diff --git a/about/index.html b/about/index.html index 395444f..6fc2908 100644 --- a/about/index.html +++ b/about/index.html @@ -70,7 +70,7 @@

Bayesian Methods Research Group

About

-

Recent years have proved that the more data is involved into analysis, the better (often much better) results one may obtain. The breakthrough in machine learning has happened due to the successful application of deep neural networks which turned out to be extremely powerful when dealing with huge amounts of data. However, it is now clear that classical methods simply do not work when one needs to process extremely large datasets. So the New Mathematics or the mathematics of Big Data Age is needed. Our group is involved in the process of developing such mathematics and is carrying out research in deep learning, stochastic optimization, tensor decompositions, scalable variational inference. Our efforts are supported by Samsung, Yandex, NVIDIA, Kaspersky lab, Sberbank, Schlumberger, JetBrains.

+

Recent years have proved that the more data is involved into analysis, the better (often much better) results one may obtain. The breakthrough in machine learning has happened due to the successful application of deep neural networks which turned out to be extremely powerful when dealing with huge amounts of data. However, it is now clear that classical methods simply do not work when one needs to process extremely large datasets. So the New Mathematics or the mathematics of Big Data Age is needed. Our group is involved in the process of developing such mathematics and is carrying out research in deep learning, stochastic optimization, tensor decompositions, scalable variational inference.

Important directions of our work are applied projects from many domains including text processing, computer vision, software code analysis. During the work over the projects, students gain practical experience of using different algorithms from computer science as well as software engineering skills. We strongly encourage the research activity of students and the publication of papers authored or co-authored by students.

Our group is involved in the teaching process at Constructor University.

diff --git a/alumni/index.html b/alumni/index.html index d2e19fd..67c15cf 100644 --- a/alumni/index.html +++ b/alumni/index.html @@ -82,6 +82,23 @@

Alumni

Dmitrii Pozdeev, Technical University of Munich + +
+ + +Ekaterina Lobacheva, Université de Montréal and Mila Quebec AI Institute +
+
+ + +Kirill Suglobov +
+ +
+
+ + +Tingir Badmaev
@@ -93,13 +110,13 @@

Alumni

Alexander Markov
-
-
Anuar Taskynov
+
+
@@ -115,13 +132,13 @@

Alumni

Artem Gerasimov
-
-
Artem Tsypin
+
+
@@ -137,13 +154,13 @@

Alumni

Nikita Bondartsev
-
-
Oleg Ivanov
+
+
@@ -159,13 +176,13 @@

Alumni

Victor Oganesyan
-
-
Alexander Fritsler
+
+
@@ -181,13 +198,13 @@

Alumni

Maxim Ryabinin, Yandex
-
-
Andrei Atanov, EPFL
+
+
@@ -203,13 +220,13 @@

Alumni

Darya Voronkova
-
-
Dmitry Molchanov
+
+
@@ -225,13 +242,13 @@

Alumni

Maxim Kochurov
-
-
Pavel Mazaev, Yandex
+
+
@@ -247,13 +264,13 @@

Alumni

Viktor Yanush
-
-
Iurii Kemaev, DeepMind
+
+
@@ -269,13 +286,13 @@

Alumni

Anton Rodomanov
-
-
Roman Bobrov
+
+
@@ -291,13 +308,13 @@

Alumni

Timur Garipov, MIT
-
-
Alexander Novikov, DeepMind
+
+
@@ -313,13 +330,13 @@

Alumni

Nikita Romanov
-
-
Vladislav Skripniuk
+
+
@@ -335,13 +352,13 @@

Alumni

Pavel Izmailov, Cornell
-
-
Michael Khalman
+
+
@@ -357,13 +374,13 @@

Alumni

Sergey Bartunov, DeepMind
-
-
Vlad Chabanenko
+
+
@@ -379,13 +396,13 @@

Alumni

Alexandr Chistyakov
-
-
Dmitry Kondrashkin, Yandex
+
+
@@ -401,13 +418,13 @@

Alumni

Peter Romov, Yandex
-
-
Denis Elshin
+
+
@@ -423,13 +440,13 @@

Alumni

Anton Golovin
-
-
Ivan Kaspersky
+
+
@@ -445,13 +462,13 @@

Alumni

Boris Yangel, Yandex
-
-
Victor Chernyshov
+
+
diff --git a/people/ekaterina-lobacheva/index.html b/people/ekaterina-lobacheva/index.html deleted file mode 100644 index 0655ee3..0000000 --- a/people/ekaterina-lobacheva/index.html +++ /dev/null @@ -1,163 +0,0 @@ - - - - - - - - - Ekaterina Lobacheva – Bayesian Methods Research Group - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - \ No newline at end of file diff --git a/people/kirill-suglobov/index.html b/people/kirill-suglobov/index.html deleted file mode 100644 index 037cc11..0000000 --- a/people/kirill-suglobov/index.html +++ /dev/null @@ -1,103 +0,0 @@ - - - - - - - - - Kirill Suglobov – Bayesian Methods Research Group - - - - - - - - - - - - - - - - - -
- - -
-
- -
-
- - -
-
-
-
-

Kirill Suglobov

-
- - - -

Recent Publications

-
    -
-
-
-
- - - - -
- - - - - - - - - - - - \ No newline at end of file diff --git a/people/tingir-badmaev/index.html b/people/tingir-badmaev/index.html deleted file mode 100644 index 964608a..0000000 --- a/people/tingir-badmaev/index.html +++ /dev/null @@ -1,103 +0,0 @@ - - - - - - - - - Tingir Badmaev – Bayesian Methods Research Group - - - - - - - - - - - - - - - - - -
- - -
-
- -
-
- - -
-
-
-
-

