paper-with-me

홈 › Papers

Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity

2018-10-17 · NeurIPS 2019 12 · Chulhee Yun, Suvrit Sra, Ali Jadbabaie

We study finite sample expressivity, i.e., memorization power of ReLU networks. Recent results require $N$ hidden nodes to memorize/interpolate arbitrary $N$ data points. In contrast, by exploiting depth, we show that 3-layer ReLU networks with $\Omega(\sqrt{N})$ hidden nodes can perfectly memorize most datasets with $N$ points. We also prove that width $\Theta(\sqrt{N})$ is necessary and sufficient for memorizing $N$ data points, proving tight bounds on memorization capacity. The sufficiency result can be extended to deeper networks; we show that an $L$-layer network with $W$ parameters in the hidden layers can memorize $N$ data points if $W = \Omega(N)$. Combined with a recent upper bound $O(WL\log W)$ on VC dimension, our construction is nearly tight for any fixed $L$. Subsequently, we analyze memorization capacity of residual networks under a general position assumption; we prove results that substantially reduce the known requirement of $N$ hidden nodes. Finally, we study the dynamics of stochastic gradient descent (SGD), and show that when initialized near a memorizing global minimum of the empirical risk, SGD quickly finds a nearby point with much smaller empirical risk.

📄 PDF Abstract BibTeX arXiv:1810.07770

Code (0)

등록된 구현이 없습니다.

Tasks

Memorization

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

ReLU Networks as Surrogate Models in Mixed-Integer Linear Programs

2019-07-06 · Bjarne Grimstad, Henrik Andersson

We consider the embedding of piecewise-linear deep neural networks (ReLU networks) as surrogate models in mixed-integer linear programming (MILP) problems. A MILP formulation of ReLU networks has recently been applied by…

The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets

2025-10-28 · Yujun Kim, Chaewon Moon, Chulhee Yun arxiv

We study the parameter complexity of robust memorization for $\mathrm{ReLU}$ networks: the number of parameters required to interpolate any given dataset with $ε$-separation between differently labeled points, while ensu…

Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization

2022-05-20 · Simone Bombari, Mohammad Hossein Amani, Marco Mondelli

The Neural Tangent Kernel (NTK) has emerged as a powerful tool to provide memorization, optimization and generalization guarantees in deep neural networks. A line of work has studied the NTK spectrum for two-layer and de…

MemorizationOpen-Ended Question Answering

Tight Worst-Case Bounds for the Smallest Eigenvalue of ReLU NTK Gram Matrices

2026-08-04 · Zhao Song arxiv

For $n$ unit vectors $x_1,\ldots,x_n \in \mathbb{R}^d$, we study the continuous ReLU derivative Gram matrix $H$, whose entries are obtained by averaging pairwise gated inner products over a standard Gaussian direction. W…

Alternative Function Approximation Parameterizations for Solving Games: An Analysis of $f$-Regression Counterfactual Regret Minimization

2019-12-06 · Ryan D'Orazio, Dustin Morrill, James R. Wright, Michael Bowling

Function approximation is a powerful approach for structuring large decision problems that has facilitated great achievements in the areas of reinforcement learning and game playing. Regression counterfactual regret mini…

counterfactualregressionreinforcement-learningReinforcement Learning+1