Pages that link to "Item:Q5857449"

The following pages link to Wide neural networks of any depth evolve as linear models under gradient descent ^* (Q5857449):

Displaying 43 items.

• Linearized two-layers neural networks in high dimension (Q2039801) (← links)
• Machine unlearning: linear filtration for logit-based classifiers (Q2102377) (← links)
• The interpolation phase transition in neural networks: memorization and generalization under lazy training (Q2105197) (← links)
• Provably training overparameterized neural network classifiers with non-convex constraints (Q2106783) (← links)
• Discriminative clustering with representation learning with any ratio of labeled to unlabeled data (Q2114048) (← links)
• Surprises in high-dimensional ridgeless least squares interpolation (Q2131262) (← links)
• Loss landscapes and optimization in over-parameterized non-linear systems and neural networks (Q2134108) (← links)
• When and why PINNs fail to train: a neural tangent kernel perspective (Q2136450) (← links)
• Improved architectures and training algorithms for deep operator networks (Q2149522) (← links)
• Data science applications to string theory (Q2187812) (← links)
• Landscape and training regimes in deep learning (Q2231925) (← links)
• On the eigenvector bias of Fourier feature networks: from regression to solving multi-scale PDEs with physics-informed neural networks (Q2237440) (← links)
• A statistician teaches deep learning (Q2241468) (← links)
• Drop-activation: implicit parameter reduction and harmonious regularization (Q2667354) (← links)
• Free dynamics of feature learning processes (Q2679634) (← links)
• Affine-invariant ensemble transform methods for logistic regression (Q2697401) (← links)
• Understanding approximate Fisher information for fast convergence of natural gradient descent in wide neural networks* (Q5020052) (← links)
• (Q5053206) (← links)
• Locality defeats the curse of dimensionality in convolutional teacher–student scenarios* (Q5055428) (← links)
• Adaptive and Implicit Regularization for Matrix Completion (Q5056933) (← links)
• Plateau Phenomenon in Gradient Descent Training of RELU Networks: Explanation, Quantification, and Avoidance (Q5157837) (← links)
• (Q5159408) (← links)
• (Q5159432) (← links)
• On the Effect of the Activation Function on the Distribution of Hidden Nodes in a Deep Network (Q5214413) (← links)
• Multilevel Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data (Q5857926) (← links)
• Training a Neural-Network-Based Surrogate Model for Aerodynamic Optimisation Using a Gaussian Process (Q5880409) (← links)
• Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation (Q5887828) (← links)
• Adversarial examples in random neural networks with general activations (Q6062703) (← links)
• A rigorous framework for the mean field limit of multilayer neural networks (Q6062704) (← links)
• Priors in Bayesian Deep Learning: A Review (Q6067601) (← links)
• Deep stable neural networks: large-width asymptotics and convergence rates (Q6103259) (← links)
• Graph-based sparse Bayesian broad learning system for semi-supervised learning (Q6118898) (← links)
• Weighted neural tangent kernel: a generalized and improved network-induced kernel (Q6134348) (← links)
• Deep Q‐learning: A robust control approach (Q6136628) (← links)
• An asynchronous parallel high-throughput model calibration framework for crystal plasticity finite element constitutive models (Q6164276) (← links)
• On the spectral bias of coupled frequency predictor-corrector triangular DNN: the convergence analysis (Q6179933) (← links)
• Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomy (Q6185714) (← links)
• Abstracting instance information and inter-label relations for sparse multi-label classification (Q6536005) (← links)
• Learning effective stochastic differential equations from microscopic simulations: linking stochastic numerics to deep learning (Q6572673) (← links)
• Exact learning dynamics of deep linear networks with prior knowledge (Q6611437) (← links)
• Precise learning curves and higher-order scaling limits for dot-product kernel regression (Q6611439) (← links)
• Self-consistent dynamical field theory of kernel evolution in wide neural networks (Q6611447) (← links)
• MHDnet: physics-preserving learning for solving magnetohydrodynamics problems (Q6646462) (← links)