A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
For self-supervised learning, Rationality implies generalization, provably
[article]
2020
arXiv
pre-print
Preserved Fulltext
We prove a new upper bound on the generalization gap of classifiers that are obtained by first using self-supervision to learn a representation r of the training data, and then fitting a simple (e.g., ...
We show that our bound is non-vacuous for many popular representation-learning based classifiers on CIFAR-10 and ImageNet, including SimCLR, AMDIM and MoCo. ...
We also thank Oracle and Microsoft for grants used for computational resources. Y.B is partially supported by MIT-IBM Watson AI Lab. ...
arXiv:2010.08508v1
fatcat:zhgfvnhbunfffokrrdm67ledzu
Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2106.04156v5 fatcat:d65pecjrv5bslb6ctwpnnuoyfaOther Versions
Recent works in self-supervised learning have advanced the state-of-the-art by relying on the contrastive learning paradigm, which learns representations by pushing positive pairs, or similar examples ...
In all, this work provides the first provable analysis for contrastive learning where guarantees for linear probe evaluation can apply to realistic empirical settings. ...
Lee, Michael Xie, and Guodong Zhang for helpful discussions. CW acknowledges support from an NSF Graduate Research Fellowship. TM acknowledges support of Google Faculty Award and NSF IIS 2045685. ...
arXiv:2106.04156v6
fatcat:ky5nyxtdrjg5vj7he6m4wfqoea
New Millennium AI and the Convergence of History: Update of 2012
[chapter]
2012
The Frontiers Collection
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
There also has been rapid progress in not quite universal but still rather general and practical artificial recurrent neural networks for learning sequenceprocessing programs, now yielding state-of-the-art ...
the previously largely heuristic field of General AI and embedded agents. ...
Optimal Self-Referential General Problem Solver The recent Gödel machines [68, 72, 74] represent the first class of mathematically rigorous, general, fully self-referential, self-improving, optimally ...
doi:10.1007/978-3-642-32560-1_4
fatcat:rjsvw2jsk5apbg4cxnxfkzwjya
Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transport
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Selecting input features of top relevance has become a popular method for building self-explaining models. ...
In this work, we extend this selective rationalization approach to text matching, where the goal is to jointly select and align text pieces, such as tokens or sentences, as a justification for the downstream ...
Acknowledgments We thank Jesse Michel, Derek Chen, Yi Yang, and the anonymous reviewers for their valuable discussions. ...
arXiv:2005.13111v1
fatcat:px3x7mhxmvejrbtzqmefews5f4
Franco Montagna's Work on Provability Logic and Many-valued Logic
2016
Studia Logica: An International Journal for Symbolic Logic
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We survey some of his results and ideas in the two disciplines he greatly contributed along his career: provability logic and many-valued logic. ...
We would like to thank the anonymous referees for careful reading and precious suggestions. ...
The work of the first author was supported by Russian Foundation for Basic Research, project No. 15-01-09218a. ...
doi:10.1007/s11225-016-9654-3
fatcat:7dhk6qh25fdvfg2q3mydf4qs6m
Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
the mean-field regime, (non-)convergence of policy-based methods for learning in games, etc. ...
Recent years have witnessed significant advances in reinforcement learning (RL), which has registered great success in solving various sequential decision-making problems in machine learning. ...
, with the policy mixture being learned through supervised learning. ...
arXiv:1911.10635v2
fatcat:ihlhtjlhnrdizbkcfzsnz5urfq
Should Robots be Obedient?
2017
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Thus, there is a tradeoff between the obedience of a robot and the value it can attain for its owner. ...
Intuitively, obedience -- following the order that a human gives -- seems like a good property for a robot to have. ...
Acknowledgements We thank Daniel Filan for feedback on an early draft. ...
doi:10.24963/ijcai.2017/662
dblp:conf/ijcai/MilliHDR17
fatcat:zhvquksfp5cf5fdvxr2qi7xhtu
Should Robots be Obedient?
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Thus, there is a tradeoff between the obedience of a robot and the value it can attain for its owner. ...
Intuitively, obedience -- following the order that a human gives -- seems like a good property for a robot to have. ...
