---
_id: '9196'
abstract:
- lang: eng
text: In order to provide a local description of a regular function in a small neighbourhood
of a point x, it is sufficient by Taylor’s theorem to know the value of the function
as well as all of its derivatives up to the required order at the point x itself.
In other words, one could say that a regular function is locally modelled by the
set of polynomials. The theory of regularity structures due to Hairer generalizes
this observation and provides an abstract setup, which in the application to singular
SPDE extends the set of polynomials by functionals constructed from, e.g., white
noise. In this context, the notion of Taylor polynomials is lifted to the notion
of so-called modelled distributions. The celebrated reconstruction theorem, which
in turn was inspired by Gubinelli’s \textit {sewing lemma}, is of paramount importance
for the theory. It enables one to reconstruct a modelled distribution as a true
distribution on Rd which is locally approximated by this extended set of models
or “monomials”. In the original work of Hairer, the error is measured by means
of Hölder norms. This was then generalized to the whole scale of Besov spaces
by Hairer and Labbé. It is the aim of this work to adapt the analytic part of
the theory of regularity structures to the scale of Triebel–Lizorkin spaces.
article_processing_charge: No
article_type: original
author:
- first_name: Sebastian
full_name: Hensel, Sebastian
id: 4D23B7DA-F248-11E8-B48F-1D18A9856A87
last_name: Hensel
orcid: 0000-0001-7252-8072
- first_name: Tommaso
full_name: Rosati, Tommaso
last_name: Rosati
citation:
ama: Hensel S, Rosati T. Modelled distributions of Triebel–Lizorkin type. Studia
Mathematica. 2020;252(3):251-297. doi:10.4064/sm180411-11-2
apa: Hensel, S., & Rosati, T. (2020). Modelled distributions of Triebel–Lizorkin
type. Studia Mathematica. Instytut Matematyczny. https://doi.org/10.4064/sm180411-11-2
chicago: Hensel, Sebastian, and Tommaso Rosati. “Modelled Distributions of Triebel–Lizorkin
Type.” Studia Mathematica. Instytut Matematyczny, 2020. https://doi.org/10.4064/sm180411-11-2.
ieee: S. Hensel and T. Rosati, “Modelled distributions of Triebel–Lizorkin type,”
Studia Mathematica, vol. 252, no. 3. Instytut Matematyczny, pp. 251–297,
2020.
ista: Hensel S, Rosati T. 2020. Modelled distributions of Triebel–Lizorkin type.
Studia Mathematica. 252(3), 251–297.
mla: Hensel, Sebastian, and Tommaso Rosati. “Modelled Distributions of Triebel–Lizorkin
Type.” Studia Mathematica, vol. 252, no. 3, Instytut Matematyczny, 2020,
pp. 251–97, doi:10.4064/sm180411-11-2.
short: S. Hensel, T. Rosati, Studia Mathematica 252 (2020) 251–297.
date_created: 2021-02-25T08:55:03Z
date_published: 2020-03-01T00:00:00Z
date_updated: 2023-10-17T09:15:53Z
day: '01'
department:
- _id: JuFi
- _id: GradSch
doi: 10.4064/sm180411-11-2
external_id:
arxiv:
- '1709.05202'
isi:
- '000558100500002'
intvolume: ' 252'
isi: 1
issue: '3'
keyword:
- General Mathematics
language:
- iso: eng
month: '03'
oa_version: Preprint
page: 251-297
publication: Studia Mathematica
publication_identifier:
eissn:
- 1730-6337
issn:
- 0039-3223
publication_status: published
publisher: Instytut Matematyczny
quality_controlled: '1'
scopus_import: '1'
status: public
title: Modelled distributions of Triebel–Lizorkin type
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 252
year: '2020'
...
---
_id: '7464'
abstract:
- lang: eng
text: 'Retrovirus assembly is driven by the multidomain structural protein Gag.
Interactions between the capsid domains (CA) of Gag result in Gag multimerization,
leading to an immature virus particle that is formed by a protein lattice based
on dimeric, trimeric, and hexameric protein contacts. Among retroviruses the inter-
and intra-hexamer contacts differ, especially in the N-terminal sub-domain of
CA (CANTD). For HIV-1 the cellular molecule inositol hexakisphosphate (IP6) interacts
with and stabilizes the immature hexamer, and is required for production of infectious
virus particles. We have used in vitro assembly, cryo-electron tomography and
subtomogram averaging, atomistic molecular dynamics simulations and mutational
analyses to study the HIV-related lentivirus equine infectious anemia virus (EIAV).
