Výsledky vyhledávání - "Afonin, Andrei"

Report

Sampling and Ranking for Digital Ink Generation on a tight computational budget

Autor: Afonin, Andrei, Maksai, Andrii, Timofeev, Aleksandr, Musat, Claudiu

Digital ink (online handwriting) generation has a number of potential applications for creating user-visible content, such as handwriting autocompletion, spelling correction, and beautification. Writing is personal and usually the processing is done

Externí odkaz: http://arxiv.org/abs/2306.03103

Zobrazit plný text záznamu

Report

Can we learn gradients by Hamiltonian Neural Networks?

Autor: Timofeev, Aleksandr, Afonin, Andrei, Liu, Yehao

In this work, we propose a meta-learner based on ODE neural networks that learns gradients. This approach makes the optimizer is more flexible inducing an automatic inductive bias to the given task. Using the simplest Hamiltonian Neural Network we de

Externí odkaz: http://arxiv.org/abs/2111.00565

Zobrazit plný text záznamu

Report

Towards Model Agnostic Federated Learning Using Knowledge Distillation

Autor: Afonin, Andrei, Karimireddy, Sai Praneeth

Is it possible to design an universal API for federated learning using which an ad-hoc group of data-holders (agents) collaborate with each other and perform federated learning? Such an API would necessarily need to be model-agnostic i.e. make no ass

Externí odkaz: http://arxiv.org/abs/2110.15210

Zobrazit plný text záznamu

Report

Which Neural Network to Choose for Post-Fault Localization, Dynamic State Estimation and Optimal Measurement Placement in Power Systems?

Autor: Afonin, Andrei, Chertkov, Michael

We consider a power transmission system monitored with Phasor Measurement Units (PMUs) placed at significant, but not all, nodes of the system. Assuming that a sufficient number of distinct single-line faults, specifically pre-fault state and (not cl

Externí odkaz: http://arxiv.org/abs/2104.03115

Zobrazit plný text záznamu