English
Related papers

Related papers: Adaptive Delayed-Update Cyclic Algorithm for Varia…

200 papers

We consider stochastic optimization with delayed gradients where, at each time step $t$, the algorithm makes an update using a stale stochastic gradient from step $t - d_t$ for some arbitrary delay $d_t$. This setting abstracts asynchronous…

Optimization and Control · Mathematics 2021-11-16 Alon Cohen , Amit Daniely , Yoel Drori , Tomer Koren , Mariano Schain

Perfect Space-Time Codes (STC) are optimal codes in their original construction for Multiple Input Multiple Output (MIMO) systems. Based on Cyclic Division Algebras (CDA), they are full-rate, full-diversity codes, have Non-Vanishing…

Information Theory · Computer Science 2010-11-03 Mireille Sarkiss , Ghaya Rekaya-Ben Othman , Mohamed Oussama Damen , Jean-Claude Belfiore

This paper presents a hierarchical low-rank decomposition algorithm assuming any matrix element can be computed in $O(1)$ time. The proposed algorithm computes rank-revealing decompositions of sub-matrices with a blocked adaptive cross…

Numerical Analysis · Mathematics 2019-09-06 Yang Liu , Wissam Sid-Lakhdar , Elizaveta Rebrova , Pieter Ghysels , Xiaoye Sherry Li

The distance profiles of linear block codes can be employed to design variational coding scheme for encoding message with variational length and getting lower decoding error probability by large minimum Hamming distance. %, e.g. the design…

Information Theory · Computer Science 2013-06-05 Xiaogang Liu , Yuan Luo , Kenneth W. Shum

We introduce two block coordinate descent algorithms for solving optimization problems with ordinary differential equations (ODEs) as dynamical constraints. The algorithms do not need to implement direct or adjoint sensitivity analysis…

Machine Learning · Computer Science 2022-08-30 Ion Matei , Maksym Zhenirovskyy , Johan de Kleer , John Maxwell

We will consider the damped Newton method for strongly monotone and Lipschitz continuous operator equations in a variational setting. We will provide a very accessible justification why the undamped Newton method performs better than its…

Numerical Analysis · Mathematics 2023-05-26 Pascal Heid

In large-scale applications, such as machine learning, it is desirable to design non-convex optimization algorithms with a high degree of parallelization. In this work, we study the adaptive complexity of finding a stationary point, which…

Optimization and Control · Mathematics 2025-05-15 Huanjian Zhou , Andi Han , Akiko Takeda , Masashi Sugiyama

Ordinary differential equations (ODEs) are fundamental tools for modeling complex dynamic systems across scientific disciplines. However, parameter estimation in ODE models is challenging due to the multimodal nature of the likelihood…

Computation · Statistics 2025-04-17 Donghui Son , Liangliang Wang

We give in this paper a convergence result concerning parallel asynchronous algorithm with bounded delays to solve a nonlinear fixed point problems. This result is applied to calculate the solution of a strongly monotone operator. Special…

Numerical Analysis · Mathematics 2007-05-23 Abdenasser Benahmed

Delays and asynchrony are inevitable in large-scale machine-learning problems where communication plays a key role. As such, several works have extensively analyzed stochastic optimization with delayed gradients. However, as far as we are…

Machine Learning · Computer Science 2023-08-28 Arman Adibi , Aritra Mitra , Hamed Hassani

We improve the understanding of the $\textit{golden ratio algorithm}$, which solves monotone variational inequalities (VI) and convex-concave min-max problems via the distinctive feature of adapting the step sizes to the local Lipschitz…

Optimization and Control · Mathematics 2022-12-29 Ahmet Alacaoglu , Axel Böhm , Yura Malitsky

Solving evolutionary equations in a parallel-in-time manner is an attractive topic and many algorithms are proposed in recent two decades. The algorithm based on the block $\alpha$-circulant preconditioning technique has shown promising…

Numerical Analysis · Mathematics 2021-04-15 Shu-Lin Wu , Tao Zhou , Zhi Zhou

Adaptive methods like Adam have become the $\textit{de facto}$ standard for large-scale vector and Euclidean optimization due to their coordinate-wise adaptation with a second-order nature. More recently, matrix-based spectral optimizers…

Machine Learning · Computer Science 2026-05-28 Zitao Song , Cedar Site Bai , Zhe Zhang , Brian Bullins , David F. Gleich

The difference-of-convex algorithm (DCA) is a conceptually simple method for the minimization of (possibly) nonconvex functions that are expressed as the difference of two convex functions. At each iteration, DCA constructs a global…

Optimization and Control · Mathematics 2023-06-06 Chaorui Yao , Xin Jiang

We give a fully dynamic deterministic algorithm for maintaining a maximal matching of an $n$-vertex graph in $\tilde{O}(n^{8/9})$ amortized update time. This breaks the long-standing $\Omega(n)$-update-time barrier on dense graphs,…

Data Structures and Algorithms · Computer Science 2025-09-01 Aaron Bernstein , Sayan Bhattacharya , Peter Kiss , Thatchaphol Saranurak

Gradient descent ascent (GDA), the simplest single-loop algorithm for nonconvex minimax optimization, is widely used in practical applications such as generative adversarial networks (GANs) and adversarial training. Albeit its desirable…

Machine Learning · Computer Science 2021-12-13 Junchi Yang , Antonio Orvieto , Aurelien Lucchi , Niao He

This paper proposes a distributed alternating mixed discrete-continuous (DAMDC) algorithm to approach the oracle algorithm based on the diffusion strategy for parameter and spectrum estimation over sensor networks. A least mean squares…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-04-12 R. C. de Lamare

In two earlier papers, we designed a distributed deterministic asynchronous algorithm for minimizing the sum of subdifferentiable and proximable functions and a regularizing quadratic on time-varying graphs based on Dykstra's algorithm, or…

Optimization and Control · Mathematics 2018-08-23 C. H. Jeffrey Pang

SOTA decentralized SGD algorithms can overcome the bandwidth bottleneck at the parameter server by using communication collectives like Ring All-Reduce for synchronization. While the parameter updates in distributed SGD may happen…

Machine Learning · Computer Science 2022-11-10 Haoze He , Parijat Dube

Adam is a popular variant of stochastic gradient descent for finding a local minimizer of a function. In the constant stepsize regime, assuming that the objective function is differentiable and non-convex, we establish the convergence in…

Machine Learning · Statistics 2020-05-15 Anas Barakat , Pascal Bianchi