In particular, we sought to understand the structural conservation of the immature
lentivirus lattice and the role of IP6 in EIAV assembly. Similar to HIV-1, IP6
strongly promoted in vitro assembly of EIAV Gag proteins into virus-like particles
(VLPs), which took three morphologically highly distinct forms: narrow tubes,
wide tubes, and spheres. Structural characterization of these VLPs to sub-4Å resolution
unexpectedly showed that all three morphologies are based on an immature lattice
with preserved key structural components, highlighting the structural versatility
of CA to form immature assemblies. A direct comparison between EIAV and HIV revealed
that both lentiviruses maintain similar immature interfaces, which are established
by both conserved and non-conserved residues. In both EIAV and HIV-1, IP6 regulates
immature assembly via conserved lysine residues within the CACTD and SP. Lastly,
we demonstrate that IP6 stimulates in vitro assembly of immature particles of
several other retroviruses in the lentivirus genus, suggesting a conserved role
for IP6 in lentiviral assembly.'
acknowledged_ssus:
- _id: ScienComp
article_number: e1008277
article_processing_charge: No
article_type: original
author:
- first_name: Robert A.
full_name: Dick, Robert A.
last_name: Dick
- first_name: Chaoyi
full_name: Xu, Chaoyi
last_name: Xu
- first_name: Dustin R.
full_name: Morado, Dustin R.
last_name: Morado
- first_name: Vladyslav
full_name: Kravchuk, Vladyslav
id: 4D62F2A6-F248-11E8-B48F-1D18A9856A87
last_name: Kravchuk
orcid: 0000-0001-9523-9089
- first_name: Clifton L.
full_name: Ricana, Clifton L.
last_name: Ricana
- first_name: Terri D.
full_name: Lyddon, Terri D.
last_name: Lyddon
- first_name: Arianna M.
full_name: Broad, Arianna M.
last_name: Broad
- first_name: J. Ryan
full_name: Feathers, J. Ryan
last_name: Feathers
- first_name: Marc C.
full_name: Johnson, Marc C.
last_name: Johnson
- first_name: Volker M.
full_name: Vogt, Volker M.
last_name: Vogt
- first_name: Juan R.
full_name: Perilla, Juan R.
last_name: Perilla
- first_name: John A. G.
full_name: Briggs, John A. G.
last_name: Briggs
- first_name: Florian KM
full_name: Schur, Florian KM
id: 48AD8942-F248-11E8-B48F-1D18A9856A87
last_name: Schur
orcid: 0000-0003-4790-8078
citation:
ama: Dick RA, Xu C, Morado DR, et al. Structures of immature EIAV Gag lattices reveal
a conserved role for IP6 in lentivirus assembly. PLOS Pathogens. 2020;16(1).
doi:10.1371/journal.ppat.1008277
apa: Dick, R. A., Xu, C., Morado, D. R., Kravchuk, V., Ricana, C. L., Lyddon, T.
D., … Schur, F. K. (2020). Structures of immature EIAV Gag lattices reveal a conserved
role for IP6 in lentivirus assembly. PLOS Pathogens. Public Library of
Science. https://doi.org/10.1371/journal.ppat.1008277
chicago: Dick, Robert A., Chaoyi Xu, Dustin R. Morado, Vladyslav Kravchuk, Clifton
L. Ricana, Terri D. Lyddon, Arianna M. Broad, et al. “Structures of Immature EIAV
Gag Lattices Reveal a Conserved Role for IP6 in Lentivirus Assembly.” PLOS
Pathogens. Public Library of Science, 2020. https://doi.org/10.1371/journal.ppat.1008277.
ieee: R. A. Dick et al., “Structures of immature EIAV Gag lattices reveal
a conserved role for IP6 in lentivirus assembly,” PLOS Pathogens, vol.
16, no. 1. Public Library of Science, 2020.
ista: Dick RA, Xu C, Morado DR, Kravchuk V, Ricana CL, Lyddon TD, Broad AM, Feathers
JR, Johnson MC, Vogt VM, Perilla JR, Briggs JAG, Schur FK. 2020. Structures of
immature EIAV Gag lattices reveal a conserved role for IP6 in lentivirus assembly.
