gradient flow
Country:
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.04)
- North America > United States > California > San Diego County > San Diego (0.04)
- Europe > United Kingdom > England > Oxfordshire > Oxford (0.04)
Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.46)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Uncertainty > Bayesian Inference (0.46)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Directed Networks > Bayesian Learning (0.46)
Particle-based Variational Inference with Generalized Wasserstein Gradient Flow
We show that GWG exhibits strong convergence guarantees.
Country:
- Asia > Middle East > Jordan (0.05)
- Asia > China (0.04)
Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (0.69)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Mathematical & Statistical Methods (0.67)
Leveraging the two-timescale regime to demonstrate convergence of neural networks
Artificial neural networks are among the most successful modern machine learning methods, in particular because their non-linear parametrization provides a flexible way to implement feature learning (see, e.g., Goodfellow et al., 2016, chapter 15).
Country:
- North America > United States > Ohio (0.04)
- North America > United States > California > Santa Clara County > Palo Alto (0.04)
- Europe > Switzerland (0.04)
- Europe > France > Île-de-France > Paris > Paris (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (1.00)
On the spectral bias of two-layer linear networks
The most forceful driver of advancements in the field of Machine Learning over the past decades has been the success of deep neural networks.
Technology:
Country:
- North America > Canada > Ontario > Toronto (0.04)
- Europe > Switzerland > Vaud > Lausanne (0.04)
Technology:
Country:
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- Europe > Germany > Lower Saxony > Gottingen (0.04)
Technology:
Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent
Stein V ariational Gradient Descent (SVGD) is a nonparametric particle-based deterministic sampling algorithm.
Country:
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.14)
- North America > United States > California > Yolo County > Davis (0.14)
- North America > United States > Massachusetts > Middlesex County > Waltham (0.04)
- (3 more...)
Technology:
Unifying GANs and Score-Based Diffusion as Generative Particle Models Jean-Yves Franceschi Criteo AI Lab, Paris, France
Score-based diffusion models (Song et al., 2021) have recently received significant attention within the
Country:
- Europe > France > Île-de-France > Paris > Paris (0.40)
- North America > Canada > Ontario > Toronto (0.14)
- Asia > Middle East > Jordan (0.04)
- (5 more...)
Technology:
- Information Technology > Artificial Intelligence > Vision (1.00)
- Information Technology > Artificial Intelligence > Natural Language (1.00)
- Information Technology > Sensing and Signal Processing > Image Processing (0.93)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.68)
Module-wise Training of Neural Networks via the Minimizing Movement Scheme Anonymous Author(s) Affiliation Address email
End-to-end backpropagation is the standard training method of neural networks.
Country:
- North America > United States > Utah > Salt Lake County > Salt Lake City (0.04)
- Europe > Switzerland > Zürich > Zürich (0.04)
- Europe > Switzerland > Basel-City > Basel (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.67)
Module-wise Training of Neural Networks via the Minimizing Movement Scheme
End-to-end backpropagation is the standard training method of neural networks.
Country:
- Europe > Switzerland > Zürich > Zürich (0.04)
- North America > United States > Utah > Salt Lake County > Salt Lake City (0.04)
- Europe > Switzerland > Basel-City > Basel (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (1.00)