LyAm: Robust Non-Convex Optimization for Stable Learning in Noisy Environments
Not on the map. Why?
Abstract (arXiv)
Training deep neural networks, particularly in computer vision tasks, often suffers from noisy gradients and unstable convergence, which hinder performance and generalization. In this paper, we propose LyAm, a novel optimizer that integrates Adam's adaptive moment estimation with Lyapunov-based stability mechanisms. LyAm dynamically adjusts the learning rate using Lyapunov stability theory to enhance convergence robustness and mitigate training noise. We provide a rigorous theoretical framework proving the convergence guarantees of LyAm in complex, non-convex settings. Extensive experiments on like as CIFAR-10 and CIFAR-100 show that LyAm consistently outperforms state-of-the-art optimizers in terms of accuracy, convergence speed, and stability, establishing it as a strong candidate for robust deep learning optimization.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 48 references that are in the map. First posted on arXiv 15 Jul 2025.
Builds on
24 of 48 references.
References · 24
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2013Intriguing properties of neural networkscited by 5,155
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
- 2015Fast R-CNNcited by 2,933
- 2016Understanding deep learning requires rethinking generalizationcited by 1,674
- 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
- 2016Optimization Methods for Large-Scale Machine Learningcited by 1,150
- 2018Robustness May Be at Odds with Accuracycited by 880
12 more
- 2019On the Convergence of Adam and Beyondcited by 841
- 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
- 2020AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradientscited by 283
- 2022Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Modelscited by 174
- 2017Deep Learning is Robust to Massive Label Noisecited by 165
- 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 154
- 2022Robust Training under Label Noise by Over-parameterizationcited by 93
- 2020Robust Deep Reinforcement Learning through Adversarial Losscited by 75
- 2020Viewmaker Networks: Learning Views for Unsupervised Representation Learningcited by 48
- 2018Robust Graph Learning from Noisy Datacited by 34
- 2021Adversarial example generation with AdaBelief Optimizer and Crop Invariancecited by 12
- 2022Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learningcited by 7
Built on by
Citing papers per year: 2026: 1.
1 paper.