---
_id: '999'
abstract:
- lang: eng
text: 'In multi-task learning, a learner is given a collection of prediction tasks
and needs to solve all of them. In contrast to previous work, which required that
annotated training data must be available for all tasks, we consider a new setting,
in which for some tasks, potentially most of them, only unlabeled training data
is provided. Consequently, to solve all tasks, information must be transferred
between tasks with labels and tasks without labels. Focusing on an instance-based
transfer method we analyze two variants of this setting: when the set of labeled
tasks is fixed, and when it can be actively selected by the learner. We state
and prove a generalization bound that covers both scenarios and derive from it
an algorithm for making the choice of labeled tasks (in the active case) and for
transferring information between the tasks in a principled way. We also illustrate
the effectiveness of the algorithm on synthetic and real data. '
alternative_title:
- PMLR
article_processing_charge: No
arxiv: 1
author:
- first_name: Anastasia
full_name: Pentina, Anastasia
id: 42E87FC6-F248-11E8-B48F-1D18A9856A87
last_name: Pentina
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Pentina A, Lampert C. Multi-task learning with labeled and unlabeled tasks.
In: Vol 70. ML Research Press; 2017:2807-2816.'
apa: 'Pentina, A., & Lampert, C. (2017). Multi-task learning with labeled and
unlabeled tasks (Vol. 70, pp. 2807–2816). Presented at the ICML: International
Conference on Machine Learning, Sydney, Australia: ML Research Press.'
chicago: Pentina, Anastasia, and Christoph Lampert. “Multi-Task Learning with Labeled
and Unlabeled Tasks,” 70:2807–16. ML Research Press, 2017.
ieee: 'A. Pentina and C. Lampert, “Multi-task learning with labeled and unlabeled
tasks,” presented at the ICML: International Conference on Machine Learning, Sydney,
Australia, 2017, vol. 70, pp. 2807–2816.'
ista: 'Pentina A, Lampert C. 2017. Multi-task learning with labeled and unlabeled
tasks. ICML: International Conference on Machine Learning, PMLR, vol. 70, 2807–2816.'
mla: Pentina, Anastasia, and Christoph Lampert. Multi-Task Learning with Labeled
and Unlabeled Tasks. Vol. 70, ML Research Press, 2017, pp. 2807–16.
short: A. Pentina, C. Lampert, in:, ML Research Press, 2017, pp. 2807–2816.
conference:
end_date: 2017-08-11
location: Sydney, Australia
name: 'ICML: International Conference on Machine Learning'
start_date: 2017-08-06
corr_author: '1'
date_created: 2018-12-11T11:49:37Z
date_published: 2017-06-08T00:00:00Z
date_updated: 2025-06-04T08:19:03Z
day: '08'
department:
- _id: ChLa
ec_funded: 1
external_id:
arxiv:
- '1602.06518'
isi:
- '000683309502093'
intvolume: ' 70'
isi: 1
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://arxiv.org/abs/1602.06518
month: '06'
oa: 1
oa_version: Submitted Version
page: 2807 - 2816
project:
- _id: 2532554C-B435-11E9-9278-68D0E5697425
call_identifier: FP7
grant_number: '308036'
name: Lifelong Learning of Visual Scene Understanding
publication_identifier:
isbn:
- '9781510855144'
publication_status: published
publisher: ML Research Press
publist_id: '6399'
quality_controlled: '1'
scopus_import: '1'
status: public
title: Multi-task learning with labeled and unlabeled tasks
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 70
year: '2017'
...
---
_id: '1098'
abstract:
- lang: eng
text: Better understanding of the potential benefits of information transfer and
representation learning is an important step towards the goal of building intelligent
systems that are able to persist in the world and learn over time. In this work,
we consider a setting where the learner encounters a stream of tasks but is able
to retain only limited information from each encountered task, such as a learned
predictor. In contrast to most previous works analyzing this scenario, we do not
make any distributional assumptions on the task generating process. Instead, we
formulate a complexity measure that captures the diversity of the observed tasks.
