2 papers
stat.ML2026
High-Probability Guarantees for SGD under -Heavy-Tailed Gradient Noise
Qijun Tong, Masahiro Ikeda, Ryota Kawasumi
Stochastic gradient descent (SGD) is widely used to train machine learning models, but subsampling the training data introduces noise into its updates. The strength and applicabili…
math.ST2020
Entropy-regularized optimal transport on multivariate normal and q-normal distributions
Qijun Tong, Kei Kobayashi
The distance and divergence of the probability measures play a central role in statistics, machine learning, and many other related fields. The Wasserstein distance has received mu…