Michal Derezinski

Publication Activity (10 Years)

Years Active: 2014-2024
Publications (10 Years): 72

Top Topics

Linear Regression

Point Processes

Superlinear Convergence

Top Venues

Publications

Sachin Garg, Kevin Tan, Michal Derezinski
Distributed Least Squares in Small Space via Sketching and Bias Reduction. CoRR (2024)
Shabarish Chenakkod, Michal Derezinski, Xiaoyu Dong, Mark Rudelson
Optimal Embedding Dimension for Sparse Subspace Embeddings. STOC (2024)
Michal Derezinski, Jiaming Yang
Solving Dense Linear Systems Faster Than via Preconditioning. STOC (2024)
Michal Derezinski, Michael W. Mahoney
Recent and Upcoming Developments in Randomized Numerical Linear Algebra for Machine Learning. KDD (2024)
Ruichen Jiang, Michal Derezinski, Aryan Mokhtari
Stochastic Newton Proximal Extragradient Method. CoRR (2024)
Michal Derezinski, Michael W. Mahoney
Recent and Upcoming Developments in Randomized Numerical Linear Algebra for Machine Learning. CoRR (2024)
Yongyi Yang, Jiaming Yang, Wei Hu, Michal Derezinski
HERTA: A High-Efficiency and Rigorous Training Algorithm for Unfolded Graph Neural Networks. CoRR (2024)
Sachin Garg, Albert S. Berahas, Michal Derezinski
Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients. CoRR (2024)
Michal Derezinski, Christopher Musco, Jiaming Yang
Faster Linear Systems and Matrix Norm Approximation via Multi-level Sketched Preconditioning. CoRR (2024)
Michal Derezinski, Elizaveta Rebrova
Sharp Analysis of Sketch-and-Project Methods via a Connection to Randomized Singular Value Decomposition. SIAM J. Math. Data Sci. 6 (1) (2024)
Michal Derezinski, Daniel LeJeune, Deanna Needell, Elizaveta Rebrova
Fine-grained Analysis and Faster Algorithms for Iteratively Solving Linear Systems. CoRR (2024)
Younghyun Cho, James Weldon Demmel, Michal Derezinski, Haoyun Li, Hengrui Luo, Michael W. Mahoney, Riley J. Murray
Surrogate-based Autotuning for Randomized Sketching Algorithms in Regression Problems. CoRR (2023)
Riley Murray, James Demmel, Michael W. Mahoney, N. Benjamin Erichson, Maksim Melnichenko, Osman Asif Malik, Laura Grigori, Piotr Luszczek, Michal Derezinski, Miles E. Lopes, Tianyu Liang, Hengrui Luo, Jack J. Dongarra
Randomized Numerical Linear Algebra : A Perspective on the Field With an Eye to Software. CoRR (2023)
Shabarish Chenakkod, Michal Derezinski, Xiaoyu Dong, Mark Rudelson
Optimal Embedding Dimension for Sparse Subspace Embeddings. CoRR (2023)
Sen Na, Michal Derezinski, Michael W. Mahoney
Hessian averaging in stochastic Newton methods achieves superlinear convergence. Math. Program. 201 (1) (2023)
Michal Derezinski
Algorithmic Gaussianization through Sketching: Converting Data into Sub-gaussian Random Designs. COLT (2023)
Michal Derezinski, Jiaming Yang
Solving Dense Linear Systems Faster than via Preconditioning. CoRR (2023)
Michal Derezinski
Stochastic Variance-Reduced Newton: Accelerating Finite-Sum Minimization with Large Batches. CoRR (2022)
Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
Unbiased estimators for random design regression. J. Mach. Learn. Res. 23 (2022)
Michal Derezinski
Algorithmic Gaussianization through Sketching: Converting Data into Sub-gaussian Random Designs. CoRR (2022)
Nima Anari, Michal Derezinski, Thuy-Duong Vuong, Elizabeth Yang
Domain Sparsification of Discrete Distributions Using Entropic Independence. ITCS (2022)
Sen Na, Michal Derezinski, Michael W. Mahoney
Hessian Averaging in Stochastic Newton Methods Achieves Superlinear Convergence. CoRR (2022)
Michal Derezinski, Elizaveta Rebrova
Sharp Analysis of Sketch-and-Project Methods via a Connection to Randomized Singular Value Decomposition. CoRR (2022)
Michal Derezinski, Zhenyu Liao, Edgar Dobriban, Michael W. Mahoney
Sparse sketches with small inversion bias. COLT (2021)
Xue Chen, Michal Derezinski
Query complexity of least absolute deviation regression via robust uniform convergence. COLT (2021)
Xue Chen, Michal Derezinski
Query Complexity of Least Absolute Deviation Regression via Robust Uniform Convergence. CoRR (2021)
Vipul Gupta, Avishek Ghosh, Michal Derezinski, Rajiv Khanna, Kannan Ramchandran, Michael W. Mahoney
LocalNewton: Reducing Communication Bottleneck for Distributed Learning. CoRR (2021)
Michal Derezinski, Jonathan Lacotte, Mert Pilanci, Michael W. Mahoney
Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update. NeurIPS (2021)
Vipul Gupta, Avishek Ghosh, Michal Derezinski, Rajiv Khanna, Kannan Ramchandran, Michael W. Mahoney
LocalNewton: Reducing communication rounds for distributed learning. UAI (2021)
Nima Anari, Michal Derezinski, Thuy-Duong Vuong, Elizabeth Yang
Domain Sparsification of Discrete Distributions using Entropic Independence. CoRR (2021)
Michal Derezinski, Rajiv Khanna, Michael W. Mahoney
Improved Guarantees and a Multiple-descent Curve for Column Subset Selection and the Nystrom Method (Extended Abstract). IJCAI (2021)
Michal Derezinski, Jonathan Lacotte, Mert Pilanci, Michael W. Mahoney
Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update. CoRR (2021)
Michal Derezinski, Feynman T. Liang, Michael W. Mahoney
Bayesian experimental design using regularized determinantal point processes. AISTATS (2020)
Michal Derezinski, Feynman T. Liang, Michael W. Mahoney
Exact expressions for double descent and implicit regularization via surrogate random design. NeurIPS (2020)
Daniele Calandriello, Michal Derezinski, Michal Valko
Sampling from a k-DPP without looking at all items. CoRR (2020)
Michal Derezinski, Feynman T. Liang, Zhenyu Liao, Michael W. Mahoney
Precise expressions for random projections: Low-rank approximation and randomized Newton. CoRR (2020)
Michal Derezinski, Michael W. Mahoney
Determinantal Point Processes in Randomized Numerical Linear Algebra. CoRR (2020)
Michal Derezinski, Rajiv Khanna, Michael W. Mahoney
Improved guarantees and a multiple-descent curve for the Column Subset Selection Problem and the Nyström method. CoRR (2020)
Nima Anari, Michal Derezinski
Isotropy and Log-Concave Polynomials: Accelerated Sampling and High-Precision Counting of Matroid Bases. FOCS (2020)
Daniele Calandriello, Michal Derezinski, Michal Valko
Sampling from a k-DPP without looking at all items. NeurIPS (2020)
Michal Derezinski, Burak Bartan, Mert Pilanci, Michael W. Mahoney
Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization. NeurIPS (2020)
Michal Derezinski, Burak Bartan, Mert Pilanci, Michael W. Mahoney
Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization. CoRR (2020)
Michal Derezinski, Rajiv Khanna, Michael W. Mahoney
Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nystrom method. NeurIPS (2020)
Nima Anari, Michal Derezinski
Isotropy and Log-Concave Polynomials: Accelerated Sampling and High-Precision Counting of Matroid Bases. CoRR (2020)
Michal Derezinski, Zhenyu Liao, Edgar Dobriban, Michael W. Mahoney
Sparse sketches with small inversion bias. CoRR (2020)
Michal Derezinski, Feynman T. Liang, Zhenyu Liao, Michael W. Mahoney
Precise expressions for random projections: Low-rank approximation and randomized Newton. NeurIPS (2020)
Mojmir Mutny, Michal Derezinski, Andreas Krause
Convergence Analysis of Block Coordinate Algorithms with Determinantal Sampling. AISTATS (2020)
Michal Derezinski
Fast determinantal point processes via distortion-free intermediate sampling. COLT (2019)
Michal Derezinski, Feynman T. Liang, Michael W. Mahoney
Bayesian experimental design using regularized determinantal point processes. CoRR (2019)
Michal Derezinski, Kenneth L. Clarkson, Michael W. Mahoney, Manfred K. Warmuth
Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression. COLT (2019)
Michal Derezinski, Michael W. Mahoney
Distributed estimation of the inverse Hessian by determinantal averaging. CoRR (2019)
Michal Derezinski, Kenneth L. Clarkson, Michael W. Mahoney, Manfred K. Warmuth
Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression. CoRR (2019)
Michal Derezinski, Daniele Calandriello, Michal Valko
Exact sampling of determinantal point processes with sublinear time preprocessing. CoRR (2019)
Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
Correcting the bias in least squares regression with volume-rescaled sampling. AISTATS (2019)
Michal Derezinski, Michael W. Mahoney
Distributed estimation of the inverse Hessian by determinantal averaging. NeurIPS (2019)
Michal Derezinski, Feynman T. Liang, Michael W. Mahoney
Exact expressions for double descent and implicit regularization via surrogate random design. CoRR (2019)
Michal Derezinski, Daniele Calandriello, Michal Valko
Exact sampling of determinantal point processes with sublinear time preprocessing. NeurIPS (2019)
Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
Unbiased estimators for random design regression. CoRR (2019)
Mojmír Mutný, Michal Derezinski, Andreas Krause
Convergence Analysis of the Randomized Newton Method with Determinantal Sampling. CoRR (2019)
Michal Derezinski, Manfred K. Warmuth
Reverse Iterative Volume Sampling for Linear Regression. J. Mach. Learn. Res. 19 (2018)
Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
Tail bounds for volume sampled linear regression. CoRR (2018)
Michal Derezinski, Manfred K. Warmuth, Daniel J. Hsu
Leveraged volume sampling for linear regression. NeurIPS (2018)
Michal Derezinski
Fast determinantal point processes via distortion-free intermediate sampling. CoRR (2018)
Michal Derezinski, Khashayar Rohanimanesh, Aamer Hydrie
Discovering Surprising Documents with Context-Aware Word Representations. IUI (2018)
Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
Correcting the bias in least squares regression with volume-rescaled sampling. CoRR (2018)
Michal Derezinski, Manfred K. Warmuth
Subsampling for Ridge Regression via Regularized Volume Sampling. AISTATS (2018)
Michal Derezinski, Dhruv Mahajan, S. Sathiya Keerthi, S. V. N. Vishwanathan, Markus Weimer
Batch-Expansion Training: An Efficient Optimization Framework. AISTATS (2018)
Michal Derezinski, Manfred K. Warmuth
Reverse iterative volume sampling for linear regression. CoRR (2018)
Michal Derezinski, Dhruv Mahajan, S. Sathiya Keerthi, S. V. N. Vishwanathan, Markus Weimer
Batch-Expansion Training: An Efficient Optimization Paradigm for Machine Learning. CoRR (2017)
Michal Derezinski, Manfred K. Warmuth
Unbiased estimates for linear regression via volume sampling. NIPS (2017)
Michal Derezinski, Manfred K. Warmuth
Unbiased estimates for linear regression via volume sampling. CoRR (2017)
Michal Derezinski, Manfred K. Warmuth
Subsampling for Ridge Regression via Regularized Volume Sampling. CoRR (2017)
Michal Derezinski, Manfred K. Warmuth
The limits of squared Euclidean distance regularization. NIPS (2014)