We provide a lifelong learning algorithm with error guarantees for every observed
task (rather than on average). We show sample complexity reductions in comparison
to solving every task in isolation in terms of our task complexity measure. Further,
our algorithmic framework can naturally be viewed as learning a representation
from encountered tasks with a neural network.
acknowledgement: "This work was in parts funded by the European Research Council under
the European Union’s Seventh Framework Programme (FP7/2007-2013)/ERC grant agreement
no 308036.\r\n\r\n"
alternative_title:
- Advances in Neural Information Processing Systems
article_processing_charge: No
author:
- first_name: Anastasia
full_name: Pentina, Anastasia
id: 42E87FC6-F248-11E8-B48F-1D18A9856A87
last_name: Pentina
- first_name: Ruth
full_name: Urner, Ruth
last_name: Urner
citation:
ama: 'Pentina A, Urner R. Lifelong learning with weighted majority votes. In: Vol
29. Neural Information Processing Systems Foundation; 2016:3619-3627.'
apa: 'Pentina, A., & Urner, R. (2016). Lifelong learning with weighted majority
votes (Vol. 29, pp. 3619–3627). Presented at the NIPS: Neural Information Processing
Systems, Barcelona, Spain: Neural Information Processing Systems Foundation.'
chicago: Pentina, Anastasia, and Ruth Urner. “Lifelong Learning with Weighted Majority
Votes,” 29:3619–27. Neural Information Processing Systems Foundation, 2016.
ieee: 'A. Pentina and R. Urner, “Lifelong learning with weighted majority votes,”
presented at the NIPS: Neural Information Processing Systems, Barcelona, Spain,
2016, vol. 29, pp. 3619–3627.'
ista: 'Pentina A, Urner R. 2016. Lifelong learning with weighted majority votes.
NIPS: Neural Information Processing Systems, Advances in Neural Information Processing
Systems, vol. 29, 3619–3627.'
mla: Pentina, Anastasia, and Ruth Urner. Lifelong Learning with Weighted Majority
Votes. Vol. 29, Neural Information Processing Systems Foundation, 2016, pp.
3619–27.
short: A. Pentina, R. Urner, in:, Neural Information Processing Systems Foundation,
2016, pp. 3619–3627.
conference:
end_date: 2016-12-10
location: Barcelona, Spain
name: 'NIPS: Neural Information Processing Systems'
start_date: 2016-12-05
date_created: 2018-12-11T11:50:08Z
date_published: 2016-12-01T00:00:00Z
date_updated: 2025-06-03T11:35:58Z
day: '01'
ddc:
- '006'
department:
- _id: ChLa
ec_funded: 1
file:
- access_level: open_access
content_type: application/pdf
creator: system
date_created: 2018-12-12T10:12:42Z
date_updated: 2018-12-12T10:12:42Z
file_id: '4961'
file_name: IST-2017-775-v1+1_main.pdf
file_size: 237111
relation: main_file
- access_level: open_access
content_type: application/pdf
creator: system
date_created: 2018-12-12T10:12:43Z
date_updated: 2018-12-12T10:12:43Z
file_id: '4962'
file_name: IST-2017-775-v1+2_supplementary.pdf
file_size: 185818
relation: main_file
file_date_updated: 2018-12-12T10:12:43Z
has_accepted_license: '1'
intvolume: ' 29'
language:
- iso: eng
month: '12'
oa: 1
oa_version: Published Version
page: 3619-3627
project:
- _id: 2532554C-B435-11E9-9278-68D0E5697425
call_identifier: FP7
grant_number: '308036'
name: Lifelong Learning of Visual Scene Understanding
publication_status: published
publisher: Neural Information Processing Systems Foundation
publist_id: '6277'
pubrep_id: '775'
quality_controlled: '1'
scopus_import: '1'
status: public
title: Lifelong learning with weighted majority votes
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 29
year: '2016'
...
