Projects

[1]

HippoTrainer: Gradient-Based Hyperparameter Optimization for PyTorch

Daniil Dorin, Igor Ignashin, Nikita Kiselev, Andrey Veprikov

We release a Python library for gradient-based hyperparameter optimization, implementing cutting-edge algorithms that leverage automatic differentiation to efficiently tune hyperparameters. · 2025

Code

[2]

Just Relax It! Leveraging relaxation for discrete variables optimization

Daniil Dorin, Igor Ignashin, Nikita Kiselev, Andrey Veprikov

We release a cutting-edge Python library designed to streamline the optimization of discrete probability distributions in neural networks, offering a suite of advanced relaxation techniques compatible with PyTorch. · 2024

Code

[3]

Models of epidemic spread, in particular COVID-19 as a model of stochastic chemical kinetics

Peter Babkin, Daniil Dorin, Nikita Kiselev, Matvei Kreinin, Maria Nikitina

Various approaches to modeling the spread of epidemics, differential equations and Markov processes. · 2023

DraftCodeSlides

[4]

Optimization methods for quadratic problems with large dimensionality

Daniil Dorin, Nikita Kiselev

Comparison of different methods of solving high-dimensional linear regression problems. · 2023

CodeSlides

[5]

Intelligent Presentation Generator

Daniil Dorin, Nikita Kiselev, Lidia Kottsova, Maria Nikitina

Application for generating presentations based on text files using topic modeling. · 2022

Code