181 citations · 479 across the 15 of their papers we have counts for
16 papers
Hyperparameter Optimization in Machine Learning
Luca Franceschi, Michele Donini, Valerio Perrone +5
Hyperparameters are configuration variables controlling the behavior of machine learning algorithms. They are ubiquitous in machine learning and artificial intelligence and the cho…
Evaluating Large Language Models with fmeval
Pola Schwöbel, Luca Franceschi, Muhammad Bilal Zafar +7
fmeval is an open source library to evaluate large language models (LLMs) in a range of tasks. It helps practitioners evaluate their model for task performance and along multiple r…
Explaining Probabilistic Models with Distributional Values
Luca Franceschi, Michele Donini, Cédric Archambeau +1
A large branch of explainable machine learning is grounded in cooperative game theory. However, research indicates that game-theoretic explanations may mislead or be hard to interp…
DAG Learning on the Permutahedron
Valentina Zantedeschi, Luca Franceschi, Jean Kaddour +2
We propose a continuous optimization framework for discovering a latent directed acyclic graph (DAG) from observational data. Our approach optimizes over the polytope of permutatio…
Learning Discrete Directed Acyclic Graphs via Backpropagation
Andrew J. Wren, Pasquale Minervini, Luca Franceschi +1
Recently continuous relaxations have been proposed in order to learn Directed Acyclic Graphs (DAGs) from data by backpropagation, instead of using combinatorial optimization. Howev…
Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models
Pasquale Minervini, Luca Franceschi, Mathias Niepert
The integration of discrete algorithmic components in deep learning architectures has numerous applications. Recently, Implicit Maximum Likelihood Estimation (IMLE, Niepert, Minerv…
ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
Yihong Chen, Pushkar Mishra, Luca Franceschi +3
Factorisation-based Models (FMs), such as DistMult, have enjoyed enduring success for Knowledge Graph Completion (KGC) tasks, often outperforming Graph Neural Networks (GNNs). Howe…
Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions
Mathias Niepert, Pasquale Minervini, Luca Franceschi
Combining discrete probability distributions and combinatorial optimization problems with neural network components has numerous applications but poses several challenges. We propo…
On the Iteration Complexity of Hypergradient Computation
Riccardo Grazzi, Luca Franceschi, Massimiliano Pontil +1
We study a general class of bilevel problems, consisting in the minimization of an upper-level objective which depends on the solution to a parametric fixed-point equation. Importa…
MARTHE: Scheduling the Learning Rate Via Online Hypergradients
Michele Donini, Luca Franceschi, Massimiliano Pontil +2
We study the problem of fitting task-specific learning rate schedules from the perspective of hyperparameter optimization, aiming at good generalization. We describe the structure…
Learning Discrete Structures for Graph Neural Networks
Luca Franceschi, Mathias Niepert, Massimiliano Pontil +1
Graph neural networks (GNNs) are a popular class of machine learning models whose major advantage is their ability to incorporate a sparse and discrete dependency structure between…
Fast and Continuous Foothold Adaptation for Dynamic Locomotion through CNNs
Octavio Villarreal, Victor Barasuol, Marco Camurri +5
Legged robots can outperform wheeled machines for most navigation tasks across unknown and rough terrains. For such tasks, visual feedback is a fundamental asset to provide robots…
Bilevel Programming for Hyperparameter Optimization and Meta-Learning
Luca Franceschi, Paolo Frasconi, Saverio Salzo +2
We introduce a framework based on bilevel programming that unifies gradient-based hyperparameter optimization and meta-learning. We show that an approximate version of the bilevel…
Far-HO: A Bilevel Programming Package for Hyperparameter Optimization and Meta-Learning
Luca Franceschi, Riccardo Grazzi, Massimiliano Pontil +2
In (Franceschi et al., 2018) we proposed a unified mathematical framework, grounded on bilevel programming, that encompasses gradient-based hyperparameter optimization and meta-lea…
A Bridge Between Hyperparameter Optimization and Learning-to-learn
Luca Franceschi, Michele Donini, Paolo Frasconi +1
We consider a class of a nested optimization problems involving inner and outer objectives. We observe that by taking into explicit account the optimization dynamics for the inner…
Forward and Reverse Gradient-Based Hyperparameter Optimization
Luca Franceschi, Michele Donini, Paolo Frasconi +1
We study two procedures (reverse-mode and forward-mode) for computing the gradient of the validation error with respect to the hyperparameters of any iterative learning algorithm s…