paper-with-me

Papers

Memorization in Overparameterized Autoencoders

2018-10-16 · ICML Workshop Deep_Phenomen 2019 6 · Adityanarayanan Radhakrishnan, Karren Yang, Mikhail Belkin, Caroline Uhler

The ability of deep neural networks to generalize well in the overparameterized regime has become a subject of significant research interest. We show that overparameterized autoencoders exhibit memorization, a form of inductive bias that constrains the functions learned through the optimization process to concentrate around the training examples, although the network could in principle represent a much larger function class. In particular, we prove that single-layer fully-connected autoencoders project data onto the (nonlinear) span of the training examples. In addition, we show that deep fully-connected autoencoders learn a map that is locally contractive at the training examples, and hence iterating the autoencoder results in convergence to the training examples. Finally, we prove that depth is necessary and provide empirical evidence that it is also sufficient for memorization in convolutional autoencoders. Understanding this inductive bias may shed light on the generalization properties of overparametrized deep neural networks that are currently unexplained by classical statistical theory.

📄 PDF Abstract BibTeX arXiv:1810.10333

Code (0)

등록된 구현이 없습니다.

Tasks

Inductive BiasMemorization

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Overparameterized Neural Networks Implement Associative Memory

2019-09-26 · Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

Identifying computational mechanisms for memorization and retrieval of data is a long-standing problem at the intersection of machine learning and neuroscience. Our main finding is that standard overparameterized deep ne…

MemorizationRetrieval

How Much Training Data is Memorized in Overparameterized Autoencoders? An Inverse Problem Perspective on Memorization Evaluation

2023-10-04 · Koren Abitbul, Yehuda Dar

Overparameterized autoencoder models often memorize their training data. For image data, memorization is often examined by using the trained autoencoder to recover missing regions in its training images (that were used o…

MemorizationRetrieval

Overparameterized Neural Networks Can Implement Associative Memory

2019-09-25 · Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

Identifying computational mechanisms for memorization and retrieval is a long-standing problem at the intersection of machine learning and neuroscience. In this work, we demonstrate empirically that overparameterized de…

MemorizationRetrieval

Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models

2025-05-22 · Alessandro Favero, Antonio Sclocchi, Matthieu Wyart

Diffusion probabilistic models have become a cornerstone of modern generative AI, yet the mechanisms underlying their generalization remain poorly understood. In fact, if these models were perfectly minimizing their trai…

Memorization

Associative Memory in Iterated Overparameterized Sigmoid Autoencoders

2020-06-30 · ICML 2020 1 · Yibo Jiang, Cengiz Pehlevan

Recent work showed that overparameterized autoencoders can be trained to implement associative memory via iterative maps, when the trained input-output Jacobian of the network has all of its eigenvalue norms strictly bel…

Learning Theoryregression