Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path

• URL: http://arxiv.org/abs/2106.02073v1
• Date: Thu, 3 Jun 2021 18:31:41 GMT
• Title: Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path
• Authors: X.Y. Han, Vardan Papyan, David L. Donoho
• Abstract summary: Recent work discovered a phenomenon called Neural Collapse (NC) that occurs pervasively in today's deep net training paradigm. In this work, we establish the empirical reality of MSE-NC by reporting experimental observations for three prototypical networks and five canonical datasets. We produce closed-form dynamics that predict full Neural Collapse in an unconstrained features model.
• Score: 11.181590224799224
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent work [Papyan, Han, and Donoho, 2020] discovered a phenomenon called Neural Collapse (NC) that occurs pervasively in today's deep net training paradigm of driving cross-entropy loss towards zero. In this phenomenon, the last-layer features collapse to their class-means, both the classifiers and class-means collapse to the same Simplex Equiangular Tight Frame (ETF), and the behavior of the last-layer classifier converges to that of the nearest-class-mean decision rule. Since then, follow-ups-such as Mixon et al. [2020] and Poggio and Liao [2020a,b]-formally analyzed this inductive bias by replacing the hard-to-study cross-entropy by the more tractable mean squared error (MSE) loss. But, these works stopped short of demonstrating the empirical reality of MSE-NC on benchmark datasets and canonical networks-as had been done in Papyan, Han, and Donoho [2020] for the cross-entropy loss. In this work, we establish the empirical reality of MSE-NC by reporting experimental observations for three prototypical networks and five canonical datasets with code for reproducing NC. Following this, we develop three main contributions inspired by MSE-NC. Firstly, we show a new theoretical decomposition of the MSE loss into (A) a term assuming the last-layer classifier is exactly the least-squares or Webb and Lowe [1990] classifier and (B) a term capturing the deviation from this least-squares classifier. Secondly, we exhibit experiments on canonical datasets and networks demonstrating that, during training, term-(B) is negligible. This motivates a new theoretical construct: the central path, where the linear classifier stays MSE-optimal-for the given feature activations-throughout the dynamics. Finally, through our study of continually renormalized gradient flow along the central path, we produce closed-form dynamics that predict full Neural Collapse in an unconstrained features model.

Related papers

• Progressive Feedforward Collapse of ResNet Training [7.824226954174748]
  We study the relationship of the last-layer features to the data and intermediate layers during training. We derive a model for the well-trained ResNet according to that ResNet with weight decay approximates the geodesic curve in Wasserstein space at the terminal phase. This study extends NC to PFC to model the collapse phenomenon of intermediate layers and its dependence on the input data, shedding light on the theoretical understanding of ResNet in classification problems.
  arXiv  Detail & Related papers  (2024-05-02T03:48:08Z)
• Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Feature Model [25.61363481391964]
  We show that when the training dataset is class-imbalanced, some Neural Collapse (NC) properties will no longer be true. In this paper, we generalize NC to imbalanced regime for cross-entropy loss under the unconstrained ReLU feature model. We find that the weights are aligned to the scaled and centered class-means with scaling factors depend on the number of training samples of each class.
  arXiv  Detail & Related papers  (2024-01-04T04:53:31Z)
• Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning [120.53458753007851]
  Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. We deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse. We propose a neural collapse inspired framework for FSCIL. Experiments on the miniImageNet, CUB-200, and CIFAR-100 datasets demonstrate that our proposed framework outperforms the state-of-the-art performances.
  arXiv  Detail & Related papers  (2023-02-06T18:39:40Z)
• Understanding Imbalanced Semantic Segmentation Through Neural Collapse [81.89121711426951]
  We show that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes. We introduce a regularizer on feature centers to encourage the network to learn features closer to the appealing structure. Our method ranks 1st and sets a new record on the ScanNet200 test leaderboard.
  arXiv  Detail & Related papers  (2023-01-03T13:51:51Z)
• Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data [12.225207401994737]
  We show that complex systems with massive amounts of parameters exhibit the same structural properties when training until convergence. In particular, it has been observed that the last-layer features collapse to their class-means. Our results demonstrate the convergence of the last-layer features and classifiers to a geometry consisting of vectors.
  arXiv  Detail & Related papers  (2023-01-01T16:29:56Z)
• Improved Convergence Guarantees for Shallow Neural Networks [91.3755431537592]
  We prove convergence of depth 2 neural networks, trained via gradient descent, to a global minimum. Our model has the following features: regression with quadratic loss function, fully connected feedforward architecture, RelU activations, Gaussian data instances, adversarial labels. They strongly suggest that, at least in our model, the convergence phenomenon extends well beyond the NTK regime''
  arXiv  Detail & Related papers  (2022-12-05T14:47:52Z)
• Do We Really Need a Learnable Classifier at the End of Deep Neural Network? [118.18554882199676]
  We study the potential of learning a neural network for classification with the classifier randomly as an ETF and fixed during training. Our experimental results show that our method is able to achieve similar performances on image classification for balanced datasets.
  arXiv  Detail & Related papers  (2022-03-17T04:34:28Z)
• On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features [38.05002597295796]
  Collapselayers collapse to the vertices of a Simplex Equiangular Tight Frame (ETF) An intriguing empirical phenomenon has been widely observed in the last-layers and features of deep neural networks for tasks.
  arXiv  Detail & Related papers  (2022-03-02T17:00:18Z)
• Extended Unconstrained Features Model for Exploring Deep Neural Collapse [59.59039125375527]
  Recently, a phenomenon termed "neural collapse" (NC) has been empirically observed in deep neural networks. Recent papers have shown that minimizers with this structure emerge when optimizing a simplified "unconstrained features model" In this paper, we study the UFM for the regularized MSE loss, and show that the minimizers' features can be more structured than in the cross-entropy case.
  arXiv  Detail & Related papers  (2022-02-16T14:17:37Z)
• Prevalence of Neural Collapse during the terminal phase of deep learning training [7.031848258307718]
  Modern practice for training classification deepnets involves a Terminal Phase of Training (TPT) During TPT, the training error stays effectively zero while training loss is pushed towards zero. The symmetric and very simple geometry induced by the TPT confers important benefits, including better performance, better generalization, and better interpretability.
  arXiv  Detail & Related papers  (2020-08-18T23:12:54Z)
• Kernel and Rich Regimes in Overparametrized Models [69.40899443842443]
  We show that gradient descent on overparametrized multilayer networks can induce rich implicit biases that are not RKHS norms. We also demonstrate this transition empirically for more complex matrix factorization models and multilayer non-linear networks.
  arXiv  Detail & Related papers  (2020-02-20T15:43:02Z)

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.