paper-with-me

Papers

The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks

2019-06-07 · NeurIPS 2019 12 · Ryo Karakida, Shotaro Akaho, Shun-ichi Amari

Normalization methods play an important role in enhancing the performance of deep learning while their theoretical understandings have been limited. To theoretically elucidate the effectiveness of normalization, we quantify the geometry of the parameter space determined by the Fisher information matrix (FIM), which also corresponds to the local shape of the loss landscape under certain conditions. We analyze deep neural networks with random initialization, which is known to suffer from a pathologically sharp shape of the landscape when the network becomes sufficiently wide. We reveal that batch normalization in the last layer contributes to drastically decreasing such pathological sharpness if the width and sample number satisfy a specific condition. In contrast, it is hard for batch normalization in the middle hidden layers to alleviate pathological sharpness in many settings. We also found that layer normalization cannot alleviate pathological sharpness either. Thus, we can conclude that batch normalization in the last layer significantly contributes to decreasing the sharpness induced by the FIM.

📄 PDF Abstract BibTeX arXiv:1906.02926

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction

2022-06-14 · Kaifeng Lyu, Zhiyuan Li, Sanjeev Arora

Normalization layers (e.g., Batch Normalization, Layer Normalization) were introduced to help with optimization difficulties in very deep nets, but they clearly also help generalization, even in not-so-deep nets. Motivat…

Normalization Layers Are All That Sharpness-Aware Minimization Needs

2023-06-07 · NeurIPS 2023 11 · Maximilian Mueller, Tiffany Vlaar, David Rolnick, Matthias Hein

Sharpness-aware minimization (SAM) was proposed to reduce sharpness of minima and has been shown to enhance generalization performance in various settings. In this work we show that perturbing only the affine normalizati…

All

Towards the Spectral bias Alleviation by Normalizations in Coordinate Networks

2024-07-25 · Zhicheng Cai, Hao Zhu, Qiu Shen, Xinran Wang 외

Representing signals using coordinate networks dominates the area of inverse problems recently, and is widely applied in various scientific computing tasks. Still, there exists an issue of spectral bias in coordinate net…

Image CompressionNovel View Synthesis

The Crucial Role of Normalization in Sharpness-Aware Minimization

2023-05-24 · NeurIPS 2023 11

Sharpness-Aware Minimization (SAM) is a recently proposed gradient-based optimizer (Foret et al., ICLR 2021) that greatly improves the prediction performance of deep neural networks. Consequently, there has been a surge …

Exploring Generalization in Deep Learning

2017-06-27 · NeurIPS 2017 12 · Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, Nathan Srebro

With a goal of understanding what drives generalization in deep networks, we consider several recently suggested explanations, including norm-based control, sharpness and robustness. We study how these measures can ensur…

Deep Learning