PLOS Pathogens. 16(1), e1008277.
mla: Dick, Robert A., et al. “Structures of Immature EIAV Gag Lattices Reveal a
Conserved Role for IP6 in Lentivirus Assembly.” PLOS Pathogens, vol. 16,
no. 1, e1008277, Public Library of Science, 2020, doi:10.1371/journal.ppat.1008277.
short: R.A. Dick, C. Xu, D.R. Morado, V. Kravchuk, C.L. Ricana, T.D. Lyddon, A.M.
Broad, J.R. Feathers, M.C. Johnson, V.M. Vogt, J.R. Perilla, J.A.G. Briggs, F.K.
Schur, PLOS Pathogens 16 (2020).
date_created: 2020-02-06T18:47:17Z
date_published: 2020-01-27T00:00:00Z
date_updated: 2023-10-17T12:29:34Z
day: '27'
ddc:
- '570'
department:
- _id: FlSc
doi: 10.1371/journal.ppat.1008277
external_id:
isi:
- '000510746400010'
pmid:
- '31986188'
file:
- access_level: open_access
checksum: a297f54d1fef0efe4789ca00f37f241e
content_type: application/pdf
creator: dernst
date_created: 2020-02-11T10:07:28Z
date_updated: 2020-07-14T12:47:59Z
file_id: '7484'
file_name: 2020_PLOSPatho_Dick.pdf
file_size: 4551246
relation: main_file
file_date_updated: 2020-07-14T12:47:59Z
has_accepted_license: '1'
intvolume: ' 16'
isi: 1
issue: '1'
language:
- iso: eng
license: https://creativecommons.org/licenses/by/4.0/
month: '01'
oa: 1
oa_version: Published Version
pmid: 1
project:
- _id: 26736D6A-B435-11E9-9278-68D0E5697425
call_identifier: FWF
grant_number: P31445
name: Structural conservation and diversity in retroviral capsid
publication: PLOS Pathogens
publication_identifier:
issn:
- 1553-7374
publication_status: published
publisher: Public Library of Science
quality_controlled: '1'
related_material:
record:
- id: '9723'
relation: research_data
status: deleted
scopus_import: '1'
status: public
title: Structures of immature EIAV Gag lattices reveal a conserved role for IP6 in
lentivirus assembly
tmp:
image: /images/cc_by.png
legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
short: CC BY (4.0)
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 16
year: '2020'
...
---
_id: '7212'
abstract:
- lang: eng
text: The fixation probability of a single mutant invading a population of residents
is among the most widely-studied quantities in evolutionary dynamics. Amplifiers
of natural selection are population structures that increase the fixation probability
of advantageous mutants, compared to well-mixed populations. Extensive studies
have shown that many amplifiers exist for the Birth-death Moran process, some
of them substantially increasing the fixation probability or even guaranteeing
fixation in the limit of large population size. On the other hand, no amplifiers
are known for the death-Birth Moran process, and computer-assisted exhaustive
searches have failed to discover amplification. In this work we resolve this disparity,
by showing that any amplification under death-Birth updating is necessarily bounded
and transient. Our boundedness result states that even if a population structure
does amplify selection, the resulting fixation probability is close to that of
the well-mixed population. Our transience result states that for any population
structure there exists a threshold r⋆ such that the population structure ceases
to amplify selection if the mutant fitness advantage r is larger than r⋆. Finally,
we also extend the above results to δ-death-Birth updating, which is a combination
of Birth-death and death-Birth updating. On the positive side, we identify population
structures that maintain amplification for a wide range of values r and δ. These
results demonstrate that amplification of natural selection depends on the specific
mechanisms of the evolutionary process.
article_number: e1007494
article_processing_charge: No
article_type: original
author:
- first_name: Josef
full_name: Tkadlec, Josef
id: 3F24CCC8-F248-11E8-B48F-1D18A9856A87
last_name: Tkadlec
orcid: 0000-0002-1097-9684
- first_name: Andreas
full_name: Pavlogiannis, Andreas
id: 49704004-F248-11E8-B48F-1D18A9856A87
last_name: Pavlogiannis
orcid: 0000-0002-8943-0722
- first_name: Krishnendu
full_name: Chatterjee, Krishnendu
id: 2E5DCA20-F248-11E8-B48F-1D18A9856A87
last_name: Chatterjee
orcid: 0000-0002-4561-241X
- first_name: Martin A.
full_name: Nowak, Martin A.
last_name: Nowak
citation:
ama: Tkadlec J, Pavlogiannis A, Chatterjee K, Nowak MA. Limits on amplifiers of
natural selection under death-Birth updating. PLoS computational biology.
