Martin Takáč

Available identifiers

zbMath Open takac.martinMaRDI QIDQ263211

List of research outcomes

Publication	Date of Publication	Type
Random-reshuffled SARAH does not need full gradient computations	2024-03-27	Paper
Preconditioning meets biased compression for efficient distributed optimization	2024-02-06	Paper
Stochastic Gradient Descent with Preconditioned Polyak Step-size	2023-10-03	Paper
Advancing the lower bounds: An accelerated, stochastic, second-order method with optimal adaptation to inexactness	2023-09-04	Paper
Convergence analysis of stochastic gradient descent with adaptive preconditioning for non-convex and convex functions	2023-08-27	Paper
Decentralized personalized federated learning: lower bounds and optimal algorithm for all personalization modes	2023-07-12	Paper
Hybrid Methods in Polynomial Optimisation	2023-05-25	Paper
Cubic Regularization is the Key! The First Accelerated Quasi-Newton Method with a Global Convergence Rate of $O(k^{-2})$ for Convex Functions	2023-02-09	Paper
Quasi-Newton methods for machine learning: forget the past, just sample	2022-12-20	Paper
A Damped Newton Method Achieves Global $O\left(\frac{1}{k^2}\right)$ and Local Quadratic Convergence Rate	2022-10-31	Paper
Effects of momentum scaling for SGD	2022-10-21	Paper
FLECS: A Federated Learning Second-Order Framework via Compression and Sketching	2022-06-04	Paper
Randomized sketch descent methods for non-separable linearly constrained optimization	2022-05-17	Paper
Alternating maximization: unifying framework for 8 sparse PCA formulations and efficient parallel codes	2022-04-22	Paper
The Power of First-Order Smooth Optimization for Black-Box Non-Smooth Problems	2022-01-28	Paper
Fast and safe: accelerated gradient methods with optimality certificates and underestimate sequences	2021-08-09	Paper
An accelerated communication-efficient primal-dual optimization framework for structured machine learning	2021-04-15	Paper
Inexact SARAH algorithm for stochastic optimization	2021-04-15	Paper
Inexact Tensor Methods and Their Application to Stochastic Convex Optimization	2020-12-31	Paper
https://portal.mardi4nfdi.de/entity/Q4969198	2020-10-05	Paper
Stochastic Reformulations of Linear Systems: Algorithms and Convergence Theory	2020-05-28	Paper
New Convergence Aspects of Stochastic Gradient Algorithms	2020-02-07	Paper
A robust multi-batch L-BFGS method for machine learning	2019-11-25	Paper
Quasi-Newton Methods for Machine Learning: Forget the Past, Just Sample	2019-01-28	Paper
https://portal.mardi4nfdi.de/entity/Q4558572	2018-11-22	Paper
Matrix completion under interval uncertainty	2018-05-24	Paper
On the complexity of parallel coordinate descent	2018-05-02	Paper
Entropy Penalized Semidefinite Programming	2018-02-12	Paper
Projected semi-stochastic gradient descent method with mini-batch scheme under weak strong convexity assumption	2018-02-06	Paper
Dual Free Adaptive Minibatch SDCA for Empirical Risk Minimization	2018-01-25	Paper
Distributed optimization with arbitrary local solvers	2017-11-24	Paper
A low-rank coordinate-descent algorithm for semidefinite programming relaxations of optimal power flow	2017-11-24	Paper
A Coordinate-Descent Algorithm for Tracking Solutions in Time-Varying Optimal Power Flows	2017-10-19	Paper
https://portal.mardi4nfdi.de/entity/Q2953662	2017-01-05	Paper
On optimal probabilities in stochastic coordinate descent methods	2016-09-21	Paper
A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning	2016-06-15	Paper
Distributed Coordinate Descent Method for Learning with Big Data	2016-06-06	Paper
Parallel coordinate descent methods for big data optimization	2016-04-04	Paper
Distributed Block Coordinate Descent for Minimizing Partially Separable Functions	2016-01-05	Paper
Hybrid Methods in Solving Alternating-Current Optimal Power Flows	2015-10-07	Paper
Efficient Serial and Parallel Coordinate Descent Methods for Huge-Scale Truss Topology Design	2015-03-03	Paper
Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function	2014-06-02	Paper
https://portal.mardi4nfdi.de/entity/Q2896264	2012-07-16	Paper
https://portal.mardi4nfdi.de/entity/Q4366596	1998-04-03	Paper

Research outcomes over time

Doctoral students

No records found.

Known relations from the MaRDI Knowledge Graph

Property	Value
MaRDI profile type	MaRDI person profile
instance of	human

This page was built for person: Martin Takáč