Three Mechanisms of Feature Learning in a Linear Network

• URL: http://arxiv.org/abs/2401.07085v3
• Date: Fri, 21 Feb 2025 11:50:09 GMT
• Title: Three Mechanisms of Feature Learning in a Linear Network
• Authors: Yizhou Xu, Liu Ziyin,
• Abstract summary: We present an exact solution for the learning dynamics of a one-hidden-layer linear network, with one-dimensional data, across any finite width.<n>We identify three novel prototype mechanisms specific to the feature learning regime.<n>Our findings are substantiated with empirical evidence showing that these mechanisms also manifest in deep nonlinear networks handling real-world tasks.
• Score: 0.34530027457862006
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding the dynamics of neural networks in different width regimes is crucial for improving their training and performance. We present an exact solution for the learning dynamics of a one-hidden-layer linear network, with one-dimensional data, across any finite width, uniquely exhibiting both kernel and feature learning phases. This study marks a technical advancement by enabling the analysis of the training trajectory from any initialization and a detailed phase diagram under varying common hyperparameters such as width, layer-wise learning rates, and scales of output and initialization. We identify three novel prototype mechanisms specific to the feature learning regime: (1) learning by alignment, (2) learning by disalignment, and (3) learning by rescaling, which contrast starkly with the dynamics observed in the kernel regime. Our theoretical findings are substantiated with empirical evidence showing that these mechanisms also manifest in deep nonlinear networks handling real-world tasks, enhancing our understanding of neural network training dynamics and guiding the design of more effective learning strategies.

