Zakhar Shumaylov

4 papers · 2021–2025 · 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 🐣 Hot Topic Early Bird

Venues

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

Top co-authors

Carola-Bibiane Schönlieb (3) Subhadip Mukherjee (1) Jeremy Budd (1) Willem Diepeveen (1) I Shumailov (1) Nicolas Papernot (1) Dmitry Kazhdan (1) Georgios Batzolis (1) James Rowbottom (1) Ferdia Sherry (1)

Research topics

Deep Learning (3) Machine Learning (3) Artificial Intelligence (2) Core AI (2) Learning Types · Deep Learning (2) Optimization & Theory (2) Security & Privacy (1) Architectures (1) Learning Types · Machine Learning (1) Privacy (1) Techniques (1)

Keywords

stochastic gradient descent (1) adversarial learning (1) data poisoning (1) adversarial optimization (1) training manipulation (1) intrinsic dimension (1) backdoor attack (1) adversarial attack (1) physics-informed neural network (1) model training (1) poisoning attack (1) lie group (1) equivariant neural network (1) neural operator (1) computed tomography (1) lie algebra (1) kurdyka-łojasiewicz condition (1) data ordering attack (1) geodesics (1) iwcnn (1)

Papers

Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups ICLR 2025 Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows ICML 2025 Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation ICML 2024 Manipulating SGD with Data Ordering Attacks NeurIPS 2021