The paper introduces Neural Low-Degree Filtering (Neural LoFi), a stylized limit of gradient-based training that turns hierarchical feature learning into an explicit iterative spectral procedure. In this framework, each layer independently selects directions with maximal low-degree correlation to the label, providing a tractable surrogate for deep learning and a kernel-space interpretation. Experiments on fully connected and convolutional networks show that Neural LoFi outperforms lazy random-feature baselines, recovers meaningful structured filters, and aligns with early gradient-descent feature discovery on real datasets.
By Yatin Dandi, Matteo Vilucchio, Luca Arnaboldi, Hugo Tabanelli, Florent Krzakala
The paper introduces a finite‑width geometric framework that explains how learned feature geometries are organized, transported, and selectively aligned in deep neural networks. It quantifies incompatibilities among weight‑generated covariance, gates, and backward sensitivities using three families of commutators, and provides exact layerwise identities that decompose these commutators into sources such as downstream transport, adjacent‑layer imbalance, and nonlinear gate‑covariance interactions. The study demonstrates that spectral alignment is a layer‑ and scale‑dependent compatibility phenomenon governed by transport, interaction, cancellation, and possible damping, rather than a universal consequence of training.
By Kaj Nystr\"om
We develop a finite-width geometric framework describing how learned feature geometries are organized, transported, and selectively aligned in deep neural networks. Incompatibility among weight-genera...
The paper investigates the singular statistical nature of Low‑Rank Adaptation (LoRA), a popular parameter‑efficient fine‑tuning method for large neural networks. By applying the real log canonical threshold (RLCT) from singular learning theory, the authors analyze how LoRA’s learning complexity depends on its low‑rank factorization and the pretrained network. They show that the forward‑backward covariance, derived from activations and backpropagated sensitivities, governs which low‑rank perturbations are statistically observable, leading to a detailed characterization of the model’s singular geometry both locally and globally, and introduce a curvature‑corrected estimator for the RLCT.
By Kamillo Ferry, Anthea Monod, Keisuke Yano
arXiv:2606. 10324v1 Announce Type: new Abstract: The analogy between deep neural network forward passes and renormalization group (RG) flows has been repeatedly noted in the literature, but existing treatments remain qualitative: depth is described as a coarse-graining scale, attention is likened to a partition function, and representations are said to flow toward fixed points.
By Parviz Haggi-Mani, Irina Rish
arXiv:2606. 04476v1 Announce Type: new Abstract: In this paper, we study the gradient descent dynamics for jointly training both layers of a one-hidden-layer ReLU network to fit a linear target function.
By Berk Tinaz, Changzhi Xie, Mahdi Soltanolkotabi
arXiv:2602.23405v3 Announce Type: replace-cross
Abstract: Varying the number of neurons while preserving function is difficult because neural networks' dense connectivity creates strong computational...
By George Bird
arXiv:2610. 09356v1 Announce Type: new Abstract: We prove global exponential (linear) convergence with an explicit rate in the rich scaling for wide two-layer linear networks trained with smooth Polyak-Lojasiewicz predictor losses.
By Stephen Y Zhang, Gabriel Peyr\'e
The analogy between deep neural network forward passes and renormalization group (RG) flows has been repeatedly noted in the literature, but existing treatments remain qualitative: depth is described as a coarse-graining scale, attention is likened to a partition function, and representations are said to flow toward fixed points. No existing work has defined a measurable RG order parameter, tested it under controlled variation of the input distribution, or made quantitative predictions that are empirically verified.
arXiv:2607. 11289v1 Announce Type: cross Abstract: Backpropagation is the computational engine of deep learning, yet its mathematical structure is typically treated as a procedural traversal of computational graphs.
By Ahmed Boughammoura
arXiv:2606. 11123v1 Announce Type: new Abstract: Backpropagation (BP) is widely viewed as biologically implausible, in part because it requires feedback weights to be the transpose of forward weights for error propagation.
By Gauthier Boeshertz, Razvan Pascanu, Claudia Clopath
The paper investigates how two‑layer polynomial‑width neural networks learn orthogonal multi‑index targets under standard initialization. It shows that incremental learning still occurs: the loss decreases sequentially following the Hermite expansion, with lower‑order components learned first. The dynamics also exhibit a competitive reallocation of parameter mass, shifting into the target subspace and concentrating on aligned neurons. The analysis uses a symmetry‑based finite‑width approximation and demonstrates that vanilla gradient descent displays the same qualitative behavior.
By Mo Zhou, Weihang Xu, Simon S. Du, Maryam Fazel