Home      Library      Discussions      About
Join us

@mipt.ru

Nov 02, 2018
Artificial Intelligence

eLIAN: Enhanced Algorithm for Angle-constrained Path Finding

Problem of finding 2D paths of special shape, e.g. paths comprised of line segments having the property that the angle between any two consecutive se…
Dec 06, 2018
Chemical Physics

On rotational-vibrational spectrum of diatomic beryllium molecule

The eigenvalue problem for second-order ordinary differential equation (SOODE) in a finite interval with the boundary conditions of the first, second…
Jun 09, 2014
Mesoscale and Nanoscale Physics

Graphene nanoelectromechanical resonators for detection of modulated …

We propose and analyze the detector of modulated terahertz (THz) radiation based on the graphene field-effect transistor with mechanically floating g…
Sep 13, 2015
Mesoscale and Nanoscale Physics

Emission and amplification of surface plasmons in resonant - tunnelin…

We predict a new mechanism of surface plasmon amplification in graphene-insulator-graphene van der Waals heterostructures. The amplification occurs u…
Nov 08, 2017
Optimization and Control

В данной работе представлен градиентный и быстрый градиентный метод для (δ,L)-модели. В работе приведены алгоритмы методов и оценки скоростей сходимости. В п.5 показано, что данные методы могут быть довольно сильным инструментом для решения большого…

Fast gradient descent method for convex optimization problems with an…

In this article we propose a new concept of a $(\delta,L)$-model of a function which generalizes the concept of the $(\delta,L)$-oracle (Devolder-Gli…
May 17, 2019
Machine Learning

An Essay on Optimization Mystery of Deep Learning

Despite the huge empirical success of deep learning, theoretical understanding of neural networks learning process is still lacking. This is the reas…
Nov 13, 2019
Optimization and Control
Machine Learning
Statistics Theory

Suppose {xi}ni=1 is a set of vectors in Rd such that xi≠xj for i≠j. Then we can select w∈RT such that the numbers {wTxi}ni=1 are all different.

Quadratic number of nodes is sufficient to learn a dataset via gradie…

We prove that if an activation function satisfies some mild conditions and number of neurons in a two-layered fully connected neural network with thi…
Jun 11, 2020
Machine Learning

Dynamically Stable Infinite-Width Limits of Neural Classifiers

Recent research has been focused on two different approaches to studying neural networks training in the limit of infinite width (1) a mean-field (MF…
Sep 27, 2017
Computation and Language

Application of a Hybrid Bi-LSTM-CRF model to the task of Russian Name…

Named Entity Recognition (NER) is one of the most common tasks of the natural language processing. The purpose of NER is to find and classify tokens …
May 09, 2017
General Physics

Cartesian nature of equal active and passive energies

The Cartesian material space approach to Maxwell's equations reveals the analytical solution of the continuous radial density for the extended elemen…
Nov 19, 2017
Space Physics

Defunct Satellites in Nearly Polar Orbits: Long-term Evolution of A…

Low Earth orbits (LEO) are known as a region of high space activity and, consequently, space debris highest density. Launcher upper stages and defunc…
Jun 28, 2017

Quark-diquark structure and masses of doubly charmed baryons

The finite size of doubly heavy diquark gives a positive correction to the masses of baryons calculated in the local diquark approximation. We evalua…
May 07, 2019
Neural and Evolutionary Computation
Artificial Intelligence
Machine Learning

Continual and Multi-task Reinforcement Learning With Shared Episodic …

Episodic memory plays an important role in the behavior of animals and humans. It allows the accumulation of information about current state of the e…
Jun 24, 2018
Optimization and Control

Walrasian Equilibrium and Centralized Distributed Optimization from t…

We consider the resource allocation problem and its numerical solution. The following constructions are demonstrated: 1) Walrasian price-adjustment m…
May 17, 2019
Computation and Language

Adaptation of Deep Bidirectional Multilingual Transformers for Russia…

The paper introduces methods of adaptation of multilingual masked language models for a specific language. Pre-trained bidirectional language models …
Mar 12, 2020
Machine Learning

Towards a General Theory of Infinite-Width Limits of Neural Classifie…

Obtaining theoretical guarantees for neural networks training appears to be a hard problem in a general case. Recent research has been focused on stu…
Dec 10, 2020
Machine Learning
Artificial Intelligence

These are the notes for the lectures that I was giving during Fall 2020 at the Moscow Institute of Physics and Technology (MIPT) and at the Yandex School of Data Analysis (YSDA). The notes cover some aspects of initialization, loss landscape, genera…

Notes on Deep Learning Theory

These are the notes for the lectures that I was giving during Fall 2020 at the Moscow Institute of Physics and Technology (MIPT) and at the Yandex Sc…
There aren't more papers

Request Comment

or Invite via email
You are asking your first question!
How to quickly get a good answer:
  • Keep your question short and to the point
  • Check for grammar or spelling errors.
  • Phrase it like a question
Test
Test description