Sadegh Farhadkhani

9 papers · 2021–2024 · 4 conferences · across top CS/AI conferences

Achievements

🧭 Keyword Pioneer 🌍 Conference Polyglot (4) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (10) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (16)

Conferences

ICML (4) AISTATS (2) NIPS (2) AAAI (1)

Top co-authors

Rachid Guerraoui (8) Lê-Nguyên Hoang (4) Nirupam Gupta (4) Rafael Pinot (4) John Stephan (3) Youssef Allouah (2) Oscar Villemaud (2) Julien Fageot (1) Sébastien Rouault (1) Sasha Voitovych (1)

Keywords

distributed learning (4) byzantine resilience (2) stochastic gradient descent (2) byzantine fault tolerance (2) decentralized learning (2) data poisoning (1) probabilistic modeling (1) robust optimization (1) model aggregation (1) decentralized optimization (1) distributed optimization (1) gradient descent (1) maximum a posteriori (1) exponential family (1) non-convex optimization (1) bradley-terry model (1) collaborative learning (1) model averaging (1) score estimation (1) machine learning (1)

Papers

Generalized Bradley-Terry Models for Score Estimation from Paired Comparisons AAAI 2024

Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates ICML 2024

Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneity AISTATS 2023

On the Strategyproofness of the Geometric Median AISTATS 2023

Epidemic Learning: Boosting Decentralized Learning with Randomized Communication NIPS 2023

Robust Collaborative Learning with Linear Gradient Overhead ICML 2023

An Equivalence Between Data Poisoning and Byzantine Gradient Attacks ICML 2022

Byzantine Machine Learning Made Easy By Resilient Averaging of Momentums ICML 2022

Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning) NIPS 2021