paper-with-me

홈 › Papers

Accelerating Neural Network Optimization Through an Automated Control Theory Lens

2022-01-01 · CVPR 2022 1 · Jiahao Wang, Baoyuan Wu, Rui Su, Mingdeng Cao, Shuwei Shi, Wanli Ouyang, Yujiu Yang

This paper studies the optimizer for accelerating the time-consuming deep network training through an automated control theory lens. We view the parameter update of a network as a feedback control process. It brings two contributions: First, we theoretically analyze the detailed intrinsic connections between deep network training and automatic control feedback system. Specifically, we demonstrate that the optimization process can be viewed as a Type I Second Order System in control field. Second, based on the math model of the equivalent system, we further design a proportional-integral-derivative algorithm type Controller with decoupled weight decay based on control theory to improve the training of deep neural networks. We conduct experiments both from a control theory lens through a phase locus verification and from a network training lens on several models, including CNNs, Transformers, MLPs, and on benchmark datasets. The results demonstrate the effectiveness of our Controller optimizer in both optimization speed and performance compared to SGD, PID Optimizer, Adam, AdamW and AdamP.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Math

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Weight Decay 설명 없음
SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…
AdamW AdamW is a stochastic optimization method that modifies the typical implementation of weight decay in Adam, by decoupling [weight…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Stochastic Resetting Accelerates Policy Convergence in Reinforcement Learning

2026-03-17 · Jello Zhou, Vudtiwat Ngampruetikorn, David J. Schwab arxiv

Stochastic resetting, where a dynamical process is intermittently returned to a fixed reference state, has emerged as a powerful mechanism for optimizing first-passage properties. Existing theory largely treats static, n…

Reinforcement LearningContinuous Control

Bayesian Co-navigation: Dynamic Designing of the Materials Digital Twins via Active Learning

2024-04-19 · Boris N. Slautin, Yongtao Liu, Hiroshi Funakubo, Rama K. Vasudevan 외

Scientific advancement is universally based on the dynamic interplay between theoretical insights, modelling, and experimental discoveries. However, this feedback loop is often slow, including delayed community interacti…

Active Learning

PAHQ: Accelerating Automated Circuit Discovery through Mixed-Precision Inference Optimization

2025-10-27 · Xinhai Wang, Shu Yang, Liangyu Wang, Lin Zhang 외 arxiv

Circuit discovery, which involves identifying sparse and task-relevant subnetworks in pre-trained language models, is a cornerstone of mechanistic interpretability. Automated Circuit Discovery (ACDC) has emerged as a piv…

Accelerating process control and optimization via machine learning: A review

2024-12-24 · Ilias Mitrai, Prodromos Daoutidis

Process control and optimization have been widely used to solve decision-making problems in chemical engineering applications. However, identifying and tuning the best solution algorithm is challenging and time-consuming…

Decision Making

Reinforcement Learning Increases Wind Farm Power Production by Enabling Closed-Loop Collaborative Control

2025-06-25 · Andrew Mole, Max Weissenbacher, Georgios Rigas, Sylvain Laizet

Traditional wind farm control operates each turbine independently to maximize individual power output. However, coordinated wake steering across the entire farm can substantially increase the combined wind farm energy pr…

Bayesian OptimizationReinforcement Learning (RL)