Spherical and Hyperbolic Toric Topology-Based Codes On Graph Embedding for Ising MRF Models: Classical and Quantum Topology Machine Learning

• URL: http://arxiv.org/abs/2307.15778v2
• Date: Tue, 5 Sep 2023 19:35:25 GMT
• Title: Spherical and Hyperbolic Toric Topology-Based Codes On Graph Embedding for Ising MRF Models: Classical and Quantum Topology Machine Learning
• Authors: Vasiliy Usatyuk, Sergey Egorov, Denis Sapozhnikov
• Abstract summary: The paper introduces the application of information geometry to describe the ground states of Ising models. The approach establishes a connection between machine learning and error-correcting coding.
• Score: 0.11805137592431453
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The paper introduces the application of information geometry to describe the ground states of Ising models by utilizing parity-check matrices of cyclic and quasi-cyclic codes on toric and spherical topologies. The approach establishes a connection between machine learning and error-correcting coding. This proposed approach has implications for the development of new embedding methods based on trapping sets. Statistical physics and number geometry applied for optimize error-correcting codes, leading to these embedding and sparse factorization methods. The paper establishes a direct connection between DNN architecture and error-correcting coding by demonstrating how state-of-the-art architectures (ChordMixer, Mega, Mega-chunk, CDIL, ...) from the long-range arena can be equivalent to of block and convolutional LDPC codes (Cage-graph, Repeat Accumulate). QC codes correspond to certain types of chemical elements, with the carbon element being represented by the mixed automorphism Shu-Lin-Fossorier QC-LDPC code. The connections between Belief Propagation and the Permanent, Bethe-Permanent, Nishimori Temperature, and Bethe-Hessian Matrix are elaborated upon in detail. The Quantum Approximate Optimization Algorithm (QAOA) used in the Sherrington-Kirkpatrick Ising model can be seen as analogous to the back-propagation loss function landscape in training DNNs. This similarity creates a comparable problem with TS pseudo-codeword, resembling the belief propagation method. Additionally, the layer depth in QAOA correlates to the number of decoding belief propagation iterations in the Wiberg decoding tree. Overall, this work has the potential to advance multiple fields, from Information Theory, DNN architecture design (sparse and structured prior graph topology), efficient hardware design for Quantum and Classical DPU/TPU (graph, quantize and shift register architect.) to Materials Science and beyond.

Related papers

• Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning [86.15009879251386]
  We propose a novel architecture and method of explainable classification with Concept Bottleneck Models (CBM) CBMs require an additional set of concepts to leverage. We show a significant increase in accuracy using sparse hidden layers in CLIP-based bottleneck models.
  arXiv  Detail & Related papers  (2024-04-04T09:43:43Z)
• Understanding Stabilizer Codes Under Local Decoherence Through a General Statistical Mechanics Mapping [0.0]
  We construct a mapping from the $n$th moment of the decohered ground state density matrix to a classical statistical mechanics model. We analyze the 3D toric code and X-cube model, deriving bounds on their optimal decoding thresholds.
  arXiv  Detail & Related papers  (2024-03-06T18:59:00Z)
• Linear Codes for Hyperdimensional Computing [9.7902367664742]
  We show that random linear codes offer a rich subcode structure that can be used to form key-value stores. We show that under the framework we develop, random linear codes admit simple recovery algorithms to factor (either bundled or bound) compositional representations.
  arXiv  Detail & Related papers  (2024-03-05T19:18:44Z)
• Topology-Aware Exploration of Energy-Based Models Equilibrium: Toric QC-LDPC Codes and Hyperbolic MET QC-LDPC Codes [0.11805137592431453]
  We present a method for achieving equilibrium in the ISING Hamiltonian when confronted with unevenly distributed charges on an irregular grid. Our approach involves dimensionally expanding the system, substituting charges with circulants, and representing distances through circulant shifts. This results in a systematic mapping of the charge system onto a space, transforming the irregular grid into a uniform configuration.
  arXiv  Detail & Related papers  (2024-01-26T10:14:10Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• QNEAT: Natural Evolution of Variational Quantum Circuit Architecture [95.29334926638462]
  We focus on variational quantum circuits (VQC), which emerged as the most promising candidates for the quantum counterpart of neural networks. Although showing promising results, VQCs can be hard to train because of different issues, e.g., barren plateau, periodicity of the weights, or choice of architecture. We propose a gradient-free algorithm inspired by natural evolution to optimize both the weights and the architecture of the VQC.
  arXiv  Detail & Related papers  (2023-04-14T08:03:20Z)
• Understanding the Mapping of Encode Data Through An Implementation of Quantum Topological Analysis [0.7106986689736827]
  We show the difference in encoding techniques can be visualized by investigating the topology of the data embedded in complex Hilbert space. Our results suggest the encoding method needs to be considered carefully within different quantum machine learning models.
  arXiv  Detail & Related papers  (2022-09-21T18:46:08Z)
• Semi-Supervised Manifold Learning with Complexity Decoupled Chart Autoencoders [65.2511270059236]
  This work introduces a chart autoencoder with an asymmetric encoding-decoding process that can incorporate additional semi-supervised information such as class labels. We discuss the theoretical approximation power of such networks that essentially depends on the intrinsic dimension of the data manifold.
  arXiv  Detail & Related papers  (2022-08-22T19:58:03Z)
• Towards Quantum Graph Neural Networks: An Ego-Graph Learning Approach [47.19265172105025]
  We propose a novel hybrid quantum-classical algorithm for graph-structured data, which we refer to as the Ego-graph based Quantum Graph Neural Network (egoQGNN) egoQGNN implements the GNN theoretical framework using the tensor product and unity matrix representation, which greatly reduces the number of model parameters required. The architecture is based on a novel mapping from real-world data to Hilbert space.
  arXiv  Detail & Related papers  (2022-01-13T16:35:45Z)
• Neural Distributed Source Coding [59.630059301226474]
  We present a framework for lossy DSC that is agnostic to the correlation structure and can scale to high dimensions. We evaluate our method on multiple datasets and show that our method can handle complex correlations and state-of-the-art PSNR.
  arXiv  Detail & Related papers  (2021-06-05T04:50:43Z)
• Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems [83.98774574197613]
  We take one of the simplest inference methods, a truncated max-product Belief propagation, and add what is necessary to make it a proper component of a deep learning model. This BP-Layer can be used as the final or an intermediate block in convolutional neural networks (CNNs) The model is applicable to a range of dense prediction problems, is well-trainable and provides parameter-efficient and robust solutions in stereo, optical flow and semantic segmentation.
  arXiv  Detail & Related papers  (2020-03-13T13:11:35Z)

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.