---
OA_place: publisher
_id: '1126'
abstract:
- lang: eng
text: "Traditionally machine learning has been focusing on the problem of solving
a single\r\ntask in isolation. While being quite well understood, this approach
disregards an\r\nimportant aspect of human learning: when facing a new problem,
humans are able to\r\nexploit knowledge acquired from previously learned tasks.
Intuitively, access to several\r\nproblems simultaneously or sequentially could
also be advantageous for a machine\r\nlearning system, especially if these tasks
are closely related. Indeed, results of many\r\nempirical studies have provided
justification for this intuition. However, theoretical\r\njustifications of this
idea are rather limited.\r\nThe focus of this thesis is to expand the understanding
of potential benefits of information\r\ntransfer between several related learning
problems. We provide theoretical\r\nanalysis for three scenarios of multi-task
learning - multiple kernel learning, sequential\r\nlearning and active task selection.
We also provide a PAC-Bayesian perspective on\r\nlifelong learning and investigate
how the task generation process influences the generalization\r\nguarantees in
this scenario. In addition, we show how some of the obtained\r\ntheoretical results
can be used to derive principled multi-task and lifelong learning\r\nalgorithms
and illustrate their performance on various synthetic and real-world datasets."
acknowledgement: "First and foremost I would like to express my gratitude to my supervisor,
Christoph\r\nLampert. Thank you for your patience in teaching me all aspects of
doing research\r\n(including English grammar), for your trust in my capabilities
and endless support. Thank\r\nyou for granting me freedom in my research and, at
the same time, having time and\r\nhelping me cope with the consequences whenever
I needed it. Thank you for creating\r\nan excellent atmosphere in the group, it
was a great pleasure and honor to be a part of\r\nit. There could not have been
a better and more inspiring adviser and mentor.\r\nI thank Shai Ben-David for welcoming
me into his group at the University of Waterloo,\r\nfor inspiring discussions and
support. It was a great pleasure to work together. I am\r\nalso thankful to Ruth
Urner for hosting me at the Max-Planck Institute Tübingen, for the\r\nfruitful
collaboration and for taking care of me during that not-so-sunny month of May.\r\nI
thank Jan Maas for kindly joining my thesis committee despite the short notice and\r\nproviding
me with insightful comments.\r\nI would like to thank my colleagues for their support,
entertaining conversations and\r\nendless table soccer games we shared together:
Georg, Jan, Amelie and Emilie, Michal\r\nand Alex, Alex K. and Alex Z., Thomas,
Sameh, Vlad, Mayu, Nathaniel, Silvester, Neel,\r\nCsaba, Vladimir, Morten. Thank
you, Mabel and Ram, for the wonderful time we spent\r\ntogether. I am thankful to
Shrinu and Samira for taking care of me during my stay at the\r\nUniversity of Waterloo.
Special thanks to Viktoriia for her never-ending optimism and for\r\nbeing so inspiring
and supportive, especially at the beginning of my PhD journey.\r\nThanks to IST
administration, in particular, Vlad and Elisabeth for shielding me from\r\nmost
of the bureaucratic paperwork.\r\n\r\nThis dissertation would not have been possible
without funding from the European\r\nResearch Council under the European Union's
Seventh Framework Programme\r\n(FP7/2007-2013)/ERC grant agreement no 308036."
alternative_title:
- ISTA Thesis
article_processing_charge: No
author:
- first_name: Anastasia
full_name: Pentina, Anastasia
id: 42E87FC6-F248-11E8-B48F-1D18A9856A87
last_name: Pentina
citation:
ama: Pentina A. Theoretical foundations of multi-task lifelong learning. 2016. doi:10.15479/AT:ISTA:TH_776
apa: Pentina, A. (2016). Theoretical foundations of multi-task lifelong learning.
Institute of Science and Technology Austria. https://doi.org/10.15479/AT:ISTA:TH_776
chicago: Pentina, Anastasia. “Theoretical Foundations of Multi-Task Lifelong Learning.”
