paper-with-me

Papers

Geometric Regularization from Overparameterization

2022-02-18 · Nicholas J. Teague

The volume of the distribution of weight sets associated with a loss value may be the source of implicit regularization from overparameterization due to the phenomenon of contracting volume with increasing dimensions for geometric figures demonstrated by hyperspheres. We introduce the geometric regularization conjecture and extract to an explanation for the double descent phenomenon by considering a similar property resulting from shrinking intrinsic dimensionality of the distribution of potential weight set updates available along training path, where if that distribution retracts across a volume verses dimensionality curve peak when approaching the global minima we could expect geometric regularization to re-emerge. We illustrate how data fidelity representational complexity may influence model capacity double descent interpolation thresholds. The existence of epoch and model capacity double descent curves originating from different geometric forms may imply universality of closed n-manifolds having dimensionally adjusted n-sphere volumetric correspondence.

📄 PDF Abstract BibTeX arXiv:2202.09276

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

High-Dimensional Linear Regression via Implicit Regularization

2019-03-22 · Peng Zhao, Yun Yang, Qiao-Chu He

Many statistical estimators for high-dimensional linear regression are M-estimators, formed through minimizing a data-dependent square loss function plus a regularizer. This work considers a new class of estimators impli…

regressionVocal Bursts Intensity Prediction

Sample Complexity and Overparameterization Bounds for Temporal Difference Learning with Neural Network Approximation

2021-03-02 · Semih Cayci, Siddhartha Satpathi, Niao He, R. Srikant

In this paper, we study the dynamics of temporal difference learning with neural network-based value function approximation over a general state space, namely, \emph{Neural TD learning}. We consider two practically used …

Critical Influence of Overparameterization on Sharpness-aware Minimization

2023-11-29 · Sungbin Shin, Dongyeop Lee, Maksym Andriushchenko, Namhoon Lee

Sharpness-Aware Minimization (SAM) has attracted considerable attention for its effectiveness in improving generalization in deep neural network training by explicitly minimizing sharpness in the loss landscape. Its succ…

Attribute

The Role of Symmetry in Optimizing Overparameterized Networks

2026-04-28 · Kusha Sareen, Mohammad Pedramfar, Sékou-Oumar Kaba, Mehran Shakerinava 외 arxiv

Overparameterization is central to the success of deep learning, yet the mechanisms by which it improves optimization remain incompletely understood. We analyze weight-space symmetries in neural networks and show that ov…

Geometry and Local Recovery of Global Minima of Two-layer Neural Networks at Overparameterization

2023-09-01 · Leyang Zhang, Yaoyu Zhang, Tao Luo

Under mild assumptions, we investigate the geometry of the loss landscape for two-layer neural networks in the vicinity of global minima. Utilizing novel techniques, we demonstrate: (i) how global minima with zero genera…