Search Results - "Konečný, Jakub"

Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting by Konecny, Jakub, Liu, Jie, Richtarik, Peter, Takac, Martin

“…We propose mS2GD: a method incorporating a mini-batching scheme for improving the theoretical complexity and practical performance of semi-stochastic gradient…”
Get full text

Distributed optimization with arbitrary local solvers by Ma, Chenxin, Konečný, Jakub, Jaggi, Martin, Smith, Virginia, Jordan, Michael I., Richtárik, Peter, Takáč, Martin

“…With the growth of data and necessity for distributed optimization methods, solvers that work well on a single machine must be re-designed to leverage…”
Get full text

Randomized Distributed Mean Estimation: Accuracy vs. Communication by Konečný, Jakub, Richtárik, Peter

“…We consider the problem of estimating the arithmetic average of a finite collection of real vectors stored in a distributed fashion across several compute…”
Get full text

Semi-stochastic coordinate descent by Konečný, Jakub, Qu, Zheng, Richtárik, Peter

“…We propose a novel stochastic gradient method-semi-stochastic coordinate descent-for the problem of minimizing a strongly convex function represented as the…”
Get full text

Semi-Stochastic Gradient Descent Methods by Konečný, Jakub, Richtárik, Peter

“…In this paper we study the problem of minimizing the average of a large number of smooth convex loss functions. We propose a new method, S2GD (Semi-Stochastic…”
Get full text

Thoracoscopic radiofrequency ablation for lone atrial fibrillation: Box-lesion technique by Klvacek, Ales, Steriovsky, Andrea, Konecny, Jakub, Skala, Tomas, Lonsky, Vladimir, Santavy, Petr

“…Abstract Background We report the feasibility and outcomes of box-lesion ablation technique to treat stand-alone atrial fibrillation (AF). Methods There were…”
Get full text

Five-year experience with cardiac surgery procedures in dialysis-dependent patients by Klváček, Ales, Šantavý, Petr, Zuščich, Ondrej, Konečný, Jakub, Hájek, Roman, Lonský, Vladimir

“…Abstract The purpose of this study was to review the outcome of dialysis-dependent patients undergoing cardiac surgery. We retrospectively reviewed 36…”
Get full text

Stochastic, distributed and federated optimization for machine learning by Konečný, Jakub

“…We study optimization algorithms for the finite sum problems frequently arising in machine learning applications. First, we propose novel variants of…”
Get full text

Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning by Charles, Zachary, Konečný, Jakub

“…Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021. PMLR: Volume 130 We study a family of algorithms,…”
Get full text

Stochastic, Distributed and Federated Optimization for Machine Learning by Konečný, Jakub

“…We study optimization algorithms for the finite sum problems frequently arising in machine learning applications. First, we propose novel variants of…”
Get full text

On the Outsized Importance of Learning Rates in Local Update Methods by Charles, Zachary, Konečný, Jakub

“…We study a family of algorithms, which we refer to as local update methods, that generalize many federated learning and meta-learning algorithms. We prove that…”
Get full text

Konference „Field Research in Anthropology: Unity and Diversity“, Olomouc, 3.–4. 10. 2017 by Šotola, Jaroslav, Konečný, Jakub, Novotná, Hedvika

“…Tým sociálních a kulturních antropologů z Univerzity Palackého v Olomouci uspořádal konferenci věnovanou metodologickým aspektům terénního výzkumu s cílem dát…”
Get full text

Federated Learning with Autotuned Communication-Efficient Secure Aggregation by Bonawitz, Keith, Salehi, Fariborz, Konecny, Jakub, McMahan, Brendan, Gruteser, Marco

“…Federated Learning enables mobile devices to collaboratively learn a shared inference model while keeping all the training data on a user's device, decoupling…”
Get full text

Optimizing the Communication-Accuracy Trade-off in Federated Learning with Rate-Distortion Theory by Mitchell, Nicole, Ballé, Johannes, Charles, Zachary, Konečný, Jakub

“…A significant bottleneck in federated learning (FL) is the network communication cost of sending model updates from client devices to the central server. We…”
Get full text

Randomized Distributed Mean Estimation: Accuracy vs Communication by Konečný, Jakub, Richtárik, Peter

“…We consider the problem of estimating the arithmetic average of a finite collection of real vectors stored in a distributed fashion across several compute…”
Get full text

Federated Learning with Autotuned Communication-Efficient Secure Aggregation by Bonawitz, Keith, Salehi, Fariborz, Konečný, Jakub, McMahan, Brendan, Gruteser, Marco

“…Federated Learning enables mobile devices to collaboratively learn a shared inference model while keeping all the training data on a user's device, decoupling…”
Get full text

Simple Complexity Analysis of Simplified Direct Search by Konečný, Jakub, Richtárik, Peter

“…We consider the problem of unconstrained minimization of a smooth function in the derivative-free setting using. In particular, we propose and study a…”
Get full text

Improving Federated Learning Personalization via Model Agnostic Meta Learning by Jiang, Yihan, Konečný, Jakub, Rush, Keith, Kannan, Sreeram

“…Federated Learning (FL) refers to learning a high quality global model based on decentralized data storage, without ever copying the raw data. A natural…”
Get full text

A Privacy Preserving Randomized Gossip Algorithm via Controlled Noise Insertion by Hanzely, Filip, Konečný, Jakub, Loizou, Nicolas, Richtárik, Peter, Grishchenko, Dmitry

“…In this work we present a randomized gossip algorithm for solving the average consensus problem while at the same time protecting the information about the…”
Get full text

One-Shot-Learning Gesture Recognition using HOG-HOF Features by Konečný, Jakub, Hagara, Michal

“…The purpose of this paper is to describe one-shot-learning gesture recognition systems developed on the \textit{ChaLearn Gesture Dataset}. We use RGB and depth…”
Get full text