Zobrazeno 1 - 10
of 515
pro vyhledávání: '"Moulines, Eric"'
We introduce a novel class of generative models based on piecewise deterministic Markov processes (PDMPs), a family of non-diffusive stochastic processes consisting of deterministic motion and random jumps at random times. Similarly to diffusions, su
Externí odkaz:
http://arxiv.org/abs/2407.19448
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
We develop a new method for creating prediction sets that combines the flexibility of conformal methods with an estimate of the conditional distribution $P_{Y \mid X}$. Most existing methods, such as conformalized quantile regression and probabilisti
Externí odkaz:
http://arxiv.org/abs/2407.01794
Autor:
Scheid, Antoine, Capitaine, Aymeric, Boursier, Etienne, Moulines, Eric, Jordan, Michael I, Durmus, Alain
In economic theory, the concept of externality refers to any indirect effect resulting from an interaction between players that affects the social welfare. Most of the models within which externality has been studied assume that agents have perfect k
Externí odkaz:
http://arxiv.org/abs/2406.19824
In this paper, we rigorously derive Central Limit Theorems (CLT) for Bayesian two-layerneural networks in the infinite-width limit and trained by variational inference on a regression task. The different networks are trained via different maximizatio
Externí odkaz:
http://arxiv.org/abs/2406.09048
Variational inference (VI) is a popular approach in Bayesian inference, that looks for the best approximation of the posterior distribution within a parametric family, minimizing a loss that is typically the (reverse) Kullback-Leibler (KL) divergence
Externí odkaz:
http://arxiv.org/abs/2406.04012
In this paper, we obtain the Berry-Esseen bound for multivariate normal approximation for the Polyak-Ruppert averaged iterates of the linear stochastic approximation (LSA) algorithm with decreasing step size. Our findings reveal that the fastest rate
Externí odkaz:
http://arxiv.org/abs/2405.16644
We introduce ReALLM, a novel approach for compression and memory-efficient adaptation of pre-trained language models that encompasses most of the post-training quantization and fine-tuning methods for a budget of <4 bits. Pre-trained matrices are dec
Externí odkaz:
http://arxiv.org/abs/2405.13155
Motivated by the widespread use of approximate derivatives in machine learning and optimization, we study inexact subgradient methods with non-vanishing additive errors and step sizes. In the nonconvex semialgebraic setting, under boundedness assumpt
Externí odkaz:
http://arxiv.org/abs/2404.19517
Interest in the use of Denoising Diffusion Models (DDM) as priors for solving inverse Bayesian problems has recently increased significantly. However, sampling from the resulting posterior distribution poses a challenge. To solve this problem, previo
Externí odkaz:
http://arxiv.org/abs/2403.11407