Michał Dereziński
11 papers · 2018–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🏃 Academic Marathon (7) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (5) 🐝 Cross-Pollinator (7)
🐣
Hot Topic Early Bird
🧭
Keyword Pioneer
🏆
Keyword Champion
(2)
🧬
Topic Evolution
🔥
Unstoppable
(5)
💎
Century Club
(11)
🗃️
Keyword Collector
(52)
Conferences
COLT (4)
JMLR (3)
NIPS (2)
IJCAI (1)
UAI (1)
Top co-authors
Keywords
least square
(3)
volume sampling
(3)
second-order method
(3)
linear regression
(2)
hessian oracle
(2)
least squares regression
(2)
importance sampling
(2)
communication efficiency
(2)
determinantal point process
(2)
distributed learning
(2)
unbiased estimator
(2)
nystrom method
(1)
low-rank approximation
(1)
spectral analysis
(1)
distributed optimization
(1)
convex optimization
(1)
strongly convex
(1)
second-order optimization
(1)
matrix approximation
(1)
subset selection
(1)
Papers
Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients
JMLR 2025
Faster Low-Rank Approximation and Kernel Ridge Regression via the Block-Nyström Method
COLT 2025
Distributed Least Squares in Small Space via Sketching and Bias Reduction
NIPS 2024
Stochastic Newton Proximal Extragradient Method
NIPS 2024
Algorithmic Gaussianization through Sketching: Converting Data into Sub-gaussian Random Designs
COLT 2023
Unbiased estimators for random design regression
JMLR 2022
LocalNewton: Reducing communication rounds for distributed learning
UAI 2021
Improved Guarantees and a Multiple-descent Curve for Column Subset Selection and the Nystrom Method (Extended Abstract)
IJCAI 2021
Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression
COLT 2019
Fast determinantal point processes via distortion-free intermediate sampling
COLT 2019
Reverse Iterative Volume Sampling for Linear Regression
JMLR 2018