Filip Hanzely
11 papers · 2018–2021 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
🌍 Conference Polyglot (5) 🧭 Keyword Pioneer 🗺️ Taxonomy Completionist (16) 🌉 Interdisciplinary Bridge 🐣 Hot Topic Early Bird
🐝
Cross-Pollinator
(14)
🤝
Dynamic Duo
(11)
💎
Century Club
(11)
🚀
Conference Pioneer
⚡
Prolific Year
(5)
Conferences
NIPS (4)
AISTATS (3)
ICML (2)
AAAI (1)
UAI (1)
Top co-authors
Keywords
variance reduction
(4)
coordinate descent
(4)
distributed optimization
(2)
convex optimization
(2)
local sgd
(2)
federated learning
(2)
stochastic gradient descent
(2)
stochastic optimization
(2)
empirical risk minimization
(1)
low-rank decomposition
(1)
finite-sum optimization
(1)
shadow removal
(1)
low-rank recovery
(1)
importance sampling
(1)
distributed learning
(1)
strongly convex
(1)
communication complexity
(1)
gradient descent
(1)
convergence analysis
(1)
nonconvex optimization
(1)
Papers
Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization
NIPS 2021
Local SGD: Unified Theory and New Efficient Methods
AISTATS 2021
Lower Bounds and Optimal Algorithms for Personalized Federated Learning
NIPS 2020
A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent
AISTATS 2020
99% of Worker-Master Communication in Distributed Optimization Is Not Needed
UAI 2020
Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems
ICML 2020
Stochastic Subspace Cubic Newton Method
ICML 2020
Accelerated Coordinate Descent with Arbitrary Sampling and Best Rates for Minibatches
AISTATS 2019
A Nonconvex Projection Method for Robust PCA
AAAI 2019
Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization
NIPS 2018
SEGA: Variance Reduction via Gradient Sketching
NIPS 2018