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

• URL: http://arxiv.org/abs/2107.09957v2
• Date: Thu, 22 Jul 2021 05:36:24 GMT
• Title: Memorization in Deep Neural Networks: Does the Loss Function matter?
• Authors: Deep Patel and P.S. Sastry
• Abstract summary: We show 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. Our results clearly bring out the role loss functions alone can play in this phenomenon of memorization.
• Score: 1.71982924656402
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Semantic Loss Functions for Neuro-Symbolic Structured Prediction [74.18322585177832]
  We discuss the semantic loss, which injects knowledge about such structure, defined symbolically, into training. It is agnostic to the arrangement of the symbols, and depends only on the semantics expressed thereby. It can be combined with both discriminative and generative neural models.
  arXiv  Detail & Related papers  (2024-05-12T22:18:25Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• Regularization, early-stopping and dreaming: a Hopfield-like setup to address generalization and overfitting [0.0]
  We look for optimal network parameters by applying a gradient descent over a regularized loss function. Within this framework, the optimal neuron-interaction matrices correspond to Hebbian kernels revised by a reiterated unlearning protocol.
  arXiv  Detail & Related papers  (2023-08-01T15:04:30Z)
• Noise-Robust Loss Functions: Enhancing Bounded Losses for Large-Scale Noisy Data Learning [0.0]
  Large annotated datasets inevitably contain noisy labels, which poses a major challenge for training deep neural networks as they easily memorize the labels. Noise-robust loss functions have emerged as a notable strategy to counteract this issue, but it remains challenging to create a robust loss function which is not susceptible to underfitting. We propose a novel method denoted as logit bias, which adds a real number $epsilon$ to the logit at the position of the correct class.
  arXiv  Detail & Related papers  (2023-06-08T18:38:55Z)
• Regression as Classification: Influence of Task Formulation on Neural Network Features [16.239708754973865]
  Neural networks can be trained to solve regression problems by using gradient-based methods to minimize the square loss. practitioners often prefer to reformulate regression as a classification problem, observing that training on the cross entropy loss results in better performance. By focusing on two-layer ReLU networks, we explore how the implicit bias induced by gradient-based optimization could partly explain the phenomenon.
  arXiv  Detail & Related papers  (2022-11-10T15:13:23Z)
• Evaluating the Impact of Loss Function Variation in Deep Learning for Classification [0.0]
  The loss function is arguably among the most important hyper parameters for a neural network. We consider deep neural networks in a supervised classification setting and analyze the impact the choice of loss function has onto the training result. While certain loss functions perform suboptimally, our work empirically shows that under-represented losses can outperform the State-of-the-Art choices significantly.
  arXiv  Detail & Related papers  (2022-10-28T09:10:10Z)
• On Codomain Separability and Label Inference from (Noisy) Loss Functions [11.780563744330038]
  We introduce the notion of codomain separability to study the necessary and sufficient conditions under which label inference is possible from any (noisy) loss function values. We show that for many commonly used loss functions, including multiclass cross-entropy with common activation functions and some Bregman divergence-based losses, it is possible to design label inference attacks for arbitrary noise levels.
  arXiv  Detail & Related papers  (2021-07-07T05:29:53Z)
• Asymmetric Loss Functions for Learning with Noisy Labels [82.50250230688388]
  We propose a new class of loss functions, namely textitasymmetric loss functions, which are robust to learning with noisy labels for various types of noise. Experimental results on benchmark datasets demonstrate that asymmetric loss functions can outperform state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-06-06T12:52:48Z)
• And/or trade-off in artificial neurons: impact on adversarial robustness [91.3755431537592]
  Presence of sufficient number of OR-like neurons in a network can lead to classification brittleness and increased vulnerability to adversarial attacks. We define AND-like neurons and propose measures to increase their proportion in the network. Experimental results on the MNIST dataset suggest that our approach holds promise as a direction for further exploration.
  arXiv  Detail & Related papers  (2021-02-15T08:19:05Z)
• A Symmetric Loss Perspective of Reliable Machine Learning [87.68601212686086]
  We review how a symmetric loss can yield robust classification from corrupted labels in balanced error rate (BER) minimization. We demonstrate how the robust AUC method can benefit natural language processing in the problem where we want to learn only from relevant keywords.
  arXiv  Detail & Related papers  (2021-01-05T06:25:47Z)
• Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation [56.343646789922545]
  We propose to automate the design of metric-specific loss functions by searching differentiable surrogate losses for each metric. Experiments on PASCAL VOC and Cityscapes demonstrate that the searched surrogate losses outperform the manually designed loss functions consistently.
  arXiv  Detail & Related papers  (2020-10-15T17:59:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.