Kaja Gruntkowska

4 papers · 2023–2024 · 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 · Silver 🗺️ Taxonomy Completionist (11)

Venues

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

Top co-authors

Peter Richtarik (4) Alexander Tyurin (3) Eduard Gorbunov (1) Ahmad Rammal (1) Nikita Fedin (1)

Research topics

Machine Learning (4) Optimization & Theory · Machine Learning (4) Mathematics & Optimization (2) Optimization (2) Artificial Intelligence (1) Computer Science (1) Deep Learning (1) Learning Paradigms (1) Optimization & Theory · Deep Learning (1) Systems (1)

Keywords

distributed optimization (4) non-convex optimization (3) stochastic gradient (2) communication compression (2) bidirectional compression (2) communication complexity (2) asynchronous computation (1) asynchronous optimization (1) time complexity (1) gradient compression (1) byzantine fault tolerance (1) byzantine robustness (1) stochastic method (1) error feedback (1) federated learning (1) downlink compression (1) stochastic optimization (1) stochastic gradient descent (1) finite-sum optimization (1) distributed learning (1)

Papers

Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates AISTATS 2024 Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations NeurIPS 2024 Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity NeurIPS 2024 EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compression ICML 2023