Search Results for author:
Found 8 papers, 4 papers with code
Module-wise Training of Residual Networks via the Minimizing Movement Scheme
Greedy layer-wise or module-wise training of neural networks is compelling in constrained and on-device settings, as it circumvents a number of problems of end-to-end back-propagation.
A Neural Tangent Kernel Perspective of GANs
We propose a novel theoretical framework of analysis for Generative Adversarial Networks (GANs).
LEADS: Learning Dynamical Systems that Generalize Across Environments
Both are sub-optimal: the former disregards the discrepancies between environments leading to biased solutions, while the latter does not exploit their potential commonalities and is prone to scarcity problems.
Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting
In this work, we introduce the APHYNITY framework, a principled approach for augmenting incomplete physical dynamics described by differential equations with deep data-driven models.
A Principle of Least Action for the Training of Neural Networks
From this observation, we reformulate the learning problem as follows: finding neural networks which solve the task while transporting the data as efficiently as possible.
Optimal Unsupervised Domain Translation
Domain Translation is the problem of finding a meaningful correspondence between two domains.
Learning Partially Observed PDE Dynamics with Neural Networks
Spatio-Temporal processes bear a central importance in many applied scientific fields.
Learning Dynamical Systems from Partial Observations
We consider the problem of forecasting complex, nonlinear space-time processes when observations provide only partial information of on the system's state.
