arXiv:2606. 28444v1 Announce Type: cross Abstract: Classical universal approximation theorems establish the expressive power of sigmoidal multilayer perceptrons, but they do not prescribe how initial weights should encode the geometry of a data distribution.
arXiv:2606.28444v2 Announce Type: replace-cross Abstract: Classical universal approximation theorems (UAT) establish the expressive power of sigmoidal multilayer perceptrons, but they do not specify...
We introduce Pre-Warm, a simple yet effective zero-training-cost method for data-conditioned initialization of the first convolutional layer. Before the first forward pass, Pre-Warm extracts mean-centered local patches from a single training batch, clusters them with MiniBatchKMeans, applies inverse Manhattan spatial weighting, and uses the resulting centroids to initialize half of the first-layer filters (the remainder retain Kaiming initialization).
arXiv:2606. 25256v1 Announce Type: cross Abstract: We introduce Pre-Warm, a simple yet effective zero-training-cost method for data-conditioned initialization of the first convolutional layer.
arXiv:2604. 15613v4 Announce Type: replace-cross Abstract: We present Green-ELM, a non-iterative neural architecture that replaces gradient-based optimization of the output layer with a closed-form analytic solution over a fixed, high-dimensional random feature representation.
arXiv:2606. 04583v1 Announce Type: new Abstract: Many researchers investigated neural networks with some of their weights fixed to values randomly drawn from a given distribution, e.
Over the past decade, deep neural networks (DNNs) have achieved remarkable success on complex machine-learning tasks, yet the theoretical foundations of their performance remain incomplete. From a statistical viewpoint, a natural question is: can DNNs attain feature-learning and prediction consistency comparable to that of classical models?
arXiv:2106. 06998v5 Announce Type: replace Abstract: Training convolutional neural networks at scale demands substantial memory, largely because intermediate activations must be stored for backpropagation.
arXiv:2609.37631v1 Announce Type: new Abstract: Transformers are typically trained from random initialization, requiring all their capabilities to emerge from large-scale optimization. Recent work sh...
arXiv:2605. 29547v2 Announce Type: replace-cross Abstract: Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due to non-smooth components such as ReLU activations and quantization operators.
arXiv:2606. 17886v1 Announce Type: new Abstract: Monotonicity has been a long-running architectural inductive bias for neural networks, motivated by tabular, scientific, and economic settings where outputs are known to respond monotonically to certain inputs.
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.
arXiv:2512. 09084v3 Announce Type: replace Abstract: The Kolmogorov-Arnold representation theorem offers a theoretical alternative to Multi-Layer Perceptrons (MLPs) by placing learnable univariate functions on edges rather than nodes.