Capacity of the treelike sign perceptrons neural networks with one hidden layer -- RDT based upper bounds

• URL: http://arxiv.org/abs/2312.08244v1
• Date: Wed, 13 Dec 2023 16:06:18 GMT
• Title: Capacity of the treelike sign perceptrons neural networks with one hidden layer -- RDT based upper bounds
• Abstract summary: We study the capacity of emphsign perceptrons neural networks (SPNN) We focus on 1-hidden layer emphtreelike committee machine (TCM) architectures.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the capacity of \emph{sign} perceptrons neural networks (SPNN) and particularly focus on 1-hidden layer \emph{treelike committee machine} (TCM) architectures. Similarly to what happens in the case of a single perceptron neuron, it turns out that, in a statistical sense, the capacity of a corresponding multilayered network architecture consisting of multiple \emph{sign} perceptrons also undergoes the so-called phase transition (PT) phenomenon. This means: (i) for certain range of system parameters (size of data, number of neurons), the network can be properly trained to accurately memorize \emph{all} elements of the input dataset; and (ii) outside the region such a training does not exist. Clearly, determining the corresponding phase transition curve that separates these regions is an extraordinary task and among the most fundamental questions related to the performance of any network. Utilizing powerful mathematical engine called Random Duality Theory (RDT), we establish a generic framework for determining the upper bounds on the 1-hidden layer TCM SPNN capacity. Moreover, we do so for \emph{any} given (odd) number of neurons. We further show that the obtained results \emph{exactly} match the replica symmetry predictions of \cite{EKTVZ92,BHS92}, thereby proving that the statistical physics based results are not only nice estimates but also mathematically rigorous bounds as well. Moreover, for $d\leq 5$, we obtain the capacity values that improve on the best known rigorous ones of \cite{MitchDurb89}, thereby establishing a first, mathematically rigorous, progress in well over 30 years.

Related papers

• A Graph Sufficiency Perspective for Neural Networks [4.872570541276082]
  This paper analyzes neural networks through graph variables and statistical sufficiency.<n>We interpret neural network layers as graph-based transformations, where neurons act as pairwise functions between inputs and learned anchor points.<n>Our framework covers fully connected layers, general pairwise functions, ReLU and sigmoid activations, and convolutional neural networks.
  arXiv  Detail & Related papers  (2025-07-14T12:31:47Z)
• Interpretable Scaling Behavior in Sparse Subnetwork Representations of Quantum States [0.46603287532620735]
  We show that sparse neural networks can reach accuracies comparable to their dense counterparts, even when pruned by more than an order of magnitude in parameter count.<n>We identify universal scaling behavior that persists across network sizes and physical models, where the boundaries of scaling regions are determined by the underlying Hamiltonian.
  arXiv  Detail & Related papers  (2025-05-28T18:00:08Z)
• Time Elastic Neural Networks [2.1756081703276]
  We introduce and detail an atypical neural network architecture, called time elastic neural network (teNN) The novelty compared to classical neural network architecture is that it explicitly incorporates time warping ability. We demonstrate that, during the training process, the teNN succeeds in reducing the number of neurons required within each cell.
  arXiv  Detail & Related papers  (2024-05-27T09:01:30Z)
• Multi-layer random features and the approximation power of neural networks [4.178980693837599]
  We prove that a reproducing kernel Hilbert space contains only functions that can be approximated by the architecture. We show that if eigenvalues of the integral operator of the NNGP decay slower than $k-n-frac23$ where $k$ is an order of an eigenvalue, our theorem guarantees a more succinct neural network approximation than Barron's theorem.
  arXiv  Detail & Related papers  (2024-04-26T14:57:56Z)
• Fixed width treelike neural networks capacity analysis -- generic activations [0.0]
  We consider the capacity of emphtreelike committee machines (TCM) neural networks. We show that the frameworks of citeStojnictcmspnncaprdt23,Stojnictcmspnncapliftedrdt23 are sufficiently powerful to enable handling of such scenarios as well.
  arXiv  Detail & Related papers  (2024-02-08T14:19:29Z)
• Memorization with neural nets: going beyond the worst case [5.662924503089369]
  In practice, deep neural networks are often able to easily interpolate their training data. For real-world data, however, one intuitively expects the presence of a benign structure so that already occurs at a smaller network size than suggested by memorization capacity. We introduce a simple randomized algorithm that, given a fixed finite dataset with two classes, with high probability constructs an interpolating three-layer neural network in time.
  arXiv  Detail & Related papers  (2023-09-30T10:06:05Z)
• Gradient Descent in Neural Networks as Sequential Learning in RKBS [63.011641517977644]
  We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights. We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning.
  arXiv  Detail & Related papers  (2023-02-01T03:18:07Z)
• 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)
• Coin Flipping Neural Networks [8.009932864430901]
  We show that neural networks with access to randomness can outperform deterministic networks by using amplification. We conjecture that for most classification problems, there is a CFNN which solves them with higher accuracy or fewer neurons than any deterministic network.
  arXiv  Detail & Related papers  (2022-06-18T11:19:44Z)
• On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks [91.3755431537592]
  We study how random pruning of the weights affects a neural network's neural kernel (NTK) In particular, this work establishes an equivalence of the NTKs between a fully-connected neural network and its randomly pruned version.
  arXiv  Detail & Related papers  (2022-03-27T15:22:19Z)
• Toward Trainability of Deep Quantum Neural Networks [87.04438831673063]
  Quantum Neural Networks (QNNs) with random structures have poor trainability due to the exponentially vanishing gradient as the circuit depth and the qubit number increase. We provide the first viable solution to the vanishing gradient problem for deep QNNs with theoretical guarantees.
  arXiv  Detail & Related papers  (2021-12-30T10:27:08Z)
• The Separation Capacity of Random Neural Networks [78.25060223808936]
  We show that a sufficiently large two-layer ReLU-network with standard Gaussian weights and uniformly distributed biases can solve this problem with high probability. We quantify the relevant structure of the data in terms of a novel notion of mutual complexity.
  arXiv  Detail & Related papers  (2021-07-31T10:25:26Z)
• Mitigating Performance Saturation in Neural Marked Point Processes: Architectures and Loss Functions [50.674773358075015]
  We propose a simple graph-based network structure called GCHP, which utilizes only graph convolutional layers. We show that GCHP can significantly reduce training time and the likelihood ratio loss with interarrival time probability assumptions can greatly improve the model performance.
  arXiv  Detail & Related papers  (2021-07-07T16:59:14Z)

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.