arXiv:2601. 22652v2 Announce Type: replace-cross Abstract: Spectral gradient methods, such as the Muon optimizer, modify gradient updates by preserving directional information while discarding scale, and have shown strong empirical performance in deep learning.
arXiv:2501. 02436v5 Announce Type: replace Abstract: Advancements in artificial intelligence call for a deeper understanding of the fundamental mechanisms underlying deep learning.
arXiv:2401. 04013v2 Announce Type: replace Abstract: Deep learning models, such as wide neural networks, can be conceptualized as nonlinear dynamical physical systems characterized by a multitude of interacting degrees of freedom.
arXiv:2607. 12332v1 Announce Type: new Abstract: We study the gradient flow dynamics of diagonal linear networks for regression tasks under infinitesimal initialization.
We study the gradient flow dynamics of diagonal linear networks for regression tasks under infinitesimal initialization. Extending Theorem 1 from Pesme & Flammarion (2023), we generalize the analysis to both deep diagonal linear networks and a broader class of two-layer diagonal linear networks (as defined in Definition 4.
The paper analyzes gradient flow in a two‑layer linear neural network as the input, hidden, and output dimensions grow proportionally. Using a closed‑form solution combined with random matrix theory, it derives exact asymptotic spectral distributions for the weight matrices at all times and tracks how the learned subspace evolves. In the limit of small initialization, the study reveals a silent alignment phase where singular directions align quickly while singular values and loss stay unchanged, followed by a visible learning phase on a logarithmic timescale where singular values increase and loss decreases through a saddle‑to‑saddle dynamic that becomes continuous in the high‑dimensional limit.
The paper introduces a pointwise generalization theory for fully connected deep neural networks, using a pointwise Riemannian Dimension derived from eigenvalues of learned feature representations across layers. This framework provides hypothesis-dependent, representation-aware generalization bounds that are significantly tighter than traditional size- or norm-based approaches, both theoretically and experimentally. The authors analytically identify structural properties that explain deep networks’ tractability and empirically show that the pointwise Riemannian Dimension captures feature compression, over‑parameterization effects, and optimizer bias.
arXiv:2610.35514v1 Announce Type: new Abstract: Neural scaling laws describe the predictable power-law dependence of model performance on training time, dataset size, and model scale, with the expone...
arXiv:2610.23779v1 Announce Type: cross Abstract: Understanding how stochastic gradient descent learns internal representations in wide neural networks trained on rich target functions is a central p...
arXiv:2608. 15239v1 Announce Type: new Abstract: Power-law anisotropy in internal representations has been observed across a wide range of biological and artificial neural systems, from state-of-the-art language models to the mouse cerebral cortex.
arXiv:2505. 21423v3 Announce Type: replace Abstract: The remarkable generalization properties of overparameterized networks are often attributed to implicit biases, such as norm minimization at small learning rates and low sharpness in the Edge-of-Stability regime.
arXiv:2501. 07400v2 Announce Type: replace-cross Abstract: We derive explicit equations governing the cumulative biases and weights in Deep Learning with ReLU activation function, based on gradient descent for the Euclidean loss in the input layer, and under the assumption that the weights are, in a precise sense, adapted to the coordinate system distinguished by the activations.