Feature Learning Beyond the Edge of Stability

• URL: http://arxiv.org/abs/2502.13110v2
• Date: Sat, 17 May 2025 15:34:29 GMT
• Title: Feature Learning Beyond the Edge of Stability
• Authors: Dávid Terjék,
• Abstract summary: We propose a homogeneous multilayer perceptron parameterization with hidden layer width pattern and analyze its training dynamics under gradient descent.<n>We obtain formulas for the first three Taylor coefficients of the minibatch loss during training that illuminate the connection between sharpness and feature learning.
• Score: 8.430481660019451
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a homogeneous multilayer perceptron parameterization with polynomial hidden layer width pattern and analyze its training dynamics under stochastic gradient descent with depthwise gradient scaling in a general supervised learning scenario. We obtain formulas for the first three Taylor coefficients of the minibatch loss during training that illuminate the connection between sharpness and feature learning, providing in particular a soft rank variant that quantifies the quality of learned hidden layer features. Based on our theory, we design a gradient scaling scheme that in tandem with a quadratic width pattern enables training beyond the edge of stability without loss explosions or numerical errors, resulting in improved feature learning and implicit sharpness regularization as demonstrated empirically.

Related papers

• In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention [52.159541540613915]
  We study how multi-head softmax attention models are trained to perform in-context learning on linear data.<n>Our results reveal that in-context learning ability emerges from the trained transformer as an aggregated effect of its architecture and the underlying data distribution.
  arXiv  Detail & Related papers  (2025-03-17T02:00:49Z)
• Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $μ$P Parametrization [66.03821840425539]
  In this paper, we investigate the training dynamics of $L$-layer neural networks using the tensor gradient program (SGD) framework. We show that SGD enables these networks to learn linearly independent features that substantially deviate from their initial values. This rich feature space captures relevant data information and ensures that any convergent point of the training process is a global minimum.
  arXiv  Detail & Related papers  (2025-03-12T17:33:13Z)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones. We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• Gradient-Variation Online Learning under Generalized Smoothness [56.38427425920781]
  gradient-variation online learning aims to achieve regret guarantees that scale with variations in gradients of online functions. Recent efforts in neural network optimization suggest a generalized smoothness condition, allowing smoothness to correlate with gradient norms. We provide the applications for fast-rate convergence in games and extended adversarial optimization.
  arXiv  Detail & Related papers  (2024-08-17T02:22:08Z)
• Demystifying Lazy Training of Neural Networks from a Macroscopic Viewpoint [5.9954962391837885]
  We study the gradient descent dynamics of neural networks through the lens of macroscopic limits. Our study reveals that gradient descent can rapidly drive deep neural networks to zero training loss. Our approach draws inspiration from the Neural Tangent Kernel (NTK) paradigm.
  arXiv  Detail & Related papers  (2024-04-07T08:07:02Z)
• Super Consistency of Neural Network Landscapes and Learning Rate Transfer [72.54450821671624]
  We study the landscape through the lens of the loss Hessian. We find that certain spectral properties under $mu$P are largely independent of the size of the network. We show that in the Neural Tangent Kernel (NTK) and other scaling regimes, the sharpness exhibits very different dynamics at different scales.
  arXiv  Detail & Related papers  (2024-02-27T12:28:01Z)
• A Dynamical Model of Neural Scaling Laws [79.59705237659547]
  We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization. Our theory shows how the gap between training and test loss can gradually build up over time due to repeated reuse of data.
  arXiv  Detail & Related papers  (2024-02-02T01:41:38Z)
• Robust Stochastically-Descending Unrolled Networks [85.6993263983062]
  Deep unrolling is an emerging learning-to-optimize method that unrolls a truncated iterative algorithm in the layers of a trainable neural network.<n>We show that convergence guarantees and generalizability of the unrolled networks are still open theoretical problems.<n>We numerically assess unrolled architectures trained under the proposed constraints in two different applications.
  arXiv  Detail & Related papers  (2023-12-25T18:51:23Z)
• A Framework for Provably Stable and Consistent Training of Deep Feedforward Networks [4.21061712600981]
  We present a novel algorithm for training deep neural networks in supervised (classification and regression) and unsupervised (reinforcement learning) scenarios. This algorithm combines the standard descent gradient and the gradient clipping method. We show, in theory and through experiments, that our algorithm updates have low variance, and the training loss reduces in a smooth manner.
  arXiv  Detail & Related papers  (2023-05-20T07:18:06Z)
• On a continuous time model of gradient descent dynamics and instability in deep learning [12.20253214080485]
