No article text was recorded for this version.
learning rate to batch size ratio
Version 2 of 211 papers18 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize
- Blog: Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent
- Blog: Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers
- Blog: Multiplicative Noise and Heavy Tails in Stochastic Optimization
- Blog: The Heavy-Tail Phenomenon in SGD
- Blog: Emergence of heavy tails in homogenized stochastic gradient descent
- Blog: Understanding Short-Range Memory Effects in Deep Neural Networks
- Blog: Heavy-Tail Phenomenon in Decentralized SGD
- Blog: Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers
- Blog: Stochastic Gradient and Langevin Processes
- Blog: The Heavy-Tail Phenomenon in SGD
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_learning_rate_to_batch_size_ratio_9451055c,
title = {learning rate to batch size ratio},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/learning-rate-to-batch-size-ratio/rdr_9451055ce5a4459a9bdef02b20fc4b53},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_learning_rate_to_batch_size_ratio_9451055c_v2,
title = {learning rate to batch size ratio},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/learning-rate-to-batch-size-ratio/rdr_9451055ce5a4459a9bdef02b20fc4b53/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}