Institute of Science and Technology Austria, 2016. https://doi.org/10.15479/AT:ISTA:TH_776.
ieee: A. Pentina, “Theoretical foundations of multi-task lifelong learning,” Institute
of Science and Technology Austria, 2016.
ista: Pentina A. 2016. Theoretical foundations of multi-task lifelong learning.
Institute of Science and Technology Austria.
mla: Pentina, Anastasia. Theoretical Foundations of Multi-Task Lifelong Learning.
Institute of Science and Technology Austria, 2016, doi:10.15479/AT:ISTA:TH_776.
short: A. Pentina, Theoretical Foundations of Multi-Task Lifelong Learning, Institute
of Science and Technology Austria, 2016.
corr_author: '1'
date_created: 2018-12-11T11:50:17Z
date_published: 2016-11-01T00:00:00Z
date_updated: 2026-04-09T10:49:34Z
day: '01'
ddc:
- '006'
degree_awarded: PhD
department:
- _id: ChLa
doi: 10.15479/AT:ISTA:TH_776
ec_funded: 1
file:
- access_level: open_access
content_type: application/pdf
creator: system
date_created: 2018-12-12T10:14:07Z
date_updated: 2018-12-12T10:14:07Z
file_id: '5056'
file_name: IST-2017-776-v1+1_Pentina_Thesis_2016.pdf
file_size: 2140062
relation: main_file
file_date_updated: 2018-12-12T10:14:07Z
has_accepted_license: '1'
language:
- iso: eng
month: '11'
oa: 1
oa_version: Published Version
page: '127'
project:
- _id: 2532554C-B435-11E9-9278-68D0E5697425
call_identifier: FP7
grant_number: '308036'
name: Lifelong Learning of Visual Scene Understanding
publication_identifier:
issn:
- 2663-337X
publication_status: published
publisher: Institute of Science and Technology Austria
publist_id: '6234'
pubrep_id: '776'
status: public
supervisor:
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
title: Theoretical foundations of multi-task lifelong learning
type: dissertation
user_id: ba8df636-2132-11f1-aed0-ed93e2281fdd
year: '2016'
...
---
_id: '1425'
abstract:
- lang: eng
text: 'In this work we aim at extending the theoretical foundations of lifelong
learning. Previous work analyzing this scenario is based on the assumption that
learning tasks are sampled i.i.d. from a task environment or limited to strongly
constrained data distributions. Instead, we study two scenarios when lifelong
learning is possible, even though the observed tasks do not form an i.i.d. sample:
first, when they are sampled from the same environment, but possibly with dependencies,
and second, when the task environment is allowed to change over time in a consistent
way. In the first case we prove a PAC-Bayesian theorem that can be seen as a direct
generalization of the analogous previous result for the i.i.d. case. For the second
scenario we propose to learn an inductive bias in form of a transfer procedure.
We present a generalization bound and show on a toy example how it can be used
to identify a beneficial transfer algorithm.'
alternative_title:
- Advances in Neural Information Processing Systems
article_processing_charge: No
author:
- first_name: Anastasia
full_name: Pentina, Anastasia
id: 42E87FC6-F248-11E8-B48F-1D18A9856A87
last_name: Pentina
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Pentina A, Lampert C. Lifelong learning with non-i.i.d. tasks. In: Vol 2015.
Neural Information Processing Systems Foundation; 2015:1540-1548.'
apa: 'Pentina, A., & Lampert, C. (2015). Lifelong learning with non-i.i.d. tasks
(Vol. 2015, pp. 1540–1548). Presented at the NIPS: Neural Information Processing
Systems, Montreal, Canada: Neural Information Processing Systems Foundation.'
chicago: Pentina, Anastasia, and Christoph Lampert. “Lifelong Learning with Non-i.i.d.
Tasks,” 2015:1540–48. Neural Information Processing Systems Foundation, 2015.
ieee: 'A. Pentina and C. Lampert, “Lifelong learning with non-i.i.d. tasks,” presented
at the NIPS: Neural Information Processing Systems, Montreal, Canada, 2015, vol.
