The Efficacy of L 1s Regularization in Two-Layer Neural Networks.

Gen Li, Yuantao Gu, Jie Ding

Type: Preprint

Publication Date: 2020-10-02

Citations: 1

Locations

arXiv (Cornell University) - View

Similar Works

Action	Title	Year	Authors
+	The Efficacy of $L_1$ Regularization in Two-Layer Neural Networks	2020	Gen Li Yuantao Gu Jie Ding
+	Nonasymptotic theory for two-layer neural networks: Beyond the bias-variance trade-off	2021	Huiyuan Wang Lin Wei
+	Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint	2020	Jimmy Ba Murat A. Erdogdu Taiji Suzuki Denny Wu Tianzong Zhang
+ PDF Chat	A General Framework of the Consistency for Large Neural Networks	2024	Haoran Zhan Yingcun Xia
+	Intrinsic dimensionality and generalization properties of the $\mathcal{R}$-norm inductive bias	2022	Clayton Sanford Navid Ardeshir Daniel Hsu
+	Empirical Risk Landscape Analysis for Understanding Deep Neural Networks	2018	Pan Zhou Jiashi Feng
+	Rethinking Bias-Variance Trade-off for Generalization of Neural Networks	2020	Zitong Yang Yaodong Yu Chong You Jacob Steinhardt Yi Ma
+	A Priori Estimates for Two-layer Neural Networks	2018	E Weinan Chao Ma Lei Wu
+	Theoretical Issues in Deep Networks: Approximation, Optimization and Generalization	2019	Tomaso Poggio Andrzej Banburski Qianli Liao
+ PDF Chat	Error Bounds of Supervised Classification from Information-Theoretic Perspective	2024	Binchuan Qi Wei Gong Li Li
+	Approximation and Estimation for High-Dimensional Deep Learning Networks	2018	Andrew R. Barron Jason M. Klusowski
+	A spectral-based analysis of the separation between two-layer neural networks and linear methods	2021	Lei Wu Jihao Long
+	Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization	2020	Benjamin Aubin Florent Krząkała Yue M. Lu Lenka Zdeborová
+	Analysis of the expected $L_2$ error of an over-parametrized deep neural network estimate learned by gradient descent without regularization	2023	Selina Drews Michael Köhler
+ PDF Chat	Can Shallow Neural Networks Beat the Curse of Dimensionality? A Mean Field Training Perspective	2020	Stephan Wojtowytsch E Weinan
+ PDF Chat	<i>A priori</i> estimates of the population risk for two-layer neural networks	2019	E Weinan Chao Ma Lei Wu
+ PDF Chat	Risk Bounds on MDL Estimators for Linear Regression Models with Application to Simple ReLU Neural Networks	2024	Yoshinari Takeishi Jun’ichi Takeuchi
+	With Greater Distance Comes Worse Performance: On the Perspective of Layer Utilization and Model Generalization	2022	James Z. Wang Cheng-Lin Yang
+	Statistical learning by sparse deep neural networks	2023	Felix Abramovich
+ PDF Chat	Stochastic Gradient Descent for Two-layer Neural Networks	2024	Dinghao Cao Zheng-Chu Guo Lei Shi

Works That Cite This (1)

Action	Title	Year	Authors
+	The Rate of Convergence of Variation-Constrained Deep Neural Networks	2021	Gen Li Yuantao Gu Jie Ding

Works Cited by This (16)

Action	Title	Year	Authors
+ PDF Chat	Information-theoretic determination of minimax rates of convergence	1999	Yuhong Yang Andrew R. Barron
+	Beating the Perils of Non-Convexity: Guaranteed Training of Neural Networks using Tensor Methods	2015	Majid Janzamin Hanie Sedghi Anima Anandkumar
+	Tensor decompositions for learning latent variable models	2014	Animashree Anandkumar Rong Ge Daniel Hsu Sham M. Kakade Matus Telgarsky
+ PDF Chat	Group sparse regularization for deep neural networks	2017	Simone Scardapane Danilo Comminiello Amir Hussain Aurelio Uncini
+	Learning Structured Sparsity in Deep Neural Networks	2016	Wei Wen Chunpeng Wu Yandan Wang Yiran Chen Hai Li
+	A Survey of Model Compression and Acceleration for Deep Neural Networks	2017	Yu Cheng Duo Wang Pan Zhou Tao Zhang
+	Size-Independent Sample Complexity of Neural Networks	2017	Noah Golowich Alexander Rakhlin Ohad Shamir
+	On the Connection Between Learning Two-Layers Neural Networks and Tensor Decomposition	2018	Marco Mondelli Andrea Montanari
+ PDF Chat	Model Selection Techniques: An Overview	2018	Jie Ding Vahid Tarokh Yuhong Yang
+	Complexity, Statistical Risk, and Metric Entropy of Deep Nets Using Total Path Variation	2019	Andrew R. Barron Jason M. Klusowski