Tingir Badmaev

-
- - - -

Recent Publications

-
    -
-
-
-
- - - - -
- - - - - - - - - - - - \ No newline at end of file diff --git a/publications/2018-bayesian-compression-for-natural-language-processing/index.html b/publications/2018-bayesian-compression-for-natural-language-processing/index.html index ca0ad97..b803761 100644 --- a/publications/2018-bayesian-compression-for-natural-language-processing/index.html +++ b/publications/2018-bayesian-compression-for-natural-language-processing/index.html @@ -77,8 +77,8 @@

-
  • - +
  • + Photo Ekaterina Lobacheva Ekaterina Lobacheva
  • diff --git a/publications/2020-on-power-laws-in-deep-ensembles-full/index.html b/publications/2020-on-power-laws-in-deep-ensembles-full/index.html index 8c39d26..a4fbb0b 100644 --- a/publications/2020-on-power-laws-in-deep-ensembles-full/index.html +++ b/publications/2020-on-power-laws-in-deep-ensembles-full/index.html @@ -71,8 +71,8 @@

      -
    1. - +
    2. + Photo Ekaterina Lobacheva Ekaterina Lobacheva
    3. diff --git a/publications/2020-structured-sparsification-of-gated-recurrent-neural-networks/index.html b/publications/2020-structured-sparsification-of-gated-recurrent-neural-networks/index.html index 098e007..4c149ed 100644 --- a/publications/2020-structured-sparsification-of-gated-recurrent-neural-networks/index.html +++ b/publications/2020-structured-sparsification-of-gated-recurrent-neural-networks/index.html @@ -71,8 +71,8 @@

        -
      1. - +
      2. + Photo Ekaterina Lobacheva Ekaterina Lobacheva
      3. diff --git a/publications/2021-on-the-periodic-behavior-of-neural-network-training-with-batch-normalization-and-weight-decay/index.html b/publications/2021-on-the-periodic-behavior-of-neural-network-training-with-batch-normalization-and-weight-decay/index.html index 4f2cba1..0cb2e6e 100644 --- a/publications/2021-on-the-periodic-behavior-of-neural-network-training-with-batch-normalization-and-weight-decay/index.html +++ b/publications/2021-on-the-periodic-behavior-of-neural-network-training-with-batch-normalization-and-weight-decay/index.html @@ -71,8 +71,8 @@

          -
        1. - +
        2. + Photo Ekaterina Lobacheva Ekaterina Lobacheva
        3. diff --git a/publications/2022-training-scale-invariant-neural-networks-on-the-sphere-can-happen-in-three-regimes/index.html b/publications/2022-training-scale-invariant-neural-networks-on-the-sphere-can-happen-in-three-regimes/index.html index cccc16d..2df24a6 100644 --- a/publications/2022-training-scale-invariant-neural-networks-on-the-sphere-can-happen-in-three-regimes/index.html +++ b/publications/2022-training-scale-invariant-neural-networks-on-the-sphere-can-happen-in-three-regimes/index.html @@ -77,8 +77,8 @@

          -
        4. - +
        5. + Photo Ekaterina Lobacheva Ekaterina Lobacheva
        6. diff --git a/publications/2023-large-learning-rates-improve-generalization-but-how-large-are-we-talking-about/index.html b/publications/2023-large-learning-rates-improve-generalization-but-how-large-are-we-talking-about/index.html index a1698e5..e5acb37 100644 --- a/publications/2023-large-learning-rates-improve-generalization-but-how-large-are-we-talking-about/index.html +++ b/publications/2023-large-learning-rates-improve-generalization-but-how-large-are-we-talking-about/index.html @@ -71,8 +71,8 @@

            -
          1. - +
          2. + Photo Ekaterina Lobacheva Ekaterina Lobacheva
          3. diff --git a/publications/2023-to-stay-or-not-to-stay-in-the-pre-train-basin-insights-on-ensembling-in-transfer-learning/index.html b/publications/2023-to-stay-or-not-to-stay-in-the-pre-train-basin-insights-on-ensembling-in-transfer-learning/index.html index df74d31..e682bce 100644 --- a/publications/2023-to-stay-or-not-to-stay-in-the-pre-train-basin-insights-on-ensembling-in-transfer-learning/index.html +++ b/publications/2023-to-stay-or-not-to-stay-in-the-pre-train-basin-insights-on-ensembling-in-transfer-learning/index.html @@ -87,8 +87,8 @@

            -
          4. - +
          5. + Photo Ekaterina Lobacheva Ekaterina Lobacheva
          6. diff --git a/teams/deep-bayes/index.html b/teams/deep-bayes/index.html index a8a1f61..0845499 100644 --- a/teams/deep-bayes/index.html +++ b/teams/deep-bayes/index.html @@ -86,10 +86,6 @@

            Researchers

            Aibek Alanov

    -
    - - Ekaterina Lobacheva, PhD -
    Timofey Yuzhakov @@ -126,20 +122,10 @@

    MSc Students

    Egor Chimbulatov
    -
    - - Kirill Suglobov -
    Nikita Morozov
    -
    -
    -
    - - Tingir Badmaev -
    Viacheslav Meshchaninov