1 citations · 1 across the 8 of their papers we have counts for
8 papers
Industrializing Prediction-Powered Inference: The GLIDE Library for Reliable GenAI and Agentic Systems Evaluation
Grégoire Martinon, Ibrahim Merad, Mohammed Raki
Reliable evaluation of agentic systems requires unbiased estimates with valid uncertainty, but standard practice navigates between costly human annotation and biased LLM-as-judge p…
Language verY Rare for All
Ibrahim Merad, Amos Wolf, Ziad Mazzawi +1
In the quest to overcome language barriers, encoder-decoder models like NLLB have expanded machine translation to rare languages, with some models (e.g., NLLB 1.3B) even trainable…
Robust Stochastic Optimization via Gradient Quantile Clipping
Ibrahim Merad, Stéphane Gaïffas
We introduce a clipping strategy for Stochastic Gradient Descent (SGD) which uses quantiles of the gradient norm as clipping thresholds. We prove that this new strategy provides a…
Convergence and concentration properties of constant step-size SGD through Markov chains
Ibrahim Merad, Stéphane Gaïffas
We consider the optimization of a smooth and strongly convex objective using constant step-size stochastic gradient descent (SGD) and study its properties through the prism of Mark…
Robust Methods for High-Dimensional Linear Learning
Ibrahim Merad, Stéphane Gaïffas
We propose statistically robust and computationally efficient linear learning methods in the high-dimensional batch setting, where the number of features may exceed the sample…
Robust supervised learning with coordinate gradient descent
Stéphane Gaïffas, Ibrahim Merad
This paper considers the problem of supervised learning with linear methods when both features and labels can be corrupted, either in the form of heavy tailed data and/or corrupted…
WildWood: a new Random Forest algorithm
Stéphane Gaïffas, Ibrahim Merad, Yiyang Yu
We introduce WildWood (WW), a new ensemble algorithm for supervised learning of Random Forest (RF) type. While standard RF algorithms use bootstrap out-of-bag samples to compute ou…
About contrastive unsupervised representation learning for classification and its convergence
Ibrahim Merad, Yiyang Yu, Emmanuel Bacry +1
Contrastive representation learning has been recently proved to be very efficient for self-supervised training. These methods have been successfully used to train encoders which pe…