Mahed Abroshan

7 papers · 2021–2024 · 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 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird 🏆 Keyword Champion (2)

Venues

AAAI (2) AISTATS (2) NeurIPS (2) ICML (1)

Top co-authors

Mohammad Mahdi Khalili (6) Xueru Zhang (3) Seyed-Mohsen Moosavi-Dezfooli (1) Miguel Rodrigues (1) Saumitra Mishra (1) Laura Toni (1) Alireza Abdollahpoorrostam (1) Gholamali Aminian (1) Andrew Elliott (1) Somayeh Sojoudi (1)

Research topics

Machine Learning (7) Application Areas (5) Optimization & Theory (3) Artificial Intelligence (2) Core AI (2) Core Methods (2) Learning Types · Machine Learning (2) Deep Learning (1) Learning Types · Deep Learning (1)

Keywords

bias mitigation (2) equal opportunity (2) fairness constraint (2) supervised learning (2) non-convex optimization (1) entropy minimization (1) interpretable machine learning (1) adversarial training (1) feature importance (1) synthetic data generation (1) model interpretability (1) covariate shift (1) gradient descent (1) generalization error (1) distribution shift (1) convex programming (1) exponential mechanism (1) adversarial attack (1) generalization bound (1) neural network robustness (1)

Papers

Imposing Fairness Constraints in Synthetic Data Generation AISTATS 2024 SuperDeepFool: a new fast and accurate minimal adversarial attack NeurIPS 2024 Loss Balancing for Fair Supervised Learning ICML 2023 Symbolic Metamodels for Interpreting Black-Boxes Using Primitive Functions AAAI 2023 An Information-theoretical Approach to Semi-supervised Learning under Covariate-shift AISTATS 2022 Fair Sequential Selection Using Supervised Learning Models NeurIPS 2021 Improving Fairness and Privacy in Selection Problems AAAI 2021