2015, pp. 1540–1548.'
ista: 'Pentina A, Lampert C. 2015. Lifelong learning with non-i.i.d. tasks. NIPS:
Neural Information Processing Systems, Advances in Neural Information Processing
Systems, vol. 2015, 1540–1548.'
mla: Pentina, Anastasia, and Christoph Lampert. Lifelong Learning with Non-i.i.d.
Tasks. Vol. 2015, Neural Information Processing Systems Foundation, 2015,
pp. 1540–48.
short: A. Pentina, C. Lampert, in:, Neural Information Processing Systems Foundation,
2015, pp. 1540–1548.
conference:
end_date: 2015-12-12
location: Montreal, Canada
name: 'NIPS: Neural Information Processing Systems'
start_date: 2015-12-07
date_created: 2018-12-11T11:51:57Z
date_published: 2015-01-01T00:00:00Z
date_updated: 2025-06-03T11:41:45Z
day: '01'
department:
- _id: ChLa
ec_funded: 1
intvolume: ' 2015'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: http://papers.nips.cc/paper/6007-lifelong-learning-with-non-iid-tasks
month: '01'
oa: 1
oa_version: None
page: 1540 - 1548
project:
- _id: 2532554C-B435-11E9-9278-68D0E5697425
call_identifier: FP7
grant_number: '308036'
name: Lifelong Learning of Visual Scene Understanding
publication_status: published
publisher: Neural Information Processing Systems Foundation
publist_id: '5781'
quality_controlled: '1'
scopus_import: '1'
status: public
title: Lifelong learning with non-i.i.d. tasks
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 2015
year: '2015'
...
---
_id: '1857'
abstract:
- lang: eng
text: 'Sharing information between multiple tasks enables algorithms to achieve
good generalization performance even from small amounts of training data. However,
in a realistic scenario of multi-task learning not all tasks are equally related
to each other, hence it could be advantageous to transfer information only between
the most related tasks. In this work we propose an approach that processes multiple
tasks in a sequence with sharing between subsequent tasks instead of solving all
tasks jointly. Subsequently, we address the question of curriculum learning of
tasks, i.e. finding the best order of tasks to be learned. Our approach is based
on a generalization bound criterion for choosing the task order that optimizes
the average expected classification performance over all tasks. Our experimental
results show that learning multiple related tasks sequentially can be more effective
than learning them jointly, the order in which tasks are being solved affects
the overall performance, and that our model is able to automatically discover
the favourable order of tasks. '
article_processing_charge: No
arxiv: 1
author:
- first_name: Anastasia
full_name: Pentina, Anastasia
id: 42E87FC6-F248-11E8-B48F-1D18A9856A87
last_name: Pentina
- first_name: Viktoriia
full_name: Sharmanska, Viktoriia
id: 2EA6D09E-F248-11E8-B48F-1D18A9856A87
last_name: Sharmanska
orcid: 0000-0003-0192-9308
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Pentina A, Sharmanska V, Lampert C. Curriculum learning of multiple tasks.
In: IEEE; 2015:5492-5500. doi:10.1109/CVPR.2015.7299188'
apa: 'Pentina, A., Sharmanska, V., & Lampert, C. (2015). Curriculum learning
of multiple tasks (pp. 5492–5500). Presented at the CVPR: Computer Vision and
Pattern Recognition, Boston, MA, United States: IEEE. https://doi.org/10.1109/CVPR.2015.7299188'
chicago: Pentina, Anastasia, Viktoriia Sharmanska, and Christoph Lampert. “Curriculum
Learning of Multiple Tasks,” 5492–5500. IEEE, 2015. https://doi.org/10.1109/CVPR.2015.7299188.
ieee: 'A. Pentina, V. Sharmanska, and C. Lampert, “Curriculum learning of multiple
tasks,” presented at the CVPR: Computer Vision and Pattern Recognition, Boston,
MA, United States, 2015, pp. 5492–5500.'
