Yu Feng

The inverse variance–flatness relation in stochastic gradient descent is critical for finding flat minima

Y. Tu, Yu Feng, 2021, Proceedings of the National Academy of Sciences.

The activity-weight duality in feed forward neural networks: The geometric determinants of generalization

Yuhai Tu, Yu Feng, 2022, ArXiv.

Phases of learning dynamics in artificial neural networks in the absence or presence of mislabeled data

Yuhai Tu, Yu Feng, Y. Tu, 2021, Mach. Learn. Sci. Technol..

Phases of learning dynamics in artificial neural networks: with or without mislabeled data pdf

Yu Feng, Yuhai Tu, Y. Tu, 2021, ArXiv.

How neural networks find generalizable solutions: Self-tuned annealing in deep learning pdf

Yu Feng, Yuhai Tu, Y. Tu, 2020, ArXiv.

Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent pdf

Brian Kingsbury, Mingrui Liu, Wei Zhang, 2021, ArXiv.