🛠 Ml-eng - miterion · Scour

A numerical study into neural network surrogate model performance for uncertainty propagation 📉Model Quantization

Training Neural Networks with Optimal Double-Bayesian Learning 📊Gradient Accumulation

Cross-Paradigm Knowledge Distillation: A Comprehensive Study of Bidirectional Transfer Between Random Forests and Deep Neural Networks for Big Data Applications 🎓Model Distillation

LymphNode: A Plug-and-Play Access Control Method for Deep Neural Networks 🔄ONNX

Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent 📊Gradient Accumulation

A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights 📊Gradient Accumulation

Rethinking Neural Network Learning Rates: A Stackelberg Perspective 📊Gradient Accumulation

GELATO: Multi-Material Topology Optimization of Programmable Gel-Elastomer Structures 🎯Tensor Cores

Characterizing Learning in Deep Neural Networks using Tractable Algorithmic Complexity Analysis 📉Model Quantization

Robust Basis Spline Decoupling for the Compression of Transformer Models 🎓Model Distillation

Adynamical systems view of training generativemodels and the memorization phenomenon 📊Gradient Accumulation

Replacement Learning: Training Neural Networks with Fewer Parameters 📊Gradient Accumulation

How does feature learning reshape the function space? 📊Gradient Accumulation

Convergence Analysis of the Wasserstein Proximal Algorithm beyond Geodesic Convexity 📉Model Quantization

A Spline-based Physics-Informed Numerical Scheme: Accurate Smooth Solutions for Differential Equations ✂️CUTLASS

A Dual Physics-Informed Kolmogorov-Arnold Neural Network Framework for Continuum Topology Optimization ⚡ONNX Runtime

Pointwise Generalization in Deep Neural Networks 📊Gradient Accumulation

From Simple to Complex: Curriculum-Guided Physics-Informed Neural Networks via Gaussian Mixture Models 🎓Model Distillation

Exact Convex Reformulations of Linear Neural Networks via Completely Positive Lifting 📉Model Quantization

Canonical Regularisation of Wide Feature-Learning Neural Networks 🧮cuDNN

Sign up or log in to see more results

Log in to enable infinite scrolling