Overview

Sample Size Determination: Posterior Distributions Proximity

This paper presents two approaches to determining a sufficient sample size based on the proximity of posterior distributions of model parameters on similar subsets.

January 2025 · Nikita Kiselev, Andrey Grabovoy

ConvNets Landscape Convergence: Hessian-Based Analysis of Matricized Networks

This paper introduces a method for estimating the Hessian matrix norm in convolutional neural networks, offering insights into the loss landscape’s local behaviour, supported by empirical convergence analysis.

December 2024 · Vladislav Meshkov, Nikita Kiselev, Andrey Grabovoy
Method Overview

Forecasting fMRI images from video sequences: linear model analysis

This paper propose a method for creating a linear model that predicts changes in fMRI signals based on video sequence images. A linear model is constructed for each individual voxel in the fMRI image, assuming that the image sequence follows a Markov property.

November 2024 · Daniil Dorin, Nikita Kiselev, Andrey Grabovoy, Vadim Strijov

Sample Size Determination: Likelihood Bootstrapping

This paper presents two approaches to determining a sufficient sample size based on likelihood values from resampled subsets.

October 2024 · Nikita Kiselev, Andrey Grabovoy
Overview

Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes

This paper explore the convergence of the loss landscape in neural networks as the sample size increases, focusing on the Hessian matrix to understand the local geometry of the loss function.

August 2024 · Nikita Kiselev, Andrey Grabovoy
Comparison

Decentralized Optimization with Coupled Constraints

The method proposed is the first linearly convergent first-order decentralized algorithm for problems with general affine coupled constraints.

May 2024 · Demyan Yarmoshik, Alexander Rogozin, Nikita Kiselev, Daniil Dorin, Alexander Gasnikov, Dmitry Kovalev