Shaddin Dughmi

8 papers · 2015–2026 · 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 🏃 Academic Marathon · Half 🌉 Interdisciplinary Bridge · Bronze ❓ The Questioner (2)

Venues

COLT (4) ALT (2) IJCAI (1) NeurIPS (1)

Top co-authors

Julian Asilis (5) Siddartha Devic (4) Vatsal Sharan (4) Shang-Hua Teng (4) Haifeng Xu (1) Arunesh Sinha (1) Yusuf Hakan Kalayci (1) Albert Xing Jiang (1) Sky Jafar (1) Grayson York (1)

Research topics

Machine Learning (6) Optimization & Theory (6) Deep Learning (2) Core Methods (2) Learning Types · Deep Learning (2) Mathematics & Optimization (1) Learning Types · Machine Learning (1) Mathematics (1)

Keywords

transductive learning (4) sample complexity (4) pac learning (3) multi-class classification (2) empirical risk minimization (2) rademacher complexity (1) structural risk minimization (1) multiclass learning (1) hypothesis class (1) marginal distribution (1) one-inclusion graph (1) local regularization (1) local regularizer (1) pac model (1) instance-optimal learning (1) error (1) cryptographic secret sharing (1) learning theory (1) learnable (1) semi-supervised learning (1)

Papers

Relatively Smart: A New Approach for Instance-Optimal Learning COLT 2026 Is Transductive Learning Equivalent to PAC Learning? ALT 2025 Local Regularizers Are Not Transductive Learners COLT 2025 Proper Learnability and the Role of Unlabeled Data ALT 2025 Open Problem: Can Local Regularization Learn All Multiclass Problems? COLT 2024 Regularization and Optimal Multiclass Learning COLT 2024 Transductive Learning is Compact NeurIPS 2024 Security Games with Information Leakage: Modeling and Computation IJCAI 2015