Zobrazeno 1 - 10
of 1 425
pro vyhledávání: '"P Bellec"'
The optimal training of a vision transformer for brain encoding depends on three factors: model size, data size, and computational resources. This study investigates these three pillars, focusing on the effects of data scaling, model scaling, and hig
Externí odkaz:
http://arxiv.org/abs/2410.19810
Autor:
Tan, Kai, Bellec, Pierre C.
This paper studies the generalization performance of iterates obtained by Gradient Descent (GD), Stochastic Gradient Descent (SGD) and their proximal variants in high-dimensional robust regression problems. The number of features is comparable to the
Externí odkaz:
http://arxiv.org/abs/2410.02629
We characterize the squared prediction risk of ensemble estimators obtained through subagging (subsample bootstrap aggregating) regularized M-estimators and construct a consistent estimator for the risk. Specifically, we consider a heterogeneous coll
Externí odkaz:
http://arxiv.org/abs/2409.15252
Autor:
Bellec, Pierre C., Tan, Kai
This paper investigates the iterates $\hbb^1,\dots,\hbb^T$ obtained from iterative algorithms in high-dimensional linear regression problems, in the regime where the feature dimension $p$ is comparable with the sample size $n$, i.e., $p \asymp n$. Th
Externí odkaz:
http://arxiv.org/abs/2404.17856
Autor:
Bellec, Pierre C, Koriyama, Takuya
This paper studies the asymptotics of resampling without replacement in the proportional regime where dimension $p$ and sample size $n$ are of the same order. For a given dataset $(X,y)\in \mathbb{R}^{n\times p}\times \mathbb{R}^n$ and fixed subsampl
Externí odkaz:
http://arxiv.org/abs/2404.02070
Brain encoding with neuroimaging data is an established analysis aimed at predicting human brain activity directly from complex stimuli features such as movie frames. Typically, these features are the latent space representation from an artificial ne
Externí odkaz:
http://arxiv.org/abs/2403.19421
Autor:
Masto, Matteo, Favre-Nicolin, Vincent, Leake, Steven, Schülli, Tobias, Richard, Marie-Ingrid, Bellec, Ewen
We propose a deep learning algorithm for the inpainting of Bragg Coherent Diffraction Imaging (BCDI) patterns affected by detector gaps. These regions of missing intensity can compromise the accuracy of reconstruction algorithms, inducing artifacts i
Externí odkaz:
http://arxiv.org/abs/2403.08596
Autor:
Lisboa, Martim, Bellec, Guillaume
Neurons in the brain communicate information via punctual events called spikes. The timing of spikes is thought to carry rich information, but it is not clear how to leverage this in digital systems. We demonstrate that event-based encoding is effici
Externí odkaz:
http://arxiv.org/abs/2402.01571
Autor:
Bellec, Pierre C., Koriyama, Takuya
We consider unregularized robust M-estimators for linear models under Gaussian design and heavy-tailed noise, in the proportional asymptotics regime where the sample size n and the number of features p are both increasing such that $p/n \to \gamma\in
Externí odkaz:
http://arxiv.org/abs/2312.13257
Autor:
Bellec, Pierre C., Koriyama, Takuya
Major progress has been made in the previous decade to characterize the asymptotic behavior of regularized M-estimators in high-dimensional regression problems in the proportional asymptotic regime where the sample size $n$ and the number of features
Externí odkaz:
http://arxiv.org/abs/2312.13254