Strong Gaussian Approximation of Constant-Learning-Rate SGD: Bias and Trajectory Inference
arXiv:2610.14567v1 Announce Type: new Abstract: This paper develops strong Gaussian approximations (KMT type) for constant learning rate stochastic gradient descent (SGD). We work with heavy tailed noise and assume that the number of iterates grows and the learning rate shrinks simultaneously. Our…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-14 04:00 · arXiv stat.ML
Strong Gaussian Approximation of Constant-Learning-Rate SGD: Bias and Trajectory Inference