Pages that link to "Item:Q2197845"

The following pages link to A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics (Q2197845):

Displaying 16 items.

• Machine learning from a continuous viewpoint. I (Q829085) (← links)
• Non-convergence of stochastic gradient descent in the training of deep neural networks (Q2034567) (← links)
• Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation (Q2079548) (← links)
• The interpolation phase transition in neural networks: memorization and generalization under lazy training (Q2105197) (← links)
• A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions (Q2145074) (← links)
• A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions (Q2167333) (← links)
• Kolmogorov width decay and poor approximators in machine learning: shallow neural networks, random feature models and neural tangent kernels (Q2226529) (← links)
• Searching the solution landscape by generalized high-index saddle dynamics (Q2238496) (← links)
• (Q4998974) (← links)
• On the Exact Computation of Linear Frequency Principle Dynamics and Its Generalization (Q5051354) (← links)
• (Q5054645) (← links)
• Full error analysis for the training of deep neural networks (Q5083408) (← links)
• Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation (Q6107984) (← links)
• SPADE4: sparsity and delay embedding based forecasting of epidemics (Q6168035) (← links)
• Strong overall error analysis for the training of artificial neural networks via random initializations (Q6617376) (← links)
• Gradient descent provably escapes saddle points in the training of shallow ReLU networks (Q6655804) (← links)