A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New method lowers spherical perceptron capacity using fully lifted random duality theory.
New insights into binary perceptron reveal phase transitions and algorithmic thresholds.
Study on theoretical limits of sparse-regression algorithms using Fl RDT.
Study potential computational gaps in symmetric binary perceptrons using fl-RDT.
Wide hidden layer TCM nets capacity analyzed using RDT and fl RDT.
Study binary perceptrons' capacity using random duality theory.
The study calculates the injectivity capacity of ReLU networks using a novel mathematical approach.
Improved neural network capacity analysis using simplified RDT.
The study revisits Hopfield's associative memory model and calculates its capacity for two specific pattern basins.
New algorithm nearly achieves ground state free energy of SK model.
CLuP achieves near optimal ground state energies for positive and negative Hopfield models.
New method finds rare dense clusters in asymmetric binary perceptrons, resolving algorithmic hardness.
This paper connects ultrametric overlap gap properties to parametric RDT for symmetric binary perceptrons.