Luca Franceschi

Orcid: 0000-0002-1810-1016

Affiliations:
  • Istituto Italiano di Tecnologia, Genoa, Italy
  • University College London, UK


According to our database1, Luca Franceschi authored at least 25 papers between 2017 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Jet Expansions of Residual Computation.
CoRR, 2024

Evaluating Large Language Models with fmeval.
CoRR, 2024

Explaining Probabilistic Models with Distributional Values.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023
Explaining Multiclass Classifiers with Categorical Values: A Case Study in Radiography.
Proceedings of the Trustworthy Machine Learning for Healthcare, 2023

Hands-on Tutorial: "Explanations in AI: Methods, Stakeholders and Pitfalls".
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023

DAG Learning on the Permutahedron.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
Learning Discrete Directed Acyclic Graphs via Backpropagation.
CoRR, 2022

ReFactorGNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective.
CoRR, 2022

ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021
A unified framework for gradient-based hyperparameter optimization and meta-learning.
PhD thesis, 2021

Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020
Marthe: Scheduling the Learning Rate Via Online Hypergradients.
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020

On the Iteration Complexity of Hypergradient Computation.
Proceedings of the 37th International Conference on Machine Learning, 2020

2019
Fast and Continuous Foothold Adaptation for Dynamic Locomotion Through CNNs.
IEEE Robotics Autom. Lett., 2019

Scheduling the Learning Rate via Hypergradients: New Insights and a New Algorithm.
CoRR, 2019

Learning Discrete Structures for Graph Neural Networks.
Proceedings of the 36th International Conference on Machine Learning, 2019

2018
Fast and Continuous Foothold Adaptation for Dynamic Locomotion through Convolutional Neural Networks.
CoRR, 2018

Far-HO: A Bilevel Programming Package for Hyperparameter Optimization and Meta-Learning.
CoRR, 2018

Bilevel Programming for Hyperparameter Optimization and Meta-Learning.
CoRR, 2018

Bilevel Programming for Hyperparameter Optimization and Meta-Learning.
Proceedings of the 35th International Conference on Machine Learning, 2018

2017
A Bridge Between Hyperparameter Optimization and Larning-to-learn.
CoRR, 2017

A Speaker Adaptive DNN Training Approach for Speaker-Independent Acoustic Inversion.
Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

Forward and Reverse Gradient-Based Hyperparameter Optimization.
Proceedings of the 34th International Conference on Machine Learning, 2017

On Hyperparameter Optimization in Learning Systems.
Proceedings of the 5th International Conference on Learning Representations, 2017


  Loading...