VoodooNet: Achieving Analytic Ground States via High-Dimensional Random Projections

arXiv:2604.15613v1 Announce Type: cross Abstract: We present VoodooNet, a non-iterative neural architecture that replaces the stochastic gradient descent (SGD) paradigm with a closed-form analytic solution via Galactic Expansion. By projecting input manifolds into a high-dimensional, high-entropy "Galactic" space (d gg 784), we demonstrate that complex features can be untangled without the thermodynamic cost of backpropagation. Utilizing the Moore-Penrose pseudoinverse to solve for the output layer in a single step, VoodooNet achieves a classification accuracy of extbf{98.10% on MNIST} and extbf{86.63% on Fashion-MNIST}. Notably, our results on Fashion-MNIST surpass a 10-epoch SGD baseline (84.41%) while reducing the training time by orders of magnitude. We observe a near-logarithmic scaling law between dimensionality and accuracy, suggesting that performance is a function of "Galactic" volume rather than iterative refinement. This "Magic Hat" approach offers a new frontier for real-time Edge AI, where the traditional training phase is bypassed in favor of instantaneous manifold discovery.

Related

• cuNNQS-SCI: A Fully GPU-Accelerated Framework for High-Performance Configuration Interaction Selection withNeural Network QQantum States
• WebLLM: A High-Performance In-Browser LLM Inference Engine
• Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads
• MoBiE: Efficient Inference of Mixture of Binary Experts under Post-Training Quantization

Source: arXiv cs.AI | 2026-04-20