2020;16. doi:10.1371/journal.pcbi.1007494
apa: Tkadlec, J., Pavlogiannis, A., Chatterjee, K., & Nowak, M. A. (2020). Limits
on amplifiers of natural selection under death-Birth updating. PLoS Computational
Biology. Public Library of Science. https://doi.org/10.1371/journal.pcbi.1007494
chicago: Tkadlec, Josef, Andreas Pavlogiannis, Krishnendu Chatterjee, and Martin
A. Nowak. “Limits on Amplifiers of Natural Selection under Death-Birth Updating.”
PLoS Computational Biology. Public Library of Science, 2020. https://doi.org/10.1371/journal.pcbi.1007494.
ieee: J. Tkadlec, A. Pavlogiannis, K. Chatterjee, and M. A. Nowak, “Limits on amplifiers
of natural selection under death-Birth updating,” PLoS computational biology,
vol. 16. Public Library of Science, 2020.
ista: Tkadlec J, Pavlogiannis A, Chatterjee K, Nowak MA. 2020. Limits on amplifiers
of natural selection under death-Birth updating. PLoS computational biology. 16,
e1007494.
mla: Tkadlec, Josef, et al. “Limits on Amplifiers of Natural Selection under Death-Birth
Updating.” PLoS Computational Biology, vol. 16, e1007494, Public Library
of Science, 2020, doi:10.1371/journal.pcbi.1007494.
short: J. Tkadlec, A. Pavlogiannis, K. Chatterjee, M.A. Nowak, PLoS Computational
Biology 16 (2020).
date_created: 2019-12-23T13:45:11Z
date_published: 2020-01-17T00:00:00Z
date_updated: 2023-10-17T12:29:47Z
day: '17'
ddc:
- '000'
department:
- _id: KrCh
doi: 10.1371/journal.pcbi.1007494
ec_funded: 1
external_id:
arxiv:
- '1906.02785'
isi:
- '000510916500025'
file:
- access_level: open_access
checksum: ce32ee2d2f53aed832f78bbd47e882df
content_type: application/pdf
creator: dernst
date_created: 2020-02-03T07:32:42Z
date_updated: 2020-07-14T12:47:53Z
file_id: '7441'
file_name: 2020_PlosCompBio_Tkadlec.pdf
file_size: 1817531
relation: main_file
file_date_updated: 2020-07-14T12:47:53Z
has_accepted_license: '1'
intvolume: ' 16'
isi: 1
language:
- iso: eng
month: '01'
oa: 1
oa_version: Published Version
project:
- _id: 2581B60A-B435-11E9-9278-68D0E5697425
call_identifier: FP7
grant_number: '279307'
name: 'Quantitative Graph Games: Theory and Applications'
- _id: 2584A770-B435-11E9-9278-68D0E5697425
call_identifier: FWF
grant_number: P 23499-N23
name: Modern Graph Algorithmic Techniques in Formal Verification
- _id: 25863FF4-B435-11E9-9278-68D0E5697425
call_identifier: FWF
grant_number: S11407
name: Game Theory
publication: PLoS computational biology
publication_identifier:
eissn:
- '15537358'
publication_status: published
publisher: Public Library of Science
quality_controlled: '1'
related_material:
record:
- id: '7196'
relation: part_of_dissertation
status: public
scopus_import: '1'
status: public
title: Limits on amplifiers of natural selection under death-Birth updating
tmp:
image: /images/cc_by.png
legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
short: CC BY (4.0)
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 16
year: '2020'
...
---
_id: '7196'
abstract:
- lang: eng
text: 'In this thesis we study certain mathematical aspects of evolution. The two
primary forces that drive an evolutionary process are mutation and selection.
Mutation generates new variants in a population. Selection chooses among the variants
depending on the reproductive rates of individuals. Evolutionary processes are
intrinsically random – a new mutation that is initially present in the population
at low frequency can go extinct, even if it confers a reproductive advantage.
