3 citations · 7 across the 13 of their papers we have counts for
13 papers
A Bregman firmly nonexpansive proximal operator for baryconvex optimization
Mastane Achab
We present a generalization of the proximal operator defined through a convex combination of convex objectives, where the coefficients are updated in a minimax fashion. We prove th…
Investigating Regularization of Self-Play Language Models
Reda Alami, Abdalgader Abubaker, Mastane Achab +2
This paper explores the effects of various forms of regularization in the context of language model alignment via self-play. While both reinforcement learning from human feedback (…
A Risk-Averse Framework for Non-Stationary Stochastic Multi-Armed Bandits
Reda Alami, Mohammed Mahfoud, Mastane Achab
In a typical stochastic multi-armed bandit problem, the objective is often to maximize the expected sum of rewards over some time horizon . While the choice of a strategy that a…
Deep Reinforcement Learning Algorithms for Hybrid V2X Communication: A Benchmarking Study
Fouzi Boukhalfa, Reda Alami, Mastane Achab +2
In today's era, autonomous vehicles demand a safety level on par with aircraft. Taking a cue from the aerospace industry, which relies on redundancy to achieve high reliability, th…
Beyond Log-Concavity: Theory and Algorithm for Sum-Log-Concave Optimization
Mastane Achab
This paper extends the classic theory of convex optimization to the minimization of functions that are equal to the negated logarithm of what we term as a sum-log-concave function,…
A Nested Matrix-Tensor Model for Noisy Multi-view Clustering
Mohamed El Amine Seddik, Mastane Achab, Henrique Goulart +1
In this paper, we propose a nested matrix-tensor model which extends the spiked rank-one tensor model of order three. This model is particularly motivated by a multi-view clusterin…
One-Step Distributional Reinforcement Learning
Mastane Achab, Reda Alami, Yasser Abdelaziz Dahou Djilali +2
Reinforcement learning (RL) allows an agent interacting sequentially with an environment to maximize its long-term expected return. In the distributional RL (DistrRL) paradigm, the…
Robustness and risk management via distributional dynamic programming
Mastane Achab, Gergely Neu
In dynamic programming (DP) and reinforcement learning (RL), an agent learns to act optimally in terms of expected long-term return by sequentially interacting with its environment…
Weighted Empirical Risk Minimization: Sample Selection Bias Correction based on Importance Sampling
Robin Vogel, Mastane Achab, Stéphan Clémençon +1
We consider statistical learning problems, when the distribution of the training observations differs from the distribution involved in the risk o…
Dimensionality Reduction and (Bucket) Ranking: a Mass Transportation Approach
Mastane Achab, Anna Korba, Stephan Clémençon
Whereas most dimensionality reduction techniques (e.g. PCA, ICA, NMF) for multivariate data essentially rely on linear algebra to a certain extent, summarizing ranking data, viewed…
Profitable Bandits
Mastane Achab, Stephan Clémençon, Aurélien Garivier
Originally motivated by default risk management applications, this paper investigates a novel problem, referred to as the profitable bandit problem here. At each step, an agent cho…
Ranking Data with Continuous Labels through Oriented Recursive Partitions
Stephan Clémençon, Mastane Achab
We formulate a supervised learning problem, referred to as continuous ranking, where a continuous real-valued label Y is assigned to an observable r.v. X taking its values in a fea…
Max K-armed bandit: On the ExtremeHunter algorithm and beyond
Mastane Achab, Stephan Clémençon, Aurélien Garivier +2
This paper is devoted to the study of the max K-armed bandit problem, which consists in sequentially allocating resources in order to detect extreme values. Our contribution is two…