@misc{dl2-a04-1,
  title={Sharp Minima Can Generalize For Deep Nets},
  author={Laurent Dinh, Razvan Pascanu, Samy Bengio, Yoshua Bengio},
  year={2017},
  url={https://arxiv.org/abs/1703.04933}
}
@misc{dl2-a04-2,
  title={On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima},
  author={Nitish Shirish Keskar, Dheevatsa Mudigere, Jorge Nocedal, Mikhail Smelyanskiy, Ping Tak Peter Tang},
  year={2017},
  url={https://arxiv.org/abs/1609.04836}
}
@misc{dl2-a04-3,
  title={Sharpness-Aware Minimization for Efficiently Improving Generalization},
  author={Pierre Foret, Ariel Kleiner, Hossein Mobahi, Behnam Neyshabur},
  year={2021},
  url={https://arxiv.org/abs/2010.01412}
}
@misc{dl2-a04-4,
  title={Visualizing the Loss Landscape of Neural Nets},
  author={Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, Tom Goldstein},
  year={2018},
  url={https://arxiv.org/abs/1712.09913}
}
@misc{dl2-a04-5,
  title={Exploring Generalization in Deep Learning},
  author={Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, Nathan Srebro},
  year={2017},
  url={https://arxiv.org/abs/1706.08947}
}
@misc{dl2-a04-6,
  title={Fantastic Generalization Measures and Where to Find Them},
  author={Yiding Jiang, Behnam Neyshabur, Hossein Mobahi, Dilip Krishnan, Samy Bengio},
  year={2019},
  url={https://arxiv.org/abs/1912.02178}
}