
Performance of Hyperbolic Geometry Models on TopN Recommendation Tasks
We introduce a simple autoencoder based on hyperbolic geometry for solvi...
read it

Stable Lowrank Tensor Decomposition for Compression of Convolutional Neural Network
Most state of the art deep neural networks are overparameterized and exh...
read it

Follow the bisector: a simple method for multiobjective optimization
This study presents a novel Equiangular Direction Method (EDM) to solve ...
read it

GeometryInspired Topk Adversarial Perturbations
Stateoftheart deep learning models are untrustworthy due to their vul...
read it

FREDE: LinearSpace Anytime Graph Embeddings
Lowdimensional representations, or embeddings, of a graph's nodes facil...
read it

Tensorized Transformer for Dynamical Systems Modeling
The identification of nonlinear dynamics from observations is essential ...
read it

Simple heuristics for efficient parallel tensor contraction and quantum circuit simulation
Tensor networks are the main building blocks in a wide variety of comput...
read it

Towards Understanding Normalization in Neural ODEs
Normalization is an important and vastly investigated technique in deep ...
read it

Stochastic gradient algorithms from ODE splitting perspective
We present a different view on stochastic optimization, which goes back ...
read it

Bayesian aggregation improves traditional single image crop classification approaches
Machine learning (ML) methods and neural networks (NN) are widely implem...
read it

Interpolated Adjoint Method for Neural ODEs
In this paper, we propose a method, which allows us to alleviate or comp...
read it

Using Reinforcement Learning in the Algorithmic Trading Problem
The development of reinforced learning methods has extended application ...
read it

Deep Representation Learning for Dynamical Systems Modeling
Proper states' representations are the key to the successful dynamics mo...
read it

Randomized Algorithms for Computation of Tucker decomposition and Higher Order SVD (HOSVD)
Big data analysis has become a crucial part of new emerging technologies...
read it

Tensor Completion via Gaussian Process Based Initialization
In this paper, we consider the tensor completion problem representing th...
read it

An adaptive algorithm for quantum circuit simulation
Efficient simulation of quantum computers is essential for the developme...
read it

Active Subspace of Neural Networks: Structural Analysis and Universal Attacks
Active subspace is a model reduction method widely used in the uncertain...
read it

Growing axons: greedy learning of neural networks with application to function approximation
We propose a new method for learning deep neural network models that is ...
read it

Graph Convolutional Policy for Solving Tree Decomposition via Reinforcement Learning Heuristics
We propose a Reinforcement Learning based approach to approximately solv...
read it

ReducedOrder Modeling of Deep Neural Networks
We introduce a new method for speeding up the inference of deep neural n...
read it

Predicting dynamical system evolution with residual neural networks
Forecasting time series and timedependent data is a common problem in m...
read it

Practical shift choice in the shiftandinvert Krylov subspace evaluations of the matrix exponential
We propose two methods to find a proper shift parameter in the shiftand...
read it

Microstructure synthesis using stylebased generative adversarial network
Work considers the usage of StyleGAN architecture for the task of micros...
read it

Empirical study of extreme overfitting points of neural networks
In this paper we propose a method of obtaining points of extreme overfit...
read it

Universality Theorems for Generative Models
Despite the fact that generative models are extremely successful in prac...
read it

Intrinsic Multiscale Evaluation of Generative Models
Generative models are often used to sample highdimensional data points ...
read it

Hyperbolic Image Embeddings
Computer vision tasks such as image classification, image retrieval and ...
read it

One time is not enough: iterative tensor decomposition for neural network compression
The lowrank tensor approximation is very promising for the compression ...
read it

Preconditioning Kaczmarz method by sketching
We propose a new method for preconditioning Kaczmarz method by sketching...
read it

Generalized Tensor Models for Recurrent Neural Networks
Recurrent Neural Networks (RNNs) are very successful at solving challeng...
read it

Tensorized Embedding Layers for Efficient Model Compression
The embedding layers transforming input words into real vectors are the ...
read it

Deep Neural Networks Predicting Oil Movement in a Development Unit
We present a novel technique for assessing the dynamics of multiphase fl...
read it

PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach
With deep neural networks providing stateoftheart machine learning mo...
read it

Adversarial point set registration
We present a novel approach to point set registration which is based on ...
read it

Tensor Networks for Latent Variable Analysis: Higher Order Canonical Polyadic Decomposition
The Canonical Polyadic decomposition (CPD) is a convenient and intuitive...
read it

Modelling hidden structure of signals in group data analysis with modified (Lr, 1) and blockterm decompositions
This work is devoted to elaboration on the idea to use block term decomp...
read it

Revealing the Unobserved by Linking Collaborative Behavior and Side Knowledge
We propose a tensorbased model that fuses a more granular representatio...
read it

Comparative study of Discrete Wavelet Transforms and Wavelet Tensor Train decomposition to feature extraction of FTIR data of medicinal plants
Fouriertransform infrared (FTIR) spectra of samples from 7 plant speci...
read it

HybridSVD: When Collaborative Information is Not Enough
We propose a hybrid algorithm for topn recommendation task that allows ...
read it

Quadraturebased features for kernel approximation
We consider the problem of improving kernel approximation via randomized...
read it

Geometry Score: A Method For Comparing Generative Adversarial Networks
One of the biggest challenges in the research of generative adversarial ...
read it

Tensor Train decomposition on TensorFlow (T3F)
Tensor Train decomposition is used across many branches of machine learn...
read it

Art of singular vectors and universal adversarial perturbations
Vulnerability of Deep Neural Networks (DNNs) to adversarial attacks has ...
read it

Riemannian Optimization for SkipGram Negative Sampling
SkipGram Negative Sampling (SGNS) word embedding model, well known by i...
read it

VicoGreengardFerrando quadratures in the tensor solver for integral equations
Convolution with Green's function of a differential operator appears in ...
read it

Efficient Rectangular MaximalVolume Algorithm for Rating Elicitation in Collaborative Filtering
Cold start problem in Collaborative Filtering can be solved by asking ne...
read it

Fifty Shades of Ratings: How to Benefit from a Negative Feedback in TopN Recommendations Tasks
Conventional collaborative filtering techniques treat a topn recommenda...
read it

Exponential Machines
Modeling interactions between features improves the performance of machi...
read it

Tensor Methods and Recommender Systems
A substantial progress in development of new and efficient tensor factor...
read it

Tensor SimRank for Heterogeneous Information Networks
We propose a generalization of SimRank similarity measure for heterogene...
read it
Ivan Oseledets
is this you? claim profile
Associate Professor at Skolkovo Institute of Science and Technology