Zobrazeno 1 - 10
of 526
pro vyhledávání: '"MOULINES, ERIC"'
In this paper, we present a novel analysis of FedAvg with constant step size, relying on the Markov property of the underlying process. We demonstrate that the global iterates of the algorithm converge to a stationary distribution and analyze its res
Externí odkaz:
http://arxiv.org/abs/2412.01389
In this paper, we present the Federated Upper Confidence Bound Value Iteration algorithm ($\texttt{Fed-UCBVI}$), a novel extension of the $\texttt{UCBVI}$ algorithm (Azar et al., 2017) tailored for the federated learning framework. We prove that the
Externí odkaz:
http://arxiv.org/abs/2410.22908
Autor:
Scheid, Antoine, Boursier, Etienne, Durmus, Alain, Jordan, Michael I., Ménard, Pierre, Moulines, Eric, Valko, Michal
Reinforcement Learning from Human Feedback (RLHF) has become a popular approach to align language models (LMs) with human preferences. This method involves collecting a large dataset of human pairwise preferences across various text generations and u
Externí odkaz:
http://arxiv.org/abs/2410.17055
Autor:
Moufad, Badr, Janati, Yazid, Bedin, Lisa, Durmus, Alain, Douc, Randal, Moulines, Eric, Olsson, Jimmy
Diffusion models have recently shown considerable potential in solving Bayesian inverse problems when used as priors. However, sampling from the resulting denoising posterior distributions remains a challenge as it involves intractable terms. To tack
Externí odkaz:
http://arxiv.org/abs/2410.09945
Autor:
Sheshukova, Marina, Belomestny, Denis, Durmus, Alain, Moulines, Eric, Naumov, Alexey, Samsonov, Sergey
We address the problem of solving strongly convex and smooth minimization problems using stochastic gradient descent (SGD) algorithm with a constant step size. Previous works suggested to combine the Polyak-Ruppert averaging procedure with the Richar
Externí odkaz:
http://arxiv.org/abs/2410.05106
Autor:
Mancini, Lorenzo, Labbi, Safwan, Meraim, Karim Abed, Boukhalfa, Fouzi, Durmus, Alain, Mangold, Paul, Moulines, Eric
Vehicle-to-everything (V2X) communication technology is revolutionizing transportation by enabling interactions between vehicles, devices, and infrastructures. This connectivity enhances road safety, transportation efficiency, and driver assistance s
Externí odkaz:
http://arxiv.org/abs/2410.20687
Autor:
Perrault, Pierre, Belomestny, Denis, Ménard, Pierre, Moulines, Éric, Naumov, Alexey, Tiapkin, Daniil, Valko, Michal
In this paper, we introduce a novel approach for bounding the cumulant generating function (CGF) of a Dirichlet process (DP) $X \sim \text{DP}(\alpha \nu_0)$, using superadditivity. In particular, our key technical contribution is the demonstration o
Externí odkaz:
http://arxiv.org/abs/2409.18621
Autor:
Shang, Guokan, Abdine, Hadi, Khoubrane, Yousef, Mohamed, Amr, Abbahaddou, Yassine, Ennadir, Sofiane, Momayiz, Imane, Ren, Xuguang, Moulines, Eric, Nakov, Preslav, Vazirgiannis, Michalis, Xing, Eric
We introduce Atlas-Chat, the first-ever collection of LLMs specifically developed for dialectal Arabic. Focusing on Moroccan Arabic, also known as Darija, we construct our instruction dataset by consolidating existing Darija language resources, creat
Externí odkaz:
http://arxiv.org/abs/2409.17912
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