Related papers

• Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond [61.18736646013446]
  In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network. Across three case studies, we illustrate how it can be applied to derive new empirical insights on a diverse range of prominent phenomena.
  arXiv  Detail & Related papers  (2024-10-31T22:54:34Z)
• From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks [47.13391046553908]
  In artificial networks, the effectiveness of these models relies on their ability to build task specific representation. Prior studies highlight that different initializations can place networks in either a lazy regime, where representations remain static, or a rich/feature learning regime, where representations evolve dynamically. These solutions capture the evolution of representations and the Neural Kernel across the spectrum from the rich to the lazy regimes.
  arXiv  Detail & Related papers  (2024-09-22T23:19:04Z)
• Dynamics of Meta-learning Representation in the Teacher-student Scenario [8.099691748821114]
  We investigate the meta-learning dynamics of nonlinear two-layer neural networks trained on streaming tasks in a teacher-student scenario. We characterize the macroscopic behavior of the meta-training processes, the formation of the shared representation, and the generalization ability of the model on new tasks.
  arXiv  Detail & Related papers  (2024-08-22T16:59:32Z)
• Unlocking the Secrets of Linear Complexity Sequence Model from A Unified Perspective [26.479602180023125]
  The Linear Complexity Sequence Model (LCSM) unites various sequence modeling techniques with linear complexity. We segment the modeling processes of these models into three distinct stages: Expand, Oscillation, and Shrink. We perform experiments to analyze the impact of different stage settings on language modeling and retrieval tasks.
  arXiv  Detail & Related papers  (2024-05-27T17:38:55Z)
• Understanding the Double Descent Phenomenon in Deep Learning [49.1574468325115]
  This tutorial sets the classical statistical learning framework and introduces the double descent phenomenon. By looking at a number of examples, section 2 introduces inductive biases that appear to have a key role in double descent by selecting. section 3 explores the double descent with two linear models, and gives other points of view from recent related works.
  arXiv  Detail & Related papers  (2024-03-15T16:51:24Z)
• Mechanistic Neural Networks for Scientific Machine Learning [58.99592521721158]
  We present Mechanistic Neural Networks, a neural network design for machine learning applications in the sciences. It incorporates a new Mechanistic Block in standard architectures to explicitly learn governing differential equations as representations. Central to our approach is a novel Relaxed Linear Programming solver (NeuRLP) inspired by a technique that reduces solving linear ODEs to solving linear programs.
  arXiv  Detail & Related papers  (2024-02-20T15:23:24Z)
• Exploiting the capacity of deep networks only at training stage for nonlinear black-box system identification [0.0]
  This study presents a novel training strategy that uses deep models only at the training stage. The proposed objective function consists of the objective of each student and teacher model adding up with a distance penalty between the learned latent representations.
  arXiv  Detail & Related papers  (2023-12-26T09:32:42Z)
• Learning Continuous Network Emerging Dynamics from Scarce Observations via Data-Adaptive Stochastic Processes [11.494631894700253]
  We introduce ODE Processes for Network Dynamics (NDP4ND), a new class of processes governed by data-adaptive network dynamics. We show that the proposed method has excellent data and computational efficiency, and can adapt to unseen network emerging dynamics.
  arXiv  Detail & Related papers  (2023-10-25T08:44:05Z)
• Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks [44.31729147722701]
  We show that three-layer neural networks have provably richer feature learning capabilities than two-layer networks. This work makes progress towards understanding the provable benefit of three-layer neural networks over two-layer networks in the feature learning regime.
  arXiv  Detail & Related papers  (2023-05-11T17:19:30Z)
• On the Stepwise Nature of Self-Supervised Learning [0.0]
  We present a simple picture of the training process of joint embedding self-supervised learning methods. We find that these methods learn their high-dimensional embeddings one dimension at a time in a sequence of discrete, well-separated steps. Our theory suggests that, just as kernel regression can be thought of as a model of supervised learning, kernel PCA may serve as a useful model of self-supervised learning.
  arXiv  Detail & Related papers  (2023-03-27T17:59:20Z)
• A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks [49.870593940818715]
  We study the infinite-width limit of a type of three-layer NN model whose first layer is random and fixed. Our theory accommodates different scaling choices of the model, resulting in two regimes of the MF limit that demonstrate distinctive behaviors.
  arXiv  Detail & Related papers  (2022-10-28T17:26:27Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning [37.27098255569438]
  We study the role of nonlinearity in the training dynamics of contrastive learning (CL) on one and two-layer nonlinear networks. We show that the presence of nonlinearity leads to many local optima even in 1-layer setting. For 2-layer setting, we also discover emphglobal modulation: those local patterns discriminative from the perspective of global-level patterns are prioritized to learn.
  arXiv  Detail & Related papers  (2022-06-02T23:52:35Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition [49.163326827954656]
  We propose a novel multi-granular-temporal graph network for skeleton-based action classification. We develop a dual-head graph network consisting of two inter-leaved branches, which enables us to extract at least two-temporal resolutions. We conduct extensive experiments on three large-scale datasets.
  arXiv  Detail & Related papers  (2021-08-10T09:25:07Z)
• A neural anisotropic view of underspecification in deep learning [60.119023683371736]
  We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
  arXiv  Detail & Related papers  (2021-04-29T14:31:09Z)
• Phase diagram for two-layer ReLU neural networks at infinite-width limit [6.380166265263755]
  We draw the phase diagram for the two-layer ReLU neural network at the infinite-width limit. We identify three regimes in the phase diagram, i.e., linear regime, critical regime and condensed regime. In the linear regime, NN training dynamics is approximately linear similar to a random feature model with an exponential loss decay. In the condensed regime, we demonstrate through experiments that active neurons are condensed at several discrete orientations.
  arXiv  Detail & Related papers  (2020-07-15T06:04:35Z)
• Deep learning of contagion dynamics on complex networks [0.0]
  We propose a complementary approach based on deep learning to build effective models of contagion dynamics on networks. By allowing simulations on arbitrary network structures, our approach makes it possible to explore the properties of the learned dynamics beyond the training data. Our results demonstrate how deep learning offers a new and complementary perspective to build effective models of contagion dynamics on networks.
  arXiv  Detail & Related papers  (2020-06-09T17:18:34Z)
• The large learning rate phase of deep learning: the catapult mechanism [50.23041928811575]
  We present a class of neural networks with solvable training dynamics. We find good agreement between our model's predictions and training dynamics in realistic deep learning settings. We believe our results shed light on characteristics of models trained at different learning rates.
  arXiv  Detail & Related papers  (2020-03-04T17:52:48Z)
• 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.