  We propose the principal flow (PF) as a continuous time flow that approximates gradient descent dynamics. The PF sheds light on the recently observed edge of stability phenomena in deep learning. Using our new understanding of instability we propose a learning rate adaptation method which enables us to control the trade-off between training stability and test set evaluation performance.
  arXiv  Detail & Related papers  (2023-02-03T19:03:10Z)
• Neural Networks with Quantization Constraints [111.42313650830248]
  We present a constrained learning approach to quantization training. We show that the resulting problem is strongly dual and does away with gradient estimations. We demonstrate that the proposed approach exhibits competitive performance in image classification tasks.
  arXiv  Detail & Related papers  (2022-10-27T17:12:48Z)
• Understanding Deep Neural Function Approximation in Reinforcement Learning via $\epsilon$-Greedy Exploration [53.90873926758026]
  This paper provides a theoretical study of deep neural function approximation in reinforcement learning (RL) We focus on the value based algorithm with the $epsilon$-greedy exploration via deep (and two-layer) neural networks endowed by Besov (and Barron) function spaces. Our analysis reformulates the temporal difference error in an $L2(mathrmdmu)$-integrable space over a certain averaged measure $mu$, and transforms it to a generalization problem under the non-iid setting.
  arXiv  Detail & Related papers  (2022-09-15T15:42:47Z)
• Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit [36.17720004582283]
  This work conducts such an exploration through the lens of learning $k$-sparse parities of $n$ bits. We find that neural networks exhibit surprising phase transitions when scaling up dataset size and running time.
  arXiv  Detail & Related papers  (2022-07-18T17:55:05Z)
• Bilevel learning of l1-regularizers with closed-form gradients(BLORC) [8.138650738423722]
  We present a method for supervised learning of sparsity-promoting regularizers. The parameters are learned to minimize the mean squared error of reconstruction on a training set of ground truth signal and measurement pairs.
  arXiv  Detail & Related papers  (2021-11-21T17:01:29Z)
• A Loss Curvature Perspective on Training Instability in Deep Learning [28.70491071044542]
  We study the evolution of the loss Hessian across many classification tasks in order to understand the effect curvature of the loss has on the training dynamics. Inspired by the conditioning perspective, we show that learning rate warmup can improve training stability just as much as batch normalization.
  arXiv  Detail & Related papers  (2021-10-08T20:25:48Z)
• Towards an Understanding of Benign Overfitting in Neural Networks [104.2956323934544]
  Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss. We examine how these benign overfitting phenomena occur in a two-layer neural network setting. We show that it is possible for the two-layer ReLU network interpolator to achieve a near minimax-optimal learning rate.
  arXiv  Detail & Related papers  (2021-06-06T19:08:53Z)
• Initialization and Regularization of Factorized Neural Layers [23.875225732697142]
  We show how to initialize and regularize Factorized layers in deep nets. We show how these schemes lead to improved performance on both translation and unsupervised pre-training.
  arXiv  Detail & Related papers  (2021-05-03T17:28:07Z)
• A block coordinate descent optimizer for classification problems exploiting convexity [0.0]
  We introduce a coordinate descent method to deep linear networks for classification tasks that exploits convexity of the cross-entropy loss in the weights of the hidden layer. By alternating between a second-order method to find globally optimal parameters for the linear layer and gradient descent to the hidden layers, we ensure an optimal fit of the adaptive basis to data throughout training.
  arXiv  Detail & Related papers  (2020-06-17T19:49:06Z)
• Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training [2.9649783577150837]
  We study the effect of mini-batching on the loss landscape of deep neural networks using spiked, field-dependent random matrix theory. We derive analytical expressions for the maximal descent and adaptive training regimens for smooth, non-Newton deep neural networks. We validate our claims on the VGG/ResNet and ImageNet datasets.
  arXiv  Detail & Related papers  (2020-06-16T11:55:45Z)
• AdaS: Adaptive Scheduling of Stochastic Gradients [50.80697760166045]
  We introduce the notions of textit"knowledge gain" and textit"mapping condition" and propose a new algorithm called Adaptive Scheduling (AdaS) Experimentation reveals that, using the derived metrics, AdaS exhibits: (a) faster convergence and superior generalization over existing adaptive learning methods; and (b) lack of dependence on a validation set to determine when to stop training.
  arXiv  Detail & Related papers  (2020-06-11T16:36:31Z)
• Regularizing Meta-Learning via Gradient Dropout [102.29924160341572]
  meta-learning models are prone to overfitting when there are no sufficient training tasks for the meta-learners to generalize. We introduce a simple yet effective method to alleviate the risk of overfitting for gradient-based meta-learning.
  arXiv  Detail & Related papers  (2020-04-13T10:47:02Z)
• 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.