paper-with-me

Papers

Towards Hyperparameter-Agnostic DNN Training via Dynamical System Insights

2023-10-21 · Carmel Fiscko, Aayushya Agarwal, Yihan Ruan, Soummya Kar, Larry Pileggi, Bruno Sinopoli

We present a stochastic first-order optimization method specialized for deep neural networks (DNNs), ECCO-DNN. This method models the optimization variable trajectory as a dynamical system and develops a discretization algorithm that adaptively selects step sizes based on the trajectory's shape. This provides two key insights: designing the dynamical system for fast continuous-time convergence and developing a time-stepping algorithm to adaptively select step sizes based on principles of numerical integration and neural network structure. The result is an optimizer with performance that is insensitive to hyperparameter variations and that achieves comparable performance to state-of-the-art optimizers including ADAM, SGD, RMSProp, and AdaGrad. We demonstrate this in training DNN models and datasets, including CIFAR-10 and CIFAR-100 using ECCO-DNN and find that ECCO-DNN's single hyperparameter can be changed by three orders of magnitude without affecting the trained models' accuracies. ECCO-DNN's insensitivity reduces the data and computation needed for hyperparameter tuning, making it advantageous for rapid prototyping and for applications with new datasets. To validate the efficacy of our proposed optimizer, we train an LSTM architecture on a household power consumption dataset with ECCO-DNN and achieve an optimal mean-square-error without tuning hyperparameters.

📄 PDF Abstract BibTeX arXiv:2310.13901

Code (0)

등록된 구현이 없습니다.

Tasks

Numerical Integration

Methods 이 논문이 사용한 방법론

Tanh Activation 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…
Sigmoid Activation 설명 없음
AdaGrad AdaGrad is a stochastic optimization method that adapts the learning rate to the parameters. It performs smaller updates for parameters associated with frequently occurring…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
RMSProp RMSProp is an unpublished adaptive learning rate optimizer proposed by Geoff Hinton. The motivation…

Similar Papers 제목 키워드 기반

AutoRL Hyperparameter Landscapes

2023-04-05 · Aditya Mohan, Carolin Benjamins, Konrad Wienecke, Alexander Dockhorn 외

Although Reinforcement Learning (RL) has shown to be capable of producing impressive results, its use is limited by the impact of its hyperparameters on performance. This often makes it difficult to achieve good results …

AutoMLHyperparameter OptimizationOpen-Ended Question AnsweringReinforcement Learning (RL)

On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning

2021-02-26 · Baohe Zhang, Raghu Rajan, Luis Pineda, Nathan Lambert 외

Model-based Reinforcement Learning (MBRL) is a promising framework for learning control in a data-efficient manner. MBRL algorithms can be fairly complex due to the separate dynamics modeling and the subsequent planning …

Hyperparameter OptimizationModel-based Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

HyperTendril: Visual Analytics for User-Driven Hyperparameter Optimization of Deep Neural Networks

2020-09-04 · Heungseok Park, Yoonsoo Nam, Ji-Hoon Kim, Jaegul Choo

To mitigate the pain of manually tuning hyperparameters of deep neural networks, automated machine learning (AutoML) methods have been developed to search for an optimal set of hyperparameters in large combinatorial sear…

AutoMLHyperparameter Optimization

HyperController: A Hyperparameter Controller for Fast and Stable Training of Reinforcement Learning Neural Networks

2025-04-27 · Jonathan Gornet, Yiannis Kantaros, Bruno Sinopoli

We introduce Hyperparameter Controller (HyperController), a computationally efficient algorithm for hyperparameter optimization during training of reinforcement learning neural networks. HyperController optimizes hyperpa…

Hyperparameter Optimizationreinforcement-learningReinforcement Learning

Iterated Population Based Training with Task-Agnostic Restarts

2025-11-12 · Alexander Chebykin, Tanja Alderliesten, Peter A. N. Bosman arxiv

Hyperparameter Optimization (HPO) can lift the burden of tuning hyperparameters (HPs) of neural networks. HPO algorithms from the Population Based Training (PBT) family are efficient thanks to dynamically adjusting HPs e…

Hyperparameter OptimizationReinforcement LearningImage Classification