The overall rate of evolution is largely determined by two quantities: the probability
that an invading advantageous mutation spreads through the population (called
fixation probability) and the time until it does so (called fixation time). Both
those quantities crucially depend not only on the strength of the invading mutation
but also on the population structure. In this thesis, we aim to understand how
the underlying population structure affects the overall rate of evolution. Specifically,
we study population structures that increase the fixation probability of advantageous
mutants (called amplifiers of selection). Broadly speaking, our results are of
three different types: We present various strong amplifiers, we identify regimes
under which only limited amplification is feasible, and we propose population
structures that provide different tradeoffs between high fixation probability
and short fixation time.'
alternative_title:
- ISTA Thesis
article_processing_charge: No
author:
- first_name: Josef
full_name: Tkadlec, Josef
id: 3F24CCC8-F248-11E8-B48F-1D18A9856A87
last_name: Tkadlec
orcid: 0000-0002-1097-9684
citation:
ama: Tkadlec J. A role of graphs in evolutionary processes. 2020. doi:10.15479/AT:ISTA:7196
apa: Tkadlec, J. (2020). A role of graphs in evolutionary processes. Institute
of Science and Technology Austria. https://doi.org/10.15479/AT:ISTA:7196
chicago: Tkadlec, Josef. “A Role of Graphs in Evolutionary Processes.” Institute
of Science and Technology Austria, 2020. https://doi.org/10.15479/AT:ISTA:7196.
ieee: J. Tkadlec, “A role of graphs in evolutionary processes,” Institute of Science
and Technology Austria, 2020.
ista: Tkadlec J. 2020. A role of graphs in evolutionary processes. Institute of
Science and Technology Austria.
mla: Tkadlec, Josef. A Role of Graphs in Evolutionary Processes. Institute
of Science and Technology Austria, 2020, doi:10.15479/AT:ISTA:7196.
short: J. Tkadlec, A Role of Graphs in Evolutionary Processes, Institute of Science
and Technology Austria, 2020.
date_created: 2019-12-20T12:26:36Z
date_published: 2020-01-12T00:00:00Z
date_updated: 2023-10-17T12:29:46Z
day: '12'
ddc:
- '519'
degree_awarded: PhD
department:
- _id: KrCh
- _id: GradSch
doi: 10.15479/AT:ISTA:7196
file:
- access_level: closed
checksum: 451f8e64b0eb26bf297644ac72bfcbe9
content_type: application/zip
creator: jtkadlec
date_created: 2020-01-12T11:49:49Z
date_updated: 2020-07-14T12:47:52Z
file_id: '7255'
file_name: thesis.zip
file_size: 21100497
relation: source_file
- access_level: open_access
checksum: d8c44cbc4f939c49a8efc9d4b8bb3985
content_type: application/pdf
creator: dernst
date_created: 2020-01-28T07:32:42Z
date_updated: 2020-07-14T12:47:52Z
file_id: '7367'
file_name: 2020_Tkadlec_Thesis.pdf
file_size: 11670983
relation: main_file
file_date_updated: 2020-07-14T12:47:52Z
has_accepted_license: '1'
language:
- iso: eng
month: '01'
oa: 1
oa_version: Published Version
page: '144'
publication_identifier:
eissn:
- 2663-337X
publication_status: published
publisher: Institute of Science and Technology Austria
related_material:
record:
- id: '7210'
relation: dissertation_contains
status: public
- id: '5751'
relation: dissertation_contains
status: public
- id: '7212'
relation: dissertation_contains
status: public
status: public
supervisor:
- first_name: Krishnendu
full_name: Chatterjee, Krishnendu
id: 2E5DCA20-F248-11E8-B48F-1D18A9856A87
last_name: Chatterjee
orcid: 0000-0002-4561-241X
title: A role of graphs in evolutionary processes
type: dissertation
user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1
year: '2020'
...
