Pages that link to "Item:Q5073895"
From MaRDI portal
The following pages link to Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers (Q5073895):
Displaying 17 items.
- Stable recovery of entangled weights: towards robust identification of deep neural networks from minimal samples (Q2105108) (← links)
- Information theory and recovery algorithms for data fusion in Earth observation (Q2106495) (← links)
- A Riemannian mean field formulation for two-layer neural networks with batch normalization (Q2157932) (← links)
- Side effects of learning from low-dimensional data embedded in a Euclidean space (Q2687305) (← links)
- Computation and learning in high dimensions. Abstracts from the workshop held August 1--7, 2021 (hybrid meeting) (Q2693017) (← links)
- Riemannian metrics for neural networks II: recurrent networks and learning symbolic data sequences (Q4602827) (← links)
- (Q5053253) (← links)
- Geometry of Linear Convolutional Networks (Q5097687) (← links)
- Wide neural networks of any depth evolve as linear models under gradient descent <sup>*</sup> (Q5857449) (← links)
- Global convergence of the gradient method for functions definable in o-minimal structures (Q6052062) (← links)
- Deep Linear Networks for Matrix Completion—an Infinite Depth Limit (Q6084954) (← links)
- Certifying the Absence of Spurious Local Minima at Infinity (Q6116236) (← links)
- Gradient descent for deep matrix factorization: dynamics and implicit bias towards low rank (Q6185686) (← links)
- Function space and critical points of linear convolutional networks (Q6562372) (← links)
- Infinite-width limit of deep linear neural networks (Q6587580) (← links)
- Gradient descent provably escapes saddle points in the training of shallow ReLU networks (Q6655804) (← links)
- The effect of smooth parametrizations on nonconvex optimization landscapes (Q6665380) (← links)
