Imad Aouali

6 papers · 2023–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (16)

Venues

AISTATS (3) ICML (1) NeurIPS (1) UAI (1)

Top co-authors

Victor-Emmanuel Brunel (3) Anna Korba (3) David Rohde (3) Pierre Alquier (1) Otmane Sakhi (1) Nicolas Nguyen (1) Nicolas Chopin (1) Claire Vernade (1) András György (1) Sumeet Katariya (1)

Research topics

Machine Learning (6) Optimization & Theory (6) Reinforcement Learning (4) Methods (4) Learning Types (3) Artificial Intelligence (2) Application Areas (1) Bayesian & Probabilistic · Machine Learning (1) Bayesian & Probabilistic · Artificial Intelligence (1) Core AI (1) Learning Paradigms (1)

Keywords

off-policy learning (3) off-policy evaluation (2) importance sampling (2) contextual bandit (2) prior information (1) importance weighting (1) online learning (1) policy selection (1) bayesian optimization (1) best arm identification (1) thompson sampling (1) multi-armed bandit (1) generalization bound (1) pac-bayesian bound (1) logging policy (1) pac-bayes bound (1) pessimistic optimization (1) pessimistic estimation (1) concentration bound (1) bandit learning (1)

Papers

Bayesian Off-Policy Evaluation and Learning for Large Action Spaces AISTATS 2025 Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits AISTATS 2025 Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning NeurIPS 2024 Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling UAI 2024 Exponential Smoothing for Off-Policy Learning ICML 2023 Mixed-Effect Thompson Sampling AISTATS 2023