@misc{Chen_Hao_The,
 author={Chen, Hao and Mo, Zhanfeng and Yang, Zhouwang},
 howpublished={online},
 publisher={Zielona Góra: Uniwersytet Zielonogórski},
 language={eng},
 abstract={Recent works have developed model complexity based and algorithm based generalization error bounds to explain how stochastic gradient descent (SGD) methods help over-parameterized models generalize better. However, previous works are limited by their scope of analysis and fail to provide comprehensive explanations. In this paper, we propose a novel Gaussian approximation framework to establish generalization error bounds for the U-SGD family, which is a class of SGD with asymptotically unbiased and uniformly bounded gradient noise. We study U-SGD dynamics, and we show both theoretically and numerically that the limiting model parameter distribution tends to be Gaussian, even when the original gradient noise is non-Gaussian.},
 type={artykuł},
 title={The generalization error bound for a stochastic gradient descent family via a Gaussian approximation method},
 keywords={stochastic gradient descent, Gaussian approximation, KL-divergence, generalization bounds},
}