🤖 Machine Learning - weblwabl · Scour

Generalization in Deep Neural Networks: Minimax Rates for Gradient Methods

📊Vector DBs Academic

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

🔢Linear Algebra Academic

Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks

🧠Computational Neuroscience Academic

GenAutoML: An Agentic Framework for Dynamic Architecture Generation and Optimization in Time-Series Analysis

🧠Computational Neuroscience Academic

Flatland: The Adventures of Gradient Descent with Large Step Sizes

🔢Linear Algebra Academic

Second-Order Path Kernel Interpolation Formulas in Machine Learning

📊Vector DBs Academic

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

🔢Linear Algebra Academic

Reinforcement Learning for Flow-Matching Policies with Density Transport

🧠Computational Neuroscience Academic

Fourier fractal dimension to predict the generalization of deep neural networks

📐Mathematics Academic

Pseudospectral Bounds for Transient Amplification in Coupled Gradient Descent

🔢Linear Algebra Academic

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

💻Computer Science Academic

Pretraining Recurrent Networks without Recurrence

🧠Computational Neuroscience Academic

Variational Proximal Policy Optimization

🧠Computational Neuroscience Academic

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

🔢Linear Algebra Academic

Stein Kernelized Molecular Dynamics for Active Learning of Interatomic Potentials

🧠Computational Neuroscience Academic

Predictive Coding with Bayesian Priors via Proximal Gradients

📊Vector DBs Academic

A prism hierarchy of learning regimes in large linear autoencoders

🔢Linear Algebra Academic

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

🧠Computational Neuroscience Academic

When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks

📊Vector DBs Academic

Hybridizing Equilibrium Propagation with Ising Machines for Efficient Energy-Based Learning

🧠Computational Neuroscience Academic

Log in to enable infinite scrolling