Organizing Systems · Physics 2026-01-27 Melvyn Tyloo

Learning Automata (LA) are considered as one of the most powerful tools in the field of reinforcement learning. The family of estimator algorithms is proposed to improve the convergence rate of LA and has made great achievements. However,…

Artificial Intelligence · Computer Science 2017-12-04 Chong Di

Simultaneous speech translation (SST) generates translations while receiving partial speech input. Recent advances show that large language models (LLMs) can substantially improve SST quality, but at the cost of high computational overhead.…

Computation and Language · Computer Science 2026-04-24 Siqi Ouyang , Shuoyang Ding , Oleksii Hrinchuk , Vitaly Lavrukhin , Brian Yan , Boris Ginsburg , Lei Li

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

Vision-language-action (VLA) models demonstrate strong generalization in robotic manipulation but face challenges in complex, real-world tasks. While supervised fine-tuning with demonstrations is constrained by data quality, reinforcement…

Robotics · Computer Science 2025-09-18 Piaopiao Jin , Qi Wang , Guokang Sun , Ziwen Cai , Pinjia He , Yangwei You

Distributed optimization often consists of two updating phases: local optimization and inter-node communication. Conventional approaches require working nodes to communicate with the server every one or few iterations to guarantee…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-06-17 Chi Zhang , Qianxiao Li

Optimization of hyper-parameters in reinforcement learning (RL) algorithms is a key task, because they determine how the agent will learn its policy by interacting with its environment, and thus what data is gathered. In this work, an…

Machine Learning · Computer Science 2019-09-19 Juan Cruz Barsce , Jorge A. Palombarini , Ernesto Martínez

Second-order methods offer an attractive path toward more sample-efficient LLM training, but their practical use is often blocked by the systems cost of maintaining and updating large matrix-based optimizer states. We introduce…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-18 Yishun Lu , Junhao Zhang , Zeyu Yang , Wes Armour

The Adam optimizer is widely used for transformer optimization in practice, which makes understanding the underlying optimization mechanisms an important problem. However, due to the Adam's complexity, theoretical analysis of how it…

Machine Learning · Computer Science 2025-03-04 Bingrui Li , Wei Huang , Andi Han , Zhanpeng Zhou , Taiji Suzuki , Jun Zhu , Jianfei Chen

Modern learning models are characterized by large hyperparameter spaces and long training times. These properties, coupled with the rise of parallel computing and the growing demand to productionize machine learning workloads, motivate the…

Machine Learning · Computer Science 2020-03-17 Liam Li , Kevin Jamieson , Afshin Rostamizadeh , Ekaterina Gonina , Moritz Hardt , Benjamin Recht , Ameet Talwalkar

High-stability optical frequency comparison over fiber link enables the establishment of ultrastable optical clock networks, having the potential to promote a series of applications, including metrology, geodesy, and astronomy. In this…

Optics · Physics 2022-07-13 Long Wang , Ruimin Xue , Wenhai Jiao , Liang Hu Jianping Chen , Guiling Wu

Local stochastic gradient descent (Local-SGD), also referred to as federated averaging, is an approach to distributed optimization where each device performs more than one SGD update per communication. This work presents an empirical study…

We consider online convex optimization (OCO) over a heterogeneous network with communication delay, where multiple workers together with a master execute a sequence of decisions to minimize the accumulation of time-varying global costs. The…

Information Theory · Computer Science 2021-07-15 Juncheng Wang , Ben Liang , Min Dong , Gary Boudreau , Hatem Abou-zeid

Neural combinatorial optimization (NCO) is a promising learning-based approach for solving challenging combinatorial optimization problems without specialized algorithm design by experts. However, most constructive NCO methods cannot solve…

Machine Learning · Computer Science 2024-01-17 Fu Luo , Xi Lin , Fei Liu , Qingfu Zhang , Zhenkun Wang

Stochastic Gradient Descent (SGD) and its momentum variants form the backbone of deep learning optimization, yet the underlying dynamics of their gradient behavior remain insufficiently understood. In this work, we reinterpret gradient…

Machine Learning · Computer Science 2026-03-09 Zhipeng Yao , Rui Yu , Guisong Chang , Ying Li , Yu Zhang , Dazhou Li