ista: 'Pentina A, Sharmanska V, Lampert C. 2015. Curriculum learning of multiple
tasks. CVPR: Computer Vision and Pattern Recognition, 5492–5500.'
mla: Pentina, Anastasia, et al. Curriculum Learning of Multiple Tasks. IEEE,
2015, pp. 5492–500, doi:10.1109/CVPR.2015.7299188.
short: A. Pentina, V. Sharmanska, C. Lampert, in:, IEEE, 2015, pp. 5492–5500.
conference:
end_date: 2015-06-12
location: Boston, MA, United States
name: 'CVPR: Computer Vision and Pattern Recognition'
start_date: 2015-06-07
corr_author: '1'
date_created: 2018-12-11T11:54:23Z
date_published: 2015-06-01T00:00:00Z
date_updated: 2025-06-11T07:19:52Z
day: '01'
department:
- _id: ChLa
doi: 10.1109/CVPR.2015.7299188
external_id:
arxiv:
- '1412.1353'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: http://arxiv.org/abs/1412.1353
month: '06'
oa: 1
oa_version: Preprint
page: 5492 - 5500
publication_status: published
publisher: IEEE
publist_id: '5243'
quality_controlled: '1'
scopus_import: '1'
status: public
title: Curriculum learning of multiple tasks
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2015'
...
---
_id: '1706'
abstract:
- lang: eng
text: We consider a problem of learning kernels for use in SVM classification in
the multi-task and lifelong scenarios and provide generalization bounds on the
error of a large margin classifier. Our results show that, under mild conditions
on the family of kernels used for learning, solving several related tasks simultaneously
is beneficial over single task learning. In particular, as the number of observed
tasks grows, assuming that in the considered family of kernels there exists one
that yields low approximation error on all tasks, the overhead associated with
learning such a kernel vanishes and the complexity converges to that of learning
when this good kernel is given to the learner.
alternative_title:
- LNCS
article_processing_charge: No
arxiv: 1
author:
- first_name: Anastasia
full_name: Pentina, Anastasia
id: 42E87FC6-F248-11E8-B48F-1D18A9856A87
last_name: Pentina
- first_name: Shai
full_name: Ben David, Shai
last_name: Ben David
citation:
ama: 'Pentina A, Ben David S. Multi-task and lifelong learning of kernels. In: Vol
9355. Springer; 2015:194-208. doi:10.1007/978-3-319-24486-0_13'
apa: 'Pentina, A., & Ben David, S. (2015). Multi-task and lifelong learning
of kernels (Vol. 9355, pp. 194–208). Presented at the ALT: Algorithmic Learning
Theory, Banff, AB, Canada: Springer. https://doi.org/10.1007/978-3-319-24486-0_13'
chicago: Pentina, Anastasia, and Shai Ben David. “Multi-Task and Lifelong Learning
of Kernels,” 9355:194–208. Springer, 2015. https://doi.org/10.1007/978-3-319-24486-0_13.
ieee: 'A. Pentina and S. Ben David, “Multi-task and lifelong learning of kernels,”
presented at the ALT: Algorithmic Learning Theory, Banff, AB, Canada, 2015, vol.
9355, pp. 194–208.'
ista: 'Pentina A, Ben David S. 2015. Multi-task and lifelong learning of kernels.