---
_id: '9198'
abstract:
- lang: eng
text: "The optimization of multilayer neural networks typically leads to a solution\r\nwith
zero training error, yet the landscape can exhibit spurious local minima\r\nand
the minima can be disconnected. In this paper, we shed light on this\r\nphenomenon:
we show that the combination of stochastic gradient descent (SGD)\r\nand over-parameterization
makes the landscape of multilayer neural networks\r\napproximately connected and
thus more favorable to optimization. More\r\nspecifically, we prove that SGD solutions
are connected via a piecewise linear\r\npath, and the increase in loss along this
path vanishes as the number of\r\nneurons grows large. This result is a consequence
of the fact that the\r\nparameters found by SGD are increasingly dropout stable
as the network becomes\r\nwider. We show that, if we remove part of the neurons
(and suitably rescale the\r\nremaining ones), the change in loss is independent
of the total number of\r\nneurons, and it depends only on how many neurons are
left. Our results exhibit\r\na mild dependence on the input dimension: they are
dimension-free for two-layer\r\nnetworks and depend linearly on the dimension
for multilayer networks. We\r\nvalidate our theoretical findings with numerical
experiments for different\r\narchitectures and classification tasks."
acknowledgement: M. Mondelli was partially supported by the 2019 LopezLoreta Prize.
The authors thank Phan-Minh Nguyen for helpful discussions and the IST Distributed
Algorithms and Systems Lab for providing computational resources.
article_processing_charge: No
author:
- first_name: Alexander
full_name: Shevchenko, Alexander
last_name: Shevchenko
- first_name: Marco
full_name: Mondelli, Marco
id: 27EB676C-8706-11E9-9510-7717E6697425
last_name: Mondelli
orcid: 0000-0002-3242-7020
citation:
ama: 'Shevchenko A, Mondelli M. Landscape connectivity and dropout stability of
SGD solutions for over-parameterized neural networks. In: Proceedings of the
37th International Conference on Machine Learning. Vol 119. ML Research Press;
2020:8773-8784.'
apa: Shevchenko, A., & Mondelli, M. (2020). Landscape connectivity and dropout
stability of SGD solutions for over-parameterized neural networks. In Proceedings
of the 37th International Conference on Machine Learning (Vol. 119, pp. 8773–8784).
ML Research Press.
chicago: Shevchenko, Alexander, and Marco Mondelli. “Landscape Connectivity and
Dropout Stability of SGD Solutions for Over-Parameterized Neural Networks.” In
Proceedings of the 37th International Conference on Machine Learning, 119:8773–84.
ML Research Press, 2020.
ieee: A. Shevchenko and M. Mondelli, “Landscape connectivity and dropout stability
of SGD solutions for over-parameterized neural networks,” in Proceedings of
the 37th International Conference on Machine Learning, 2020, vol. 119, pp.
8773–8784.
ista: Shevchenko A, Mondelli M. 2020. Landscape connectivity and dropout stability
of SGD solutions for over-parameterized neural networks. Proceedings of the 37th
International Conference on Machine Learning. vol. 119, 8773–8784.
mla: Shevchenko, Alexander, and Marco Mondelli. “Landscape Connectivity and Dropout
Stability of SGD Solutions for Over-Parameterized Neural Networks.” Proceedings
of the 37th International Conference on Machine Learning, vol. 119, ML Research
Press, 2020, pp. 8773–84.
short: A. Shevchenko, M. Mondelli, in:, Proceedings of the 37th International Conference
on Machine Learning, ML Research Press, 2020, pp. 8773–8784.
date_created: 2021-02-25T09:36:22Z
date_published: 2020-07-13T00:00:00Z
date_updated: 2023-10-17T12:43:19Z
day: '13'
ddc:
- '000'
department:
- _id: MaMo
external_id:
arxiv:
- '1912.10095'
file:
- access_level: open_access
checksum: f042c8d4316bd87c6361aa76f1fbdbbe
content_type: application/pdf
creator: dernst
date_created: 2021-03-02T15:38:14Z
date_updated: 2021-03-02T15:38:14Z
file_id: '9217'
file_name: 2020_PMLR_Shevchenko.pdf
file_size: 5336380
relation: main_file
success: 1
file_date_updated: 2021-03-02T15:38:14Z
has_accepted_license: '1'
intvolume: ' 119'
language:
- iso: eng
month: '07'
oa: 1
oa_version: Published Version
page: 8773-8784
project:
- _id: 059876FA-7A3F-11EA-A408-12923DDC885E
name: Prix Lopez-Loretta 2019 - Marco Mondelli
publication: Proceedings of the 37th International Conference on Machine Learning
publication_status: published
publisher: ML Research Press
quality_controlled: '1'
status: public
title: Landscape connectivity and dropout stability of SGD solutions for over-parameterized
neural networks
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 119
year: '2020'
...