paper-with-me

홈 › Papers

Parameter Optimization with Conscious Allocation (POCA)

2023-12-29 · Joshua Inman, Tanmay Khandait, Giulia Pedrielli, Lalitha Sankar

The performance of modern machine learning algorithms depends upon the selection of a set of hyperparameters. Common examples of hyperparameters are learning rate and the number of layers in a dense neural network. Auto-ML is a branch of optimization that has produced important contributions in this area. Within Auto-ML, hyperband-based approaches, which eliminate poorly-performing configurations after evaluating them at low budgets, are among the most effective. However, the performance of these algorithms strongly depends on how effectively they allocate the computational budget to various hyperparameter configurations. We present the new Parameter Optimization with Conscious Allocation (POCA), a hyperband-based algorithm that adaptively allocates the inputted budget to the hyperparameter configurations it generates following a Bayesian sampling scheme. We compare POCA to its nearest competitor at optimizing the hyperparameters of an artificial toy function and a deep neural network and find that POCA finds strong configurations faster in both settings.

📄 PDF Abstract BibTeX arXiv:2312.17404

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

POCAII: Parameter Optimization with Conscious Allocation using Iterative Intelligence

2025-05-16 · Joshua Inman, Tanmay Khandait, Lalitha Sankar, Giulia Pedrielli

In this paper we propose for the first time the hyperparameter optimization (HPO) algorithm POCAII. POCAII differs from the Hyperband and Successive Halving literature by explicitly separating the search and evaluation p…

Hyperparameter OptimizationSMACSMAC+

Automatic hippocampal surface generation via 3D U-net and active shape modeling with hybrid particle swarm optimization

2021-09-14 · Pinyuan Zhong, Yue Zhang, Xiaoying Tang

In this paper, we proposed and validated a fully automatic pipeline for hippocampal surface generation via 3D U-net coupled with active shape modeling (ASM). Principally, the proposed pipeline consisted of three steps. I…

HippocampusSegmentation

Stable Memory Allocation in the Hippocampus: Fundamental Limits and Neural Realization

2016-12-14 · Wenlong Mou, Zhi Wang, Li-Wei Wang

It is believed that hippocampus functions as a memory allocator in brain, the mechanism of which remains unrevealed. In Valiant's neuroidal model, the hippocampus was described as a randomly connected graph, the computat…

HippocampusMemorization

The DIME Architecture: A Unified Operational Algorithm for Neural Representation, Dynamics, Control and Integration

2026-03-07 · Ionel Cristian Vladu, Nicu Bizdoaca, Ionica Pirici, Tudor-Adrian Balseanu 외 arxiv

Modern neuroscience has accumulated extensive evidence on perception, memory, prediction, valuation, and consciousness, yet still lacks an explicit operational architecture capable of integrating these phenomena within a…

Energy-Aware Edge Association for Cluster-based Personalized Federated Learning

2022-02-06 · Y. Li, X. Qin, H. Chen, K. Han 외

Federated Learning (FL) over wireless network enables data-conscious services by leveraging the ubiquitous intelligence at network edge for privacy-preserving model training. As the proliferation of context-aware service…

Deep Reinforcement LearningFederated LearningManagementPersonalized Federated Learning+1