Physical Sciences › Computer Science › Artificial Intelligence
Stochastic Gradient Optimization Techniques
1.613 indexierte Paper
Dieses Unterthema und seine Hierarchie stammen aus der OpenAlex-Klassifikation, dem offenen Katalog der weltweiten wissenschaftlichen Forschung.
Monatliches Volumen — letzte 12 Monate
Neueste Paper
- A Stable Whitening Optimizer for Efficient Neural Network Training
Kevin Frans, Sergey Levine, Pieter Abbeel · 27. Oktober 2025
- Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
Daniel Kunin, Giovanni Luca Marchetti, Feng Chen, Dhruva Karkada, James B. Simon, Michael R. DeWeese, Surya Ganguli, Nina Miolane · 27. Oktober 2025
- Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness
Mojtaba Kolahdouzi, Hatice Gunes, Ali Etemad · 27. Oktober 2025
- Convergence of Stochastic Gradient Langevin Dynamics in the Lazy Training Regime
Noah Oberweis, Semih Cayci · 27. Oktober 2025
- Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
Hancheng Min, Zhihui Zhu, Ren\'e Vidal · 27. Oktober 2025
- From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD
Konstantinos Christopher Tsiolis, Alireza Mousavi-Hosseini, Murat A. Erdogdu · 27. Oktober 2025
- Global Dynamics of Heavy-Tailed SGDs in Nonconvex Loss Landscape: Characterization and Control
Xingyu Wang, Chang-Han Rhee · 27. Oktober 2025
- A Convergence Analysis of Adaptive Optimizers under Floating-point Quantization
Xuan Tang, Jichu Li, Difan Zou · 27. Oktober 2025