Zobrazeno 1 - 10
of 1 938
pro vyhledávání: '"A, El Mahdi"'
Autor:
Khribch, El Mahdi, Alquier, Pierre
Recent advances in statistical learning theory have revealed profound connections between mutual information (MI) bounds, PAC-Bayesian theory, and Bayesian nonparametrics. This work introduces a novel mutual information bound for statistical models.
Externí odkaz:
http://arxiv.org/abs/2412.18539
Importance sampling and independent Metropolis-Hastings (IMH) are among the fundamental building blocks of Monte Carlo methods. Both require a proposal distribution that globally approximates the target distribution. The Radon-Nikodym derivative of t
Externí odkaz:
http://arxiv.org/abs/2411.09514
Gradient attacks and data poisoning tamper with the training of machine learning algorithms to maliciously alter them and have been proven to be equivalent in convex settings. The extent of harm these attacks can produce in non-convex settings is sti
Externí odkaz:
http://arxiv.org/abs/2410.21453
We study stochastic second-order methods for solving general non-convex optimization problems. We propose using a special version of momentum to stabilize the stochastic gradient and Hessian estimates in Newton's method. We show that momentum provabl
Externí odkaz:
http://arxiv.org/abs/2410.19644
Autor:
El-Mhamdi, El-Mahdi, Hoang, Lê-Nguyên
``When a measure becomes a target, it ceases to be a good measure'', this adage is known as {\it Goodhart's law}. In this paper, we investigate formally this law and prove that it critically depends on the tail distribution of the discrepancy between
Externí odkaz:
http://arxiv.org/abs/2410.09638
Dataset ownership verification, the process of determining if a dataset is used in a model's training data, is necessary for detecting unauthorized data usage and data contamination. Existing approaches, such as backdoor watermarking, rely on inducin
Externí odkaz:
http://arxiv.org/abs/2410.09101
Autor:
Chayti, El Mahdi, Jaggi, Martin
Learning new tasks by drawing on prior experience gathered from other (related) tasks is a core property of any intelligent system. Gradient-based meta-learning, especially MAML and its variants, has emerged as a viable solution to accomplish this go
Externí odkaz:
http://arxiv.org/abs/2409.03682
Autor:
Capitaine, Aymeric, Boursier, Etienne, Scheid, Antoine, Moulines, Eric, Jordan, Michael I., El-Mhamdi, El-Mahdi, Durmus, Alain
Collaborative learning offers a promising avenue for leveraging decentralized data. However, collaboration in groups of strategic learners is not a given. In this work, we consider strategic agents who wish to train a model together but have sampling
Externí odkaz:
http://arxiv.org/abs/2407.14332
Autor:
Kreß, Fabian, Annabi, El Mahdi El, Hotfilter, Tim, Hoefer, Julian, Harbaum, Tanja, Becker, Juergen
Distributed systems can be found in various applications, e.g., in robotics or autonomous driving, to achieve higher flexibility and robustness. Thereby, data flow centric applications such as Deep Neural Network (DNN) inference benefit from partitio
Externí odkaz:
http://arxiv.org/abs/2406.19913
Autor:
Scheid, Antoine, Tiapkin, Daniil, Boursier, Etienne, Capitaine, Aymeric, Mhamdi, El Mahdi El, Moulines, Eric, Jordan, Michael I., Durmus, Alain
This work considers a repeated principal-agent bandit game, where the principal can only interact with her environment through the agent. The principal and the agent have misaligned objectives and the choice of action is only left to the agent. Howev
Externí odkaz:
http://arxiv.org/abs/2403.03811