Bogdan Kulynych

4 papers · 2022–2024 · 3 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 👑 Triple Crown

Venues

NeurIPS (2) ICLR (1) ICML (1)

Top co-authors

Carmela Troncoso (2) Michael Gastpar (1) Theresa Stadler (1) Yaodong Yu (1) Tsui-Wei Weng (1) Georgios Kaissis (1) Nicolas Papernot (1) Avni Kothari (1) Jarosław Błasiok (1) Yao-Yuan Yang (1)

Research topics

Machine Learning (4) Artificial Intelligence (3) Application Areas (3) Core AI (3) Computer Science (1) Deep Learning (1) Core Methods (1) Foundations (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1)

Keywords

differential privacy (2) stochastic gradient descent (1) adversarial training (1) feature representation (1) feature space (1) robust overfitting (1) sensitive information (1) inference attack (1) model fairness (1) reachable set (1) distributional generalization (1) sgd stability (1) noise calibration (1) attack risk (1) recourse verification (1) trade-off (1) utility (1) leakage (1) privacy-preserving machine learning (1) least-privilege learning (1)

Papers

Attack-Aware Noise Calibration for Differential Privacy NeurIPS 2024 Prediction without Preclusion: Recourse Verification with Reachable Sets ICLR 2024 The Fundamental Limits of Least-Privilege Learning ICML 2024 What You See is What You Get: Principled Deep Learning via Distributional Generalization NeurIPS 2022