paper-with-me

홈 › Papers

Understanding How Over-Parametrization Leads to Acceleration: A case of learning a single teacher neuron

2020-10-04 · Jun-Kun Wang, Jacob Abernethy

Over-parametrization has become a popular technique in deep learning. It is observed that by over-parametrization, a larger neural network needs a fewer training iterations than a smaller one to achieve a certain level of performance -- namely, over-parametrization leads to acceleration in optimization. However, despite that over-parametrization is widely used nowadays, little theory is available to explain the acceleration due to over-parametrization. In this paper, we propose understanding it by studying a simple problem first. Specifically, we consider the setting that there is a single teacher neuron with quadratic activation, where over-parametrization is realized by having multiple student neurons learn the data generated from the teacher neuron. We provably show that over-parametrization helps the iterate generated by gradient descent to enter the neighborhood of a global optimal solution that achieves zero testing error faster. On the other hand, we also point out an issue regarding the necessity of over-parametrization and study how the scaling of the output neurons affects the convergence time.

📄 PDF Abstract BibTeX arXiv:2010.01637

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Noether: The More Things Change, the More Stay the Same

2021-04-12 · Grzegorz Głuch, Rüdiger Urbanke

Symmetries have proven to be important ingredients in the analysis of neural networks. So far their use has mostly been implicit or seemingly coincidental. We undertake a systematic study of the role that symmetry plays.…

Data Augmentation

Functional Acceleration for Policy Mirror Descent

2024-07-23 · Veronica Chelu, Doina Precup

We apply functional acceleration to the Policy Mirror Descent (PMD) general family of algorithms, which cover a wide range of novel and fundamental methods in Reinforcement Learning (RL). Leveraging duality, we propose a…

Reinforcement Learning (RL)

(Deep) Generative Geodesics

2024-07-15 · Beomsu Kim, Michael Puthawala, Jong Chul Ye, Emanuele Sansone

In this work, we propose to study the global geometrical properties of generative models. We introduce a new Riemannian metric to assess the similarity between any two data points. Importantly, our metric is agnostic to …

Data Visualization

Theory of overparametrization in quantum neural networks

2021-09-23 · Martin Larocca, Nathan Ju, Diego García-Martín, Patrick J. Coles 외

The prospect of achieving quantum advantage with Quantum Neural Networks (QNNs) is exciting. Understanding how QNN properties (e.g., the number of parameters $M$) affect the loss landscape is crucial to the design of sca…

What causes the test error? Going beyond bias-variance via ANOVA

2020-10-11 · Licong Lin, Edgar Dobriban

Modern machine learning methods are often overparametrized, allowing adaptation to the data at a fine level. This can seem puzzling; in the worst case, such models do not need to generalize. This puzzle inspired a great …