29 citations · 63 across the 7 of their papers we have counts for
11 papers
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning
Aleksandr Ermolov, Leyla Mirvakhabova, Valentin Khrulkov +2
Metric learning aims to learn a highly discriminative model encouraging the embeddings of similar classes to be close in the chosen metrics and pushed apart for dissimilar ones. Th…
Disentangled Representations from Non-Disentangled Models
Valentin Khrulkov, Leyla Mirvakhabova, Ivan Oseledets +1
Constructing disentangled representations is known to be a difficult task, especially in the unsupervised scenario. The dominating paradigm of unsupervised disentanglement is curre…
Functional Space Analysis of Local GAN Convergence
Valentin Khrulkov, Artem Babenko, Ivan Oseledets
Recent work demonstrated the benefits of studying continuous-time dynamics governing the GAN training. However, this dynamics is analyzed in the model parameter space, which result…
Performance of Hyperbolic Geometry Models on Top-N Recommendation Tasks
Leyla Mirvakhabova, Evgeny Frolov, Valentin Khrulkov +2
We introduce a simple autoencoder based on hyperbolic geometry for solving standard collaborative filtering problem. In contrast to many modern deep learning techniques, we build o…
Sample Efficient Ensemble Learning with Catalyst.RL
Sergey Kolesnikov, Valentin Khrulkov
We present Catalyst.RL, an open-source PyTorch framework for reproducible and sample efficient reinforcement learning (RL) research. Main features of Catalyst.RL include large-scal…
Universality Theorems for Generative Models
Valentin Khrulkov, Ivan Oseledets
Despite the fact that generative models are extremely successful in practice, the theory underlying this phenomenon is only starting to catch up with practice. In this work we addr…