Mildly Overparameterized ReLU Networks on Orthogonal Data: Incremental Learning and Implicit Bias

• URL: http://arxiv.org/abs/2605.27097v1
• Date: Tue, 26 May 2026 14:39:20 GMT
• Title: Mildly Overparameterized ReLU Networks on Orthogonal Data: Incremental Learning and Implicit Bias
• Abstract summary: We study the gradient flow dynamics of two-layer ReLU networks with training data.<n>We prove the limiting flow converges to a saddle-to-saddle jump process.<n>More broadly, our work provides the first rigorous proof of an incremental learning process for ReLU networks.
• Score: 11.187895893664484
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The successful training of neural networks hinges on the use of first order optimization methods, yet the theoretical characterization of these methods remains incomplete. This is especially true in settings with mild overparameterization. In this work, we study the gradient flow dynamics of two-layer ReLU networks from small initialization with orthogonal training data. We prove the limiting flow converges to a saddle-to-saddle jump process as the initialization scale tends to zero, revealing an incremental learning phenomenon in which a new neuron activates at each saddle. This analysis recovers the known result of Dana et al. (2025, arXiv:2502.16977) that the network interpolates the training data with high probability as soon as $m \gtrsim \log(n)$, where $m$ is the network width and $n$ is the number of training samples. This incremental process characterization also allows us to derive a novel implicit bias result: the learned interpolator has a squared $\ell_2$-norm scaling as $\sqrt{n}$, which is within a constant factor of the minimal $\ell_2$-norm interpolator. More broadly, our work provides the first rigorous proof of an incremental learning process for ReLU networks, whilst suggesting mildly overparameterized networks can converge to interpolating solutions whose complexity is of the same order as that of the optimal interpolator.

Related papers

• Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit [66.20349460098275]
  We study the gradient descent learning of a general Gaussian Multi-index model $f(boldsymbolx)=g(boldsymbolUboldsymbolx)$ with hidden subspace $boldsymbolUin mathbbRrtimes d$.<n>We prove that under generic non-degenerate assumptions on the link function, a standard two-layer neural network trained via layer-wise gradient descent can agnostically learn the target with $o_d(1)$ test error.
  arXiv  Detail & Related papers  (2025-11-19T04:46:47Z)
• Optimization and generalization analysis for two-layer physics-informed neural networks without over-parametrization [0.6215404942415159]
  This work focuses on the behavior of gradient descent (SGD) in solving least-squares regression with physics-informed neural networks (PINNs)<n>We show that if the network width exceeds a threshold that depends only on $epsilon$ and the problem, then the training loss and expected loss will decrease below $O(epsilon)$.
  arXiv  Detail & Related papers  (2025-07-22T09:24:22Z)
• Sharp Generalization for Nonparametric Regression in Interpolation Space by Over-Parameterized Neural Networks Trained with Preconditioned Gradient Descent and Early Stopping [15.975065054204753]
  We study non regression using an over-parametricized two-layer neural networks trained with algorithmic guarantees.<n>We demonstrate that training the neural network with a novel Preconditioned Gradient Descent (PGD) algorithm, equipped with early stopping, achieves a sharp regression rate.
  arXiv  Detail & Related papers  (2024-07-16T03:38:34Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• 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)
• Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data [63.34506218832164]
  In this work, we investigate the implicit bias of gradient flow and gradient descent in two-layer fully-connected neural networks with ReLU activations. For gradient flow, we leverage recent work on the implicit bias for homogeneous neural networks to show that leakyally, gradient flow produces a neural network with rank at most two. For gradient descent, provided the random variance is small enough, we show that a single step of gradient descent suffices to drastically reduce the rank of the network, and that the rank remains small throughout training.
  arXiv  Detail & Related papers  (2022-10-13T15:09:54Z)
• 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)
• Sample Complexity and Overparameterization Bounds for Projection-Free Neural TD Learning [38.730333068555275]
  Existing analysis of neural TD learning relies on either infinite width-analysis or constraining the network parameters in a (random) compact set. We show that the projection-free TD learning equipped with a two-layer ReLU network of any width exceeding $poly(overlinenu,1/epsilon)$ converges to the true value function with error $epsilon$ given $poly(overlinenu,1/epsilon)$ iterations or samples.
  arXiv  Detail & Related papers  (2021-03-02T01:05:19Z)
• A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks [56.084798078072396]
  We take a step towards closing the gap between theory and practice by significantly improving the known theoretical bounds on both the network width and the convergence time. We show that convergence to a global minimum is guaranteed for networks with quadratic widths in the sample size and linear in their depth at a time logarithmic in both. Our analysis and convergence bounds are derived via the construction of a surrogate network with fixed activation patterns that can be transformed at any time to an equivalent ReLU network of a reasonable size.
  arXiv  Detail & Related papers  (2021-01-12T00:40:45Z)
• Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network [20.132432350255087]
  Overparametrized neural networks trained by tangent descent (GD) can provably overfit any training data. This paper studies how well overparametrized neural networks can recover the true target function in the presence of random noises.
  arXiv  Detail & Related papers  (2020-07-06T01:02:23Z)
• A Revision of Neural Tangent Kernel-based Approaches for Neural Networks [34.75076385561115]
  We use the neural tangent kernel to show that networks can fit any finite training sample perfectly. A simple and analytic kernel function was derived as indeed equivalent to a fully-trained network. Our tighter analysis resolves the scaling problem and enables the validation of the original NTK-based results.
  arXiv  Detail & Related papers  (2020-07-02T05:07:55Z)

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.