The following pages link to (Q4614113):
Displaying 50 items.
- Optimizing the efficiency of first-order methods for decreasing the gradient of smooth convex functions (Q2026726) (← links)
- Four heads are better than three (Q2038021) (← links)
- A selective overview of deep learning (Q2038303) (← links)
- Linearized two-layers neural networks in high dimension (Q2039801) (← links)
- Bias of homotopic gradient descent for the hinge loss (Q2045131) (← links)
- Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness (Q2057701) (← links)
- On the robustness of minimum norm interpolators and regularized empirical risk minimizers (Q2091842) (← links)
- Measurement error models: from nonparametric methods to deep neural networks (Q2092892) (← links)
- AdaBoost and robust one-bit compressed sensing (Q2102435) (← links)
- Stable recovery of entangled weights: towards robust identification of deep neural networks from minimal samples (Q2105108) (← links)
- On the perceptron's compression (Q2106618) (← links)
- From inexact optimization to learning via gradient concentration (Q2111477) (← links)
- Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution (Q2189396) (← links)
- Generalized gradients in dynamic optimization, optimal control, and machine learning problems (Q2215292) (← links)
- Discussion of: ``Nonparametric regression using deep neural networks with ReLU activation function'' (Q2215716) (← links)
- Rejoinder: ``Nonparametric regression using deep neural networks with ReLU activation function'' (Q2215717) (← links)
- Accelerating flash calculation through deep learning methods (Q2222279) (← links)
- Generalization Error in Deep Learning (Q3296180) (← links)
- (Q4449797) (← links)
- (Q4614113) (← links)
- (Q4999011) (← links)
- (Q4999109) (← links)
- Implicit Regularization and Momentum Algorithms in Nonlinearly Parameterized Adaptive Control and Prediction (Q5004318) (← links)
- An analytic theory of shallow networks dynamics for hinge loss classification* (Q5020044) (← links)
- Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification* (Q5020049) (← links)
- (Q5053226) (← links)
- (Q5053228) (← links)
- (Q5054622) (← links)
- Two-Layer Neural Networks with Values in a Banach Space (Q5055293) (← links)
- Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting, and Regularization (Q5065474) (← links)
- Prevalence of neural collapse during the terminal phase of deep learning training (Q5073172) (← links)
- Theoretical issues in deep networks (Q5073211) (← links)
- The inverse variance–flatness relation in stochastic gradient descent is critical for finding flat minima (Q5073270) (← links)
- Geometry of Linear Convolutional Networks (Q5097687) (← links)
- (Q5148955) (← links)
- (Q5159406) (← links)
- (Q5159434) (← links)
- Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks (Q5162358) (← links)
- Spurious Valleys in Two-layer Neural Network Optimization Landscapes (Q5214225) (← links)
- On the Purity and Entropy of Mixed Gaussian States (Q5230194) (← links)
- Scaling description of generalization with number of parameters in deep learning (Q5856249) (← links)
- Dynamics of stochastic gradient descent for two-layer neural networks in the teacher–student setup* (Q5857458) (← links)
- Implicit regularization with strongly convex bias: Stability and acceleration (Q5873931) (← links)
- Deep learning: a statistical viewpoint (Q5887827) (← links)
- Solving Elliptic Problems with Singular Sources Using Singularity Splitting Deep Ritz Method (Q6095431) (← links)
- Tractability from overparametrization: the example of the negative perceptron (Q6193766) (← links)
- Gradient descent on infinitely wide neural networks: global convergence and generalization (Q6200217) (← links)
- Stability analysis of stochastic gradient descent for homogeneous neural networks and linear classifiers (Q6488828) (← links)
- When will gradient methods converge to max-margin classifier under ReLU models? (Q6541764) (← links)
- The curse of overparametrization in adversarial training: precise analysis of robust generalization for random features regression (Q6550964) (← links)
