Results 21 to 30 of about 6,234,642 (356)
Policy Optimization for H2 Linear Control with H∞ Robustness Guarantee: Implicit Regularization and Global Convergence [PDF]
SIAM Journal of Control and Optimization, 2019 Policy optimization (PO) is a key ingredient for reinforcement learning (RL). For control design, certain constraints are usually enforced on the policies to optimize, accounting for either the stability, robustness, or safety concerns on the system ...
K. Zhang, Bin Hu, T. Başar
semanticscholar +1 more source
On the Global Convergence of the Jacobi Method [PDF]
PAMM, 2016 AbstractThe paper is concerned with the global convergence of the Jacobi method for symmetric matrices under a special class of cyclic pivot strategies. That class generalizes the well‐known class of serial strategies. (© 2016 Wiley‐VCH Verlag GmbH & Co. KGaA, Weinheim)
Vjeran Hari, Erna Begović Kovač
openaire +3 more sources
Scientific Reports, 2023 Mucosal tissues serve as the first defense line and their commensal microbiota play a role in sustaining of host health. This study aimed to isolate and evaluate a putative probiotic strain on various mucosal regions.
Hye-Shin Kim +6 more
doaj +1 more source
Toward Moderate Overparameterization: Global Convergence Guarantees for Training Shallow Neural Networks [PDF]
IEEE Journal on Selected Areas in Information Theory, 2019 Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset.
Samet Oymak, M. Soltanolkotabi
semanticscholar +1 more source
Frontiers in Energy Research, 2022 The recent use of hybrid renewable energy systems (HRESs) is considered one of the most reliable ways to improve energy access to decentralized communities because of their techno-economic and environmental benefits.
Noel Ngando Same +6 more
doaj +1 more source
ADMM for Efficient Deep Learning with Global Convergence [PDF]
Knowledge Discovery and Data Mining, 2019 Alternating Direction Method of Multipliers (ADMM) has been used successfully in many conventional machine learning applications and is considered to be a useful alternative to Stochastic Gradient Descent (SGD) as a deep learning optimizer.
Junxiang Wang +3 more
semanticscholar +1 more source
Financial Globalization, Convergence and Growth [PDF]
SSRN Electronic Journal, 2008 Using a panel data set covering the period 1970-2004 and 96 countries, we provide empirical evidence that the composition of foreign capital, measured by the ratio FDI over total liabilities, has a positive effect on growth, directly and through convergence. Developing countries benefit relatively more as their initial GDP is smaller. These results are
Delfim Gomes Neto, Francisco José Veiga
openaire +3 more sources
IEEE Access, 2023 Event logs play a crucial role in monitoring the status of IT systems. These logs contain text that describes how a system operates using natural language, which can be associated with sentiment polarity.
Tuan-Anh Pham, Jong-Hoon Lee
doaj +1 more source
Photonics, 2021 The optimization of solid-state laser cavities requires a deep understanding of the gain module, the most critical laser component. This study proposes a procedure for evaluating the performance of the solid-state laser gain module.
Daewoong Park +5 more
doaj +1 more source
Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Stochastic Optimization: Non-Asymptotic Performance Bounds and Momentum-Based Acceleration [PDF]
Operational Research, 2018 Stochastic gradient Hamiltonian Monte Carlo (SGHMC) is a variant of stochastic gradient with momentum where a controlled and properly scaled Gaussian noise is added to the stochastic gradients to steer the iterates towards a global minimum.
Xuefeng Gao +2 more
semanticscholar +1 more source