Scholar
Michał Dereziński
Google Scholar ID: qhP66JAAAAAJ
Assistant Professor at University of Michigan
machine learning
optimization
statistics
randomized algorithms
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,279
H-index
24
i10-index
33
Publications
20
Co-authors
56
list available
Publications
12 items
Inference for Newton Methods with Accelerated Sketch-and-Project via Random Scaling
2026
Cited
0
How AI settled the complexity of the oldest SGD algorithm
2026
Cited
0
Debiasing Random Oblique Projections for Subsampled OLS and Fast CUR in High Dimensions
2026
Cited
0
Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration
2026
Cited
0
Accelerating Power Method with Fast Sketching for Stronger Low-Rank Approximation
2026
Cited
0
Well-Conditioned Oblivious Perturbations in Linear Space
2026
Cited
0
Towards Universal Convergence of Backward Error in Linear System Solvers
2026
Cited
0
Last-Iterate Convergence of Randomized Kaczmarz and SGD with Greedy Step Size
2026
Cited
0
Load more
Co-authors
14 total
Michael Mahoney
Professor of Statistics, UC Berkeley
James W DEMMEL
Professor of EECS and Mathematics, UC Berkeley
Daniel Hsu
Columbia University
Rajiv Khanna
Assistant Prof, PurdueCS
Jiaming Yang
University of Michigan
Michal Valko
Chief Models Officer @ Stealth Startup, Inria & MVA - Ex: Llama at Meta; Gemini and BYOL @ Deepmind
Daniele Calandriello
Research Scientist, DeepMind
Elizaveta Rebrova
Princeton ORFE
