GeoAdaLer: Geometric Insights into Adaptive Stochastic Gradient Descent Algorithms

The Adam optimization method has achieved remarkable success in addressing contemporary challenges in stochastic optimization. This method falls within the realm of adaptive sub-gradient techniques, yet the underlying geometric principles guiding its performance have remained shrouded in mystery, and have long confounded researchers. In this paper, we introduce GeoAdaLer (Geometric Adaptive Learner), a novel adaptive learning method for stochastic gradient descent optimization, which draws from the geometric properties of the optimization landscape. Beyond emerging as a formidable contender, the proposed method extends the concept of adaptive learning by introducing a geometrically inclined approach that enhances the interpretability and effectiveness in complex optimization scenarios

@article{eleh2025_2405.16255,
  title={ GeoAdaLer: Geometric Insights into Adaptive Stochastic Gradient Descent Algorithms },
  author={ Chinedu Eleh and Masuzyo Mwanza and Ekene Aguegboh and Hans-Werner van Wyk },
  journal={arXiv preprint arXiv:2405.16255},
  year={ 2025 }
}