no code implementations • 29 Aug 2022 • Eugene Golikov, Eduard Pokonechnyy, Vladimir Korviakov
A seminal work [Jacot et al., 2018] demonstrated that training a neural network under specific parameterization is equivalent to performing a particular kernel method as width goes to infinity.
no code implementations • 31 May 2022 • Arthur Jacot, Eugene Golikov, Clément Hongler, Franck Gabriel
This second reformulation allows us to prove a sparsity result for homogeneous DNNs: any local minimum of the $L_{2}$-regularized loss can be achieved with at most $N(N+1)$ neurons in each hidden layer (where $N$ is the size of the training set).
no code implementations • 28 Sep 2020 • Eugene Golikov
Existing MF and NTK limit models, as well as one novel limit model, satisfy most of the properties demonstrated by finite-width models.
no code implementations • 17 May 2019 • Eugene Golikov
Despite the huge empirical success of deep learning, theoretical understanding of neural networks learning process is still lacking.
1 code implementation • 6 Dec 2018 • Eugene Golikov, Maksim Kretov
Conventional prior for Variational Auto-Encoder (VAE) is a Gaussian distribution.
2 code implementations • 13 Dec 2017 • Vlad Zhukov, Eugene Golikov, Maksim Kretov
In natural language processing tasks performance of the models is often measured with some non-differentiable metric, such as BLEU score.
1 code implementation • 21 Nov 2017 • Eugene Golikov, Vlad Zhukov, Maksim Kretov
Variety of machine learning problems can be formulated as an optimization task for some (surrogate) loss function.