Valentin Khrulkov

Publications22
h-index10
Citations492
Highly Influential Citations75
Claim Author Page
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • I. Oseledets
  • 262 Publications • 7,615 Citations
  • P. Abbeel
  • 549 Publications • 70,800 Citations
  • Olivier Bachem
  • 52 Publications • 2,821 Citations
  • Yoshua Bengio
  • 847 Publications • 358,502 Citations
  • Publications
  • Influence
Hyperbolic Image Embeddings
TLDR
It is demonstrated that in many practical scenarios, hyperbolic embeddings provide a better alternative to linear hyperplanes, Euclidean distances, or spherical geodesic distances.
View on IEEE
Art of Singular Vectors and Universal Adversarial Perturbations
TLDR
This work proposes a new algorithm based on computing the so-called (p, q)-singular vectors of the Jacobian matrices of hidden layers of a network that is able to construct universal perturbations with more than 60 % fooling rate on the dataset consisting of 50000 images.
View on IEEE
Tensorized Embedding Layers for Efficient Model Compression
TLDR
This work introduces a novel way of parametrizing embedding layers based on the Tensor Train (TT) decomposition, which allows compressing the model significantly at the cost of a negligible drop or even a slight gain in performance.
View PDF on arXiv
Revisiting Deep Learning Models for Tabular Data
TLDR
An overview of the main families of DL architectures for tabular data is performed and the bar of baselines in tabular DL is raised by identifying two simple and powerful deep architectures, which turns out to be a strong baseline that is often missing in prior works.
View PDF on arXiv
Geometry Score: A Method For Comparing Generative Adversarial Networks
TLDR
A novel measure of performance of a GAN is constructed by comparing geometrical properties of the underlying data manifold and the generated one, which provides both qualitative and quantitative means for evaluation.
View PDF on arXiv
Tensor Train decomposition on TensorFlow (T3F)
TLDR
A library that aims to fix Tensor Train decomposition and makes machine learning papers that rely on Tensor train decomposition easier to implement and includes 92% test coverage, examples, and API reference documentation.
View PDF on arXiv
Expressive power of recurrent neural networks
TLDR
The expressive power theorem is proved (an exponential lower bound on the width of the equivalent shallow network) for a class of recurrent neural networks -- ones that correspond to the Tensor Train (TT) decomposition, meaning that even processing an image patch by patch with an RNN can be exponentially more efficient than a (shallow) convolutional network with one hidden layer.
View PDF on arXiv
Generalized Tensor Models for Recurrent Neural Networks
TLDR
This work attempts to reduce the gap between theory and practice by extending the theoretical analysis to RNNs which employ various nonlinearities, such as Rectified Linear Unit (ReLU), and shows that they also benefit from properties of universality and depth efficiency.
View PDF on arXiv
Tensorized Embedding Layers
TLDR
A novel way of parameterizing embedding layers based on the Tensor Train decomposition is introduced, which allows compressing the model significantly at the cost of a negligible drop or even a slight gain in performance.
View on ACL
Understanding DDPM Latent Codes Through Optimal Transport
TLDR
It is shown that, perhaps surprisingly, the DDPM encoder map coincides with the optimal transport map for common distributions; this claim theoretically and by extensive numerical experiments is supported.
View PDF on arXiv
...
...