[11:30]
The dynamics of representation learning in shallow, non-linear autoencoders
[11:35]
Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks
[11:40]
Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing
[11:45]
Failure and success of the spectral bias prediction for Kernel Ridge Regression: the case of low-dimensional data
[11:50]
Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
[11:55]
Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows
[12:00]
Bounding the Width of Neural Networks via Coupled Initialization - A Worst Case Analysis
[12:05]
Maslow's Hammer in Catastrophic Forgetting: Node Re-Use vs. Node Activation
[12:10]
The Pathway Race Reduction: Dynamics of Abstraction in Gated Networks
[12:15]
Efficient Learning of CNNs using Patch Based Features
[12:20]
Neural Tangent Kernel Analysis of Deep Narrow Neural Networks
[12:25]
Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)
[12:30]
Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis
[12:35]
Non-Vacuous Generalisation Bounds for Shallow Neural Networks
[12:40]
An initial alignment between neural network and target is needed for gradient descent to learn
[12:45]
Inductive Biases and Variable Creation in Self-Attention Mechanisms
[12:50]
Topology-aware Generalization of Decentralized SGD
[12:55]
Understanding Gradient Descent on the Edge of Stability in Deep Learning