HYBRID MACHINE LEARNING AND NUMERICAL METHODS FOR HIGH-DIMENSIONAL OPTIMIZATION PROBLEMS
SURESHREDDY KOMSANI
, PEDDAKAPU DASHARATHAM , YENDRU REVATHI
numerical methods, hybrid modelling, numerical techniques, high-dimensional, fluid dynamics.
ABSTRACT
Accompanying exact methods are numerical methods that include a deterministic synthesis of drift terms and a stochastic interpolation of diffusion terms with the purpose of increasing precision and stability and optimizing used computing time. The focus of this work is to consider composite numerical techniques for the approximation of SDEs with nonlinear coefficients in the drift and diffusion terms.While discretising and solving differential equations can be accomplished with the help of traditional numerical methods like finite difference, finite element, and spectral methods, neural networks, especially deep learning models, excel at learning complicated patterns and estimating solutions in high-dimensional spaces. In situations when precise analytical answers are unattainable or very difficult to get, hybrid techniques may improve the solution process in terms of accuracy, efficiency, and generalisability by combining various methods. Combining these two approaches improves the management of singularities, boundary conditions, and irregular geometries, all of which are common in real-world applications such as biological modelling and fluid dynamics.Ultimately, when the amount of samples in the data set is reduced, the generalization of the physics-related corrective model outperforms the purely data-driven model, which also demonstrates efficient applicability of the proposed hybrid modelling approach to problems where data is scarce.
"HYBRID MACHINE LEARNING AND NUMERICAL METHODS FOR HIGH-DIMENSIONAL OPTIMIZATION PROBLEMS", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.11, Issue 1, page no.b123-b130, January-2026, Available :https://ijsdr.org/papers/IJSDR2601113.pdf
Volume 11
Issue 1,
January-2026
Pages : b123-b130
Paper Reg. ID: IJSDR_306950
Published Paper Id: IJSDR2601113
Downloads: 000261
Research Area: Science All
Country: Kamareddy, Telangana, India
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave
