Michal Derezinski

94 papers A* 26A 8Journal 57Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	A*	`conf`	Approaching Optimality for Solving Dense Linear Systems with Low-Rank Structure. SODA Michal Derezinski, Aaron Sidford
2026	J	`jnl`	Linear Systems and Eigenvalue Problems: Open Questions from a Simons Workshop. CoRR Noah Amsel, Yves Baumann, Paul Beckman, Peter Bürgisser, Chris Camaño, Tyler Chen, Edmond Chow, Anil Damle, Michal Derezinski, Mark Embree, Ethan N. Epperly, Robert D. Falgout, Mark Fornace, Anne Greenbaum, Chen Greif, Diana Halikias, Zhen Huang, Elias Jarlebring, Yiannis Koutis, Daniel Kressner, Rasmus Kyng, Jörg Liesen, Jackie Lok, Raphael A. Meyer, Yuji Nakatsukasa, Kate Pearce, Richard Peng, David Persson, Elizaveta Rebrova, Ryan Schneider, Rikhav Shah, Edgar Solomonik, Nikhil Srivastava, Alex Townsend, Robert J. Webber, Jess Williams
2026	A*	`conf`	Optimal Subspace Embeddings: Resolving Nelson-Nguyen Conjecture Up to Sub-Polylogarithmic Factors. SODA Shabarish Chenakkod, Michal Derezinski, Xiaoyu Dong
2026	J	`jnl`	The matrix-vector complexity of Ax=b. CoRR Michal Derezinski, Ethan N. Epperly, Raphael A. Meyer
2025	J	`jnl`	Approaching Optimality for Solving Dense Linear Systems with Low-Rank Structure. CoRR Michal Derezinski, Aaron Sidford
2025	A*	`conf`	Faster Linear Systems and Matrix Norm Approximation via Multi-level Sketched Preconditioning. SODA Michal Derezinski, Christopher Musco, Jiaming Yang
2025	A*	`conf`	Faster Low-Rank Approximation and Kernel Ridge Regression via the Block-Nyström Method. COLT Sachin Garg, Michal Derezinski
2025	J	`jnl`	Faster Low-Rank Approximation and Kernel Ridge Regression via the Block-Nyström Method. CoRR Sachin Garg, Michal Derezinski
2025	J	`jnl`	Fine-grained Analysis and Faster Algorithms for Iteratively Solving Linear Systems. J. Mach. Learn. Res. Michal Derezinski, Daniel LeJeune, Deanna Needell, Elizaveta Rebrova
2025	A*	`conf`	Optimal Oblivious Subspace Embeddings with Near-Optimal Sparsity. ICALP Shabarish Chenakkod, Michal Derezinski, Xiaoyu Dong
2025	J	`jnl`	Optimal Subspace Embeddings: Resolving Nelson-Nguyen Conjecture Up to Sub-Polylogarithmic Factors. CoRR Shabarish Chenakkod, Michal Derezinski, Xiaoyu Dong
2025	J	`jnl`	Randomized Kaczmarz Methods with Beyond-Krylov Convergence. CoRR Michal Derezinski, Deanna Needell, Elizaveta Rebrova, Jiaming Yang
2025	J	`jnl`	Randomized Kaczmarz Methods with Beyond-Krylov Convergence. SIAM J. Matrix Anal. Appl. Michal Derezinski, Deanna Needell, Elizaveta Rebrova, Jiaming Yang
2025	J	`jnl`	Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients. J. Mach. Learn. Res. Sachin Garg, Albert S. Berahas, Michal Derezinski
2025	J	`jnl`	Stochastic Variance-Reduced Newton: Accelerating Finite-Sum Minimization with Large Batches. Trans. Mach. Learn. Res. Michal Derezinski
2025	J	`jnl`	Surrogate-Based Autotuning for Randomized Sketching Algorithms in Regression Problems. SIAM J. Matrix Anal. Appl. Younghyun Cho, James Demmel, Michal Derezinski, Haoyun Li, Hengrui Luo, Michael W. Mahoney, Riley Murray
2025	J	`jnl`	Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project. CoRR Pratik Rathore, Zachary Frangella, Sachin Garg, Shaghayegh Fazliani, Michal Derezinski, Madeleine Udell
2024	A*	`conf`	Distributed Least Squares in Small Space via Sketching and Bias Reduction. NeurIPS Sachin Garg, Kevin Tan, Michal Derezinski
2024	J	`jnl`	Distributed Least Squares in Small Space via Sketching and Bias Reduction. CoRR Sachin Garg, Kevin Tan, Michal Derezinski
2024	J	`jnl`	Faster Linear Systems and Matrix Norm Approximation via Multi-level Sketched Preconditioning. CoRR Michal Derezinski, Christopher Musco, Jiaming Yang
2024	J	`jnl`	Fine-grained Analysis and Faster Algorithms for Iteratively Solving Linear Systems. CoRR Michal Derezinski, Daniel LeJeune, Deanna Needell, Elizaveta Rebrova
2024	J	`jnl`	HERTA: A High-Efficiency and Rigorous Training Algorithm for Unfolded Graph Neural Networks. CoRR Yongyi Yang, Jiaming Yang, Wei Hu, Michal Derezinski
2024	A*	`conf`	Optimal Embedding Dimension for Sparse Subspace Embeddings. STOC Shabarish Chenakkod, Michal Derezinski, Xiaoyu Dong, Mark Rudelson
2024	J	`jnl`	Optimal Oblivious Subspace Embeddings with Near-optimal Sparsity. CoRR Shabarish Chenakkod, Michal Derezinski, Xiaoyu Dong
2024	A*	`conf`	Recent and Upcoming Developments in Randomized Numerical Linear Algebra for Machine Learning. KDD Michal Derezinski, Michael W. Mahoney
2024	J	`jnl`	Recent and Upcoming Developments in Randomized Numerical Linear Algebra for Machine Learning. CoRR Michal Derezinski, Michael W. Mahoney
2024	J	`jnl`	Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients. CoRR Sachin Garg, Albert S. Berahas, Michal Derezinski
2024	J	`jnl`	Sharp Analysis of Sketch-and-Project Methods via a Connection to Randomized Singular Value Decomposition. SIAM J. Math. Data Sci. Michal Derezinski, Elizaveta Rebrova
2024	A*	`conf`	Solving Dense Linear Systems Faster Than via Preconditioning. STOC Michal Derezinski, Jiaming Yang
2024	A*	`conf`	Stochastic Newton Proximal Extragradient Method. NeurIPS Ruichen Jiang, Michal Derezinski, Aryan Mokhtari
2024	J	`jnl`	Stochastic Newton Proximal Extragradient Method. CoRR Ruichen Jiang, Michal Derezinski, Aryan Mokhtari
2023	A*	`conf`	Algorithmic Gaussianization through Sketching: Converting Data into Sub-gaussian Random Designs. COLT Michal Derezinski
2023	J	`jnl`	Hessian averaging in stochastic Newton methods achieves superlinear convergence. Math. Program. Sen Na, Michal Derezinski, Michael W. Mahoney
2023	J	`jnl`	Optimal Embedding Dimension for Sparse Subspace Embeddings. CoRR Shabarish Chenakkod, Michal Derezinski, Xiaoyu Dong, Mark Rudelson
2023	J	`jnl`	Randomized Numerical Linear Algebra : A Perspective on the Field With an Eye to Software. CoRR 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
2023	J	`jnl`	Solving Dense Linear Systems Faster than via Preconditioning. CoRR Michal Derezinski, Jiaming Yang
2023	J	`jnl`	Surrogate-based Autotuning for Randomized Sketching Algorithms in Regression Problems. CoRR Younghyun Cho, James Weldon Demmel, Michal Derezinski, Haoyun Li, Hengrui Luo, Michael W. Mahoney, Riley J. Murray
2022	J	`jnl`	Algorithmic Gaussianization through Sketching: Converting Data into Sub-gaussian Random Designs. CoRR Michal Derezinski
2022	A	`conf`	Domain Sparsification of Discrete Distributions Using Entropic Independence. ITCS Nima Anari, Michal Derezinski, Thuy-Duong Vuong, Elizabeth Yang
2022	J	`jnl`	Hessian Averaging in Stochastic Newton Methods Achieves Superlinear Convergence. CoRR Sen Na, Michal Derezinski, Michael W. Mahoney
2022	J	`jnl`	Sharp Analysis of Sketch-and-Project Methods via a Connection to Randomized Singular Value Decomposition. CoRR Michal Derezinski, Elizaveta Rebrova
2022	J	`jnl`	Stochastic Variance-Reduced Newton: Accelerating Finite-Sum Minimization with Large Batches. CoRR Michal Derezinski
2022	J	`jnl`	Unbiased estimators for random design regression. J. Mach. Learn. Res. Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
2021	J	`jnl`	Domain Sparsification of Discrete Distributions using Entropic Independence. CoRR Nima Anari, Michal Derezinski, Thuy-Duong Vuong, Elizabeth Yang
2021	A*	`conf`	Improved Guarantees and a Multiple-descent Curve for Column Subset Selection and the Nystrom Method (Extended Abstract). IJCAI Michal Derezinski, Rajiv Khanna, Michael W. Mahoney
2021	J	`jnl`	LocalNewton: Reducing Communication Bottleneck for Distributed Learning. CoRR Vipul Gupta, Avishek Ghosh, Michal Derezinski, Rajiv Khanna, Kannan Ramchandran, Michael W. Mahoney
2021	A	`conf`	LocalNewton: Reducing communication rounds for distributed learning. UAI Vipul Gupta, Avishek Ghosh, Michal Derezinski, Rajiv Khanna, Kannan Ramchandran, Michael W. Mahoney
2021	A*	`conf`	Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update. NeurIPS Michal Derezinski, Jonathan Lacotte, Mert Pilanci, Michael W. Mahoney
2021	J	`jnl`	Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update. CoRR Michal Derezinski, Jonathan Lacotte, Mert Pilanci, Michael W. Mahoney
2021	J	`jnl`	Query Complexity of Least Absolute Deviation Regression via Robust Uniform Convergence. CoRR Xue Chen, Michal Derezinski
2021	A*	`conf`	Query complexity of least absolute deviation regression via robust uniform convergence. COLT Xue Chen, Michal Derezinski
2021	A*	`conf`	Sparse sketches with small inversion bias. COLT Michal Derezinski, Zhenyu Liao, Edgar Dobriban, Michael W. Mahoney
2020	A	`conf`	Bayesian experimental design using regularized determinantal point processes. AISTATS Michal Derezinski, Feynman T. Liang, Michael W. Mahoney
2020	A	`conf`	Convergence Analysis of Block Coordinate Algorithms with Determinantal Sampling. AISTATS Mojmir Mutny, Michal Derezinski, Andreas Krause
2020	A*	`conf`	Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization. NeurIPS Michal Derezinski, Burak Bartan, Mert Pilanci, Michael W. Mahoney
2020	J	`jnl`	Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization. CoRR Michal Derezinski, Burak Bartan, Mert Pilanci, Michael W. Mahoney
2020	J	`jnl`	Determinantal Point Processes in Randomized Numerical Linear Algebra. CoRR Michal Derezinski, Michael W. Mahoney
2020	A*	`conf`	Exact expressions for double descent and implicit regularization via surrogate random design. NeurIPS Michal Derezinski, Feynman T. Liang, Michael W. Mahoney
2020	A*	`conf`	Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nystrom method. NeurIPS Michal Derezinski, Rajiv Khanna, Michael W. Mahoney
2020	J	`jnl`	Improved guarantees and a multiple-descent curve for the Column Subset Selection Problem and the Nyström method. CoRR Michal Derezinski, Rajiv Khanna, Michael W. Mahoney
2020	A*	`conf`	Isotropy and Log-Concave Polynomials: Accelerated Sampling and High-Precision Counting of Matroid Bases. FOCS Nima Anari, Michal Derezinski
2020	J	`jnl`	Isotropy and Log-Concave Polynomials: Accelerated Sampling and High-Precision Counting of Matroid Bases. CoRR Nima Anari, Michal Derezinski
2020	A*	`conf`	Precise expressions for random projections: Low-rank approximation and randomized Newton. NeurIPS Michal Derezinski, Feynman T. Liang, Zhenyu Liao, Michael W. Mahoney
2020	J	`jnl`	Precise expressions for random projections: Low-rank approximation and randomized Newton. CoRR Michal Derezinski, Feynman T. Liang, Zhenyu Liao, Michael W. Mahoney
2020	A*	`conf`	Sampling from a k-DPP without looking at all items. NeurIPS Daniele Calandriello, Michal Derezinski, Michal Valko
2020	J	`jnl`	Sampling from a k-DPP without looking at all items. CoRR Daniele Calandriello, Michal Derezinski, Michal Valko
2020	J	`jnl`	Sparse sketches with small inversion bias. CoRR Michal Derezinski, Zhenyu Liao, Edgar Dobriban, Michael W. Mahoney
2019	J	`jnl`	Bayesian experimental design using regularized determinantal point processes. CoRR Michal Derezinski, Feynman T. Liang, Michael W. Mahoney
2019	J	`jnl`	Convergence Analysis of the Randomized Newton Method with Determinantal Sampling. CoRR Mojmír Mutný, Michal Derezinski, Andreas Krause
2019	A	`conf`	Correcting the bias in least squares regression with volume-rescaled sampling. AISTATS Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
2019	A*	`conf`	Distributed estimation of the inverse Hessian by determinantal averaging. NeurIPS Michal Derezinski, Michael W. Mahoney
2019	J	`jnl`	Distributed estimation of the inverse Hessian by determinantal averaging. CoRR Michal Derezinski, Michael W. Mahoney
2019	J	`jnl`	Exact expressions for double descent and implicit regularization via surrogate random design. CoRR Michal Derezinski, Feynman T. Liang, Michael W. Mahoney
2019	A*	`conf`	Exact sampling of determinantal point processes with sublinear time preprocessing. NeurIPS Michal Derezinski, Daniele Calandriello, Michal Valko
2019	J	`jnl`	Exact sampling of determinantal point processes with sublinear time preprocessing. CoRR Michal Derezinski, Daniele Calandriello, Michal Valko
2019	A*	`conf`	Fast determinantal point processes via distortion-free intermediate sampling. COLT Michal Derezinski
2019	A*	`conf`	Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression. COLT Michal Derezinski, Kenneth L. Clarkson, Michael W. Mahoney, Manfred K. Warmuth
2019	J	`jnl`	Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression. CoRR Michal Derezinski, Kenneth L. Clarkson, Michael W. Mahoney, Manfred K. Warmuth
2019	J	`jnl`	Unbiased estimators for random design regression. CoRR Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
2018	A	`conf`	Batch-Expansion Training: An Efficient Optimization Framework. AISTATS Michal Derezinski, Dhruv Mahajan, S. Sathiya Keerthi, S. V. N. Vishwanathan, Markus Weimer
2018	J	`jnl`	Correcting the bias in least squares regression with volume-rescaled sampling. CoRR Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
2018	A	`conf`	Discovering Surprising Documents with Context-Aware Word Representations. IUI Michal Derezinski, Khashayar Rohanimanesh, Aamer Hydrie
2018	J	`jnl`	Fast determinantal point processes via distortion-free intermediate sampling. CoRR Michal Derezinski
2018	A*	`conf`	Leveraged volume sampling for linear regression. NeurIPS Michal Derezinski, Manfred K. Warmuth, Daniel J. Hsu
2018	J	`jnl`	Reverse Iterative Volume Sampling for Linear Regression. J. Mach. Learn. Res. Michal Derezinski, Manfred K. Warmuth
2018	J	`jnl`	Reverse iterative volume sampling for linear regression. CoRR Michal Derezinski, Manfred K. Warmuth
2018	A	`conf`	Subsampling for Ridge Regression via Regularized Volume Sampling. AISTATS Michal Derezinski, Manfred K. Warmuth
2018	J	`jnl`	Tail bounds for volume sampled linear regression. CoRR Michal Derezinski, Manfred K. Warmuth, Daniel Hsu
2018	—	`—`	Volume sampling for linear regression. Michal Derezinski
2017	J	`jnl`	Batch-Expansion Training: An Efficient Optimization Paradigm for Machine Learning. CoRR Michal Derezinski, Dhruv Mahajan, S. Sathiya Keerthi, S. V. N. Vishwanathan, Markus Weimer
2017	J	`jnl`	Subsampling for Ridge Regression via Regularized Volume Sampling. CoRR Michal Derezinski, Manfred K. Warmuth
2017	—	`conf`	Unbiased estimates for linear regression via volume sampling. NIPS Michal Derezinski, Manfred K. Warmuth
2017	J	`jnl`	Unbiased estimates for linear regression via volume sampling. CoRR Michal Derezinski, Manfred K. Warmuth
2014	—	`conf`	The limits of squared Euclidean distance regularization. NIPS Michal Derezinski, Manfred K. Warmuth