paper-with-me

홈 › Papers

Memorization in Deep Neural Networks: Does the Loss Function matter?

2021-07-21 · Deep Patel, P. S. Sastry

Deep Neural Networks, often owing to the overparameterization, are shown to be capable of exactly memorizing even randomly labelled data. Empirical studies have also shown that none of the standard regularization techniques mitigate such overfitting. We investigate whether the choice of the loss function can affect this memorization. We empirically show, with benchmark data sets MNIST and CIFAR-10, that a symmetric loss function, as opposed to either cross-entropy or squared error loss, results in significant improvement in the ability of the network to resist such overfitting. We then provide a formal definition for robustness to memorization and provide a theoretical explanation as to why the symmetric losses provide this robustness. Our results clearly bring out the role loss functions alone can play in this phenomenon of memorization.

📄 PDF Abstract BibTeX arXiv:2107.09957

Code (1)

dbp1994/masters_thesis_codes/tree/main/memorization_and_overparam 공식 구현

Tasks

Memorization

Similar Papers 제목 키워드 기반

Provable Separations between Memorization and Generalization in Diffusion Models

2025-11-05 · Zeqi Ye, Qijie Zhu, Molei Tao, Minshuo Chen arxiv

Diffusion models have achieved remarkable success across diverse domains, but they remain vulnerable to memorization -- reproducing training data rather than generating novel outputs. This not only limits their creative …

Large Loss Matters in Weakly Supervised Multi-Label Classification

2022-06-08 · CVPR 2022 1 · Youngwook Kim, Jae Myung Kim, Zeynep Akata, Jungwoo Lee

Weakly supervised multi-label classification (WSML) task, which is to learn a multi-label classification using partially observed labels per image, is becoming increasingly important due to its huge annotation cost. In t…

ClassificationMemorizationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION

Untrained neural networks can demonstrate memorization-independent abstract reasoning

2024-07-25 · Tomer Barak, Yonatan Loewenstein

The nature of abstract reasoning is a matter of debate. Modern artificial neural network (ANN) models, like large language models, demonstrate impressive success when tested on abstract reasoning problems. However, it ha…

MemorizationVisual Reasoning

Capacity Matters: a Proof-of-Concept for Transformer Memorization on Real-World Data

2025-06-17 · Anton Changalidis, Aki Härmä

This paper studies how the model architecture and data configurations influence the empirical memorization capacity of generative transformers. The models are trained using synthetic text datasets derived from the System…

Memorization

Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory

2024-05-14 · Xueyan Niu, Bo Bai, Lei Deng, Wei Han

Increasing the size of a Transformer does not always lead to enhanced performance. This phenomenon cannot be explained by the empirical scaling laws. Furthermore, the model's enhanced performance is closely associated wi…

Memorization