research
∙
07/10/2023
On the curvature of the loss landscape
One of the main challenges in modern deep learning is to understand why ...
share
research
∙
05/16/2023
The Hessian perspective into the Nature of Convolutional Neural Networks
While Convolutional Neural Networks (CNNs) have long been investigated a...
research
∙
02/21/2023
Some Fundamental Aspects about Lipschitz Continuity of Neural Network Functions
Lipschitz continuity is a simple yet pivotal functional property of any ...
research
∙
06/07/2022
Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse
Transformers have achieved remarkable success in several domains, rangin...
research
∙
03/14/2022
Phenomenology of Double Descent in Finite-Width Neural Networks
`Double descent' delineates the generalization behaviour of models depen...
research
∙
06/30/2021
Analytic Insights into Structure and Rank of Neural Network Hessian Maps
The Hessian of a neural network captures parameter interactions through ...
research
∙
04/29/2020
WoodFisher: Efficient second-order approximations for model compression
Second-order information, in the form of Hessian- or Inverse-Hessian-vec...
research
∙
10/12/2019
Model Fusion via Optimal Transport
Combining different models is a widely used paradigm in machine learning...
research
∙
07/15/2019
GLOSS: Generative Latent Optimization of Sentence Representations
We propose a method to learn unsupervised sentence representations in a ...
research
∙
08/29/2018