SGDR: Stochastic Gradient Descent with Warm Restarts and Cosine Annealing learning rate schedule engine.
-
Updated
Sep 10, 2026 - Python
#
learning-rate-schedule
Here are 6 public repositories matching this topic...
SGDR: Stochastic Gradient Descent with Warm Restarts and Cosine Annealing learning rate schedule engine.
-
Updated
Sep 10, 2026 - Python
Negative result paper: the King Wen sequence has genuine anti-habituation statistical properties (confirmed via Monte Carlo against 100k baselines) but does not improve neural network training. Experiments on NVIDIA RTX 2060 (PyTorch) and Apple Silicon (MLX).
neural-network reproducible-research monte-carlo pytorch mlx i-ching king-wen apple-silicon negative-result learning-rate-schedule
-
Updated
Jun 25, 2026 - TeX
A hands-on experimental lab comparing gradient descent variants, learning rate decay strategies, and optimization behaviors.
python machine-learning optimization gradient-descent experiments stochastic-gradient-descent learning-rate-schedule
-
Updated
Dec 9, 2025 - Jupyter Notebook
A trust-region framework for moment estimation
neural-networks adam filter-design sgd-optimizer sgd-momentum filtering-algorithm trust-region-optimization large-language-models moment-estimation learning-rate-schedule
-
Updated
Aug 24, 2026 - Python
Learning-rate schedules from boundary-value constrained trust-region problems.
learning deep-learning optimizer energy-minimization step-size learning-rate-decay boundary-value-problem learning-rate-scheduling learning-rate-warmup trust-region-methods stochastic-gradient-method learning-rate-scheduler learning-rate-schedule
-
Updated
Sep 8, 2026 - Python
Add this topic to your repo
To associate your repository with the learning-rate-schedule topic, visit your repo's landing page and select "manage topics."