ALT: Algorithmic Learning Theory, LNCS, vol. 9355, 194–208.'
mla: Pentina, Anastasia, and Shai Ben David. Multi-Task and Lifelong Learning
of Kernels. Vol. 9355, Springer, 2015, pp. 194–208, doi:10.1007/978-3-319-24486-0_13.
short: A. Pentina, S. Ben David, in:, Springer, 2015, pp. 194–208.
conference:
end_date: 2015-10-06
location: Banff, AB, Canada
name: 'ALT: Algorithmic Learning Theory'
start_date: 2015-10-04
corr_author: '1'
date_created: 2018-12-11T11:53:35Z
date_published: 2015-01-01T00:00:00Z
date_updated: 2025-09-23T09:36:51Z
day: '01'
department:
- _id: ChLa
doi: 10.1007/978-3-319-24486-0_13
ec_funded: 1
external_id:
arxiv:
- '1602.06531'
isi:
- '000367595100013'
intvolume: ' 9355'
isi: 1
language:
- iso: eng
main_file_link:
- open_access: '1'
url: http://arxiv.org/abs/1602.06531
month: '01'
oa: 1
oa_version: Preprint
page: 194 - 208
project:
- _id: 2532554C-B435-11E9-9278-68D0E5697425
call_identifier: FP7
grant_number: '308036'
name: Lifelong Learning of Visual Scene Understanding
publication_status: published
publisher: Springer
publist_id: '5430'
quality_controlled: '1'
scopus_import: '1'
status: public
title: Multi-task and lifelong learning of kernels
type: conference
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
volume: 9355
year: '2015'
...
---
_id: '2160'
abstract:
- lang: eng
text: Transfer learning has received a lot of attention in the machine learning
community over the last years, and several effective algorithms have been developed.
However, relatively little is known about their theoretical properties, especially
in the setting of lifelong learning, where the goal is to transfer information
to tasks for which no data have been observed so far. In this work we study lifelong
learning from a theoretical perspective. Our main result is a PAC-Bayesian generalization
bound that offers a unified view on existing paradigms for transfer learning,
such as the transfer of parameters or the transfer of low-dimensional representations.
We also use the bound to derive two principled lifelong learning algorithms, and
we show that these yield results comparable with existing methods.
article_processing_charge: No
author:
- first_name: Anastasia
full_name: Pentina, Anastasia
id: 42E87FC6-F248-11E8-B48F-1D18A9856A87
last_name: Pentina
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Pentina A, Lampert C. A PAC-Bayesian bound for Lifelong Learning. In: Vol
32. ML Research Press; 2014:991-999.'
apa: 'Pentina, A., & Lampert, C. (2014). A PAC-Bayesian bound for Lifelong Learning
(Vol. 32, pp. 991–999). Presented at the ICML: International Conference on Machine
Learning, Beijing, China: ML Research Press.'
chicago: Pentina, Anastasia, and Christoph Lampert. “A PAC-Bayesian Bound for Lifelong
Learning,” 32:991–99. ML Research Press, 2014.
ieee: 'A. Pentina and C. Lampert, “A PAC-Bayesian bound for Lifelong Learning,”
presented at the ICML: International Conference on Machine Learning, Beijing,
China, 2014, vol. 32, pp. 991–999.'
ista: 'Pentina A, Lampert C. 2014. A PAC-Bayesian bound for Lifelong Learning. ICML:
International Conference on Machine Learning vol. 32, 991–999.'
mla: Pentina, Anastasia, and Christoph Lampert. A PAC-Bayesian Bound for Lifelong
Learning. Vol. 32, ML Research Press, 2014, pp. 991–99.
short: A. Pentina, C. Lampert, in:, ML Research Press, 2014, pp. 991–999.
conference:
end_date: 2014-06-26
location: Beijing, China
name: 'ICML: International Conference on Machine Learning'
start_date: 2014-06-21
corr_author: '1'
date_created: 2018-12-11T11:56:03Z
date_published: 2014-05-10T00:00:00Z
date_updated: 2024-10-09T20:55:36Z
day: '10'
department:
- _id: ChLa
intvolume: ' 32'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://dl.acm.org/citation.cfm?id=3045003
month: '05'
oa: 1
oa_version: Submitted Version
page: 991 - 999
publication_status: published
publisher: ML Research Press
publist_id: '4844'
quality_controlled: '1'
scopus_import: '1'
status: public
title: A PAC-Bayesian bound for Lifelong Learning
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 32
year: '2014'
...