Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Franceschi, Luca"'
We introduce a framework for expanding residual computational graphs using jets, operators that generalize truncated Taylor series. Our method provides a systematic approach to disentangle contributions of different computational paths to model predi
Externí odkaz:
http://arxiv.org/abs/2410.06024
Autor:
Schwöbel, Pola, Franceschi, Luca, Zafar, Muhammad Bilal, Vasist, Keerthan, Malhotra, Aman, Shenhar, Tomer, Tailor, Pinal, Yilmaz, Pinar, Diamond, Michael, Donini, Michele
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 responsible AI dimensions. This paper presents the library and exposes
Externí odkaz:
http://arxiv.org/abs/2407.12872
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 interpret. We argue that often there is a critical mismatch between what one
Externí odkaz:
http://arxiv.org/abs/2402.09947
We propose a continuous optimization framework for discovering a latent directed acyclic graph (DAG) from observational data. Our approach optimizes over the polytope of permutation vectors, the so-called Permutahedron, to learn a topological orderin
Externí odkaz:
http://arxiv.org/abs/2301.11898
Recently continuous relaxations have been proposed in order to learn Directed Acyclic Graphs (DAGs) from data by backpropagation, instead of using combinatorial optimization. However, a number of techniques for fully discrete backpropagation could in
Externí odkaz:
http://arxiv.org/abs/2210.15353
The integration of discrete algorithmic components in deep learning architectures has numerous applications. Recently, Implicit Maximum Likelihood Estimation (IMLE, Niepert, Minervini, and Franceschi 2021), a class of gradient estimators for discrete
Externí odkaz:
http://arxiv.org/abs/2209.04862
Autor:
Chen, Yihong, Mishra, Pushkar, Franceschi, Luca, Minervini, Pasquale, Stenetorp, Pontus, Riedel, Sebastian
Factorisation-based Models (FMs), such as DistMult, have enjoyed enduring success for Knowledge Graph Completion (KGC) tasks, often outperforming Graph Neural Networks (GNNs). However, unlike GNNs, FMs struggle to incorporate node features and genera
Externí odkaz:
http://arxiv.org/abs/2207.09980
Combining discrete probability distributions and combinatorial optimization problems with neural network components has numerous applications but poses several challenges. We propose Implicit Maximum Likelihood Estimation (I-MLE), a framework for end
Externí odkaz:
http://arxiv.org/abs/2106.01798
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. Important instances arising in machine learning include hyperparameter optimi
Externí odkaz:
http://arxiv.org/abs/2006.16218
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 of the gradient of a validation error w.r.t. the learning rate schedul
Externí odkaz:
http://arxiv.org/abs/1910.08525