🧠 Neural Networks - jhcha.oyo · Scour

Gradient descent at the Edge of Stability: free energy model and kinetic description of the two-layer network

🧠Deep Learning Academic

Generalization in Deep Neural Networks: Minimax Rates for Gradient Methods

🧠Deep Learning Academic

KJLdefeated/RL.cu: RLVR training for LLM in CUDA/C++

⚡Flash Attention Code

github.com··Hacker News

Flatland: The Adventures of Gradient Descent with Large Step Sizes

🧠Deep Learning Academic

Projected Inverse Iteration: An Eigenvalue Approach to Ground-State Computation with Neural Quantum States

🧠Deep Learning Academic

PC Layer: Polynomial Weight Preconditioning for Improving LLM Pre-Training

💬LLMs Academic

Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training

🤖AI Academic

Learning Dynamics Reveal a Hierarchy of Weight-Induced Layerwise Gram Metrics

🤖AI Academic

An Ensembled Latent Factor Model via Differential Evolution and Gradient Descent Optimization

🤖Machine Learning Academic

Multilevel Stochastic Gradient Descent for Risk-Averse PDE-Constrained Optimization

📈Optimization Academic

Second-Order Path Kernel Interpolation Formulas in Machine Learning

🤖Machine Learning Academic

DBHN-Net: Dual-Branch Hybrid Neural Network For Low-Complexity Monaural Speech Enhancement

🤖AI Academic

Predictive Coding with Bayesian Priors via Proximal Gradients

🎲Probability Academic

Quantifying Uncertainty In Wide Two-Layer Neural Networks: On The Law Of The Limiting Fluctuation Process

🤖AI Academic

Fourier fractal dimension to predict the generalization of deep neural networks

🤖AI Academic

Pretraining Recurrent Networks without Recurrence

🤖AI Academic

Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters

📈Optimization Academic

Pseudospectral Bounds for Transient Amplification in Coupled Gradient Descent

🤖Machine Learning Academic

Attention at the Theoretical Minimum: A Mathematics of Arrays Framework for Memory-Optimal Transformer Kernels

🤖AI Academic

AI from concrete to abstract: demystifying artificial intelligence to the general public

🤖AI Academic

Log in to enable infinite scrolling