We wish to analyze R's incentive to obey H given that We first contribute a general model for this type of interaction, which we call a supervision POMDP. ...
arXiv:1705.09990v1
fatcat:shak3nj47vh7tginijzkzn56ha
Taking Uncertainty Seriously: Adaptive Governance and International Trade: A Rejoinder to Monica Garcia-Salmones
2009
European journal of international law
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We are grateful, therefore, to Mónica García-Salmones for her response to our article, and are pleased to have this opportunity to clarify some aspects of our thinking and our approach that may not have ...
While we view the WTO as a policy arena that can be used for enhancing learning, the possibility of such learning does not in our view imply unproblematic harmony between actors ' interests. ...
, and policy choices are justifi ed as products of enlightened rationality. ...
doi:10.1093/ejil/chp007
fatcat:e4nx6h34ibh7zemw3tmdtvnoiy
Impossibility Results in AI: A Survey
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2109.00484v1 fatcat:hyfjj24pcjdejn3uj7aof7cgfq
The remaining results deal with misalignment between the clones and put a limit to the self-awareness of agents. We concluded that deductive impossibilities deny 100%-guarantees for security. ...
They were first formulated in general supervised learning and optimization, which were subsequently unified through that framework. ...
agents
[42], [43]
Y
I
No Free Lunch -
supervised learning
[15]
Y
I
No Free Lunch -
[16]
Y
I ...
arXiv:2109.00484v2
fatcat:466ohk3tczefdaa7xhf3i32uuu
Systems Challenges for Trustworthy Embodied Systems
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2201.03413v1 fatcat:wykeewanave3jmpnrsclkyzzhq
A new generation of increasingly autonomous and self-learning embodied systems is about to be developed. ...
self-integration, and continual analysis and assurance. ...
This ability of self-learning through exploration is, of course, a far cry from supervised machine learning schemes for synthesizing, say, neural network representations for approximating functions from ...
arXiv:2201.03413v2
fatcat:hwprg3zjhvfuro3etecx2t4qua
Bayesian cognitive science, predictive brains, and the nativism debate
2017
Synthese
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Unlike Connectionism, the Bayesian approach would show how unsupervised and self-supervised forms of hierarchical learning can be responsible for the quick, robust, and smooth acquisition of novel psychological ...
These networks could successfully carry out their processing in a self-supervised fashion by learning a compact, invertible code that allowed them to reconstruct their own input on their output (i.e., ...
doi:10.1007/s11229-017-1427-7
fatcat:wcjelmh47relnightn2g5n2tby
Learning Whenever Learning is Possible: Universal Learning under General Stochastic Processes
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This work initiates a general study of learning and generalization without the i.i.d. assumption, starting from first principles. ...
We study this question in three natural learning settings: inductive, self-adaptive, and online. ...
In the special case of an i.i.d. process, the self-adaptive setting is closely related to the semi-supervised learning setting studied in the statistical learning theory literature (Chapelle, Schölkopf ...
arXiv:1706.01418v2
fatcat:neq4yc5fqzdahopslcc23fgrhe
Toward an AI Physicist for Unsupervised Learning
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We investigate opportunities and challenges for improving unsupervised machine learning using four common strategies with a long history in physics: divide-and-conquer, Occam's razor, unification and lifelong ...
learning. ...
We thank Isaac Chuang, John Peurifoy and Marin Soljačić for helpful discussions and suggestions, and the Center for Brains, Minds, and Machines (CBMM) for hospitality. ...
arXiv:1810.10525v3
fatcat:j75ejqkuifae5ljwvpygxy2xi4
Multi-agent Reinforcement Learning: An Overview
[chapter]
2010
Studies in Computational Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
This chapter reviews a representative selection of Multi-Agent Reinforcement Learning (MARL) algorithms for fully cooperative, fully competitive, and more general (neither cooperative nor competitive) ...
The agents must instead discover a solution on their own, using learning. A significant part of the research on multi-agent learning concerns reinforcement learning techniques. ...
Together with the simplicity and generality of the setting, this makes RL attractive also for multi-agent learning. ...
doi:10.1007/978-3-642-14435-6_7
fatcat:uonoth4kijcjdohhnq73upjnzu
« Previous
Showing results 1 — 15 out of 800 results