research
∙
01/27/2023
DAG Learning on the Permutahedron
We propose a continuous optimization framework for discovering a latent ...
share
research
∙
10/27/2022
Learning Discrete Directed Acyclic Graphs via Backpropagation
Recently continuous relaxations have been proposed in order to learn Dir...
research
∙
09/11/2022
Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models
The integration of discrete algorithmic components in deep learning arch...
research
∙
07/20/2022
ReFactorGNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
Factorisation-based Models (FMs), such as DistMult, have enjoyed endurin...
research
∙
06/03/2021
Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions
Integrating discrete probability distributions and combinatorial optimiz...
research
∙
06/29/2020
On the Iteration Complexity of Hypergradient Computation
We study a general class of bilevel problems, consisting in the minimiza...
research
∙
10/18/2019
Scheduling the Learning Rate via Hypergradients: New Insights and a New Algorithm
We study the problem of fitting task-specific learning rate schedules fr...
research
∙
03/28/2019
Learning Discrete Structures for Graph Neural Networks
Graph neural networks (GNNs) are a popular class of machine learning mod...
research
∙
09/25/2018
Fast and Continuous Foothold Adaptation for Dynamic Locomotion through Convolutional Neural Networks
Legged robots can outperform wheeled machines for most navigation tasks ...
research
∙
06/13/2018
Far-HO: A Bilevel Programming Package for Hyperparameter Optimization and Meta-Learning
In (Franceschi et al., 2018) we proposed a unified mathematical framewor...
research
∙
06/13/2018
Bilevel Programming for Hyperparameter Optimization and Meta-Learning
We introduce a framework based on bilevel programming that unifies gradi...
research
∙
12/18/2017
A Bridge Between Hyperparameter Optimization and Larning-to-learn
We consider a class of a nested optimization problems involving inner an...
research
∙
03/06/2017