3 papers
cs.LG2021
Can we learn gradients by Hamiltonian Neural Networks?
Aleksandr Timofeev, Andrei Afonin, Yehao Liu
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…
cs.CV2021
Self-Supervised Neural Architecture Search for Imbalanced Datasets
Aleksandr Timofeev, Grigorios G. Chrysos, Volkan Cevher
Neural Architecture Search (NAS) provides state-of-the-art results when trained on well-curated datasets with annotated labels. However, annotating data or even having balanced num…
math.ST2020
Manifold-based time series forecasting
Nikita Puchkin, Aleksandr Timofeev, Vladimir Spokoiny
Prediction for high dimensional time series is a challenging task due to the curse of dimensionality problem. Classical parametric models like ARIMA or VAR require strong modeling…