Filters








27 Hits in 9.1 sec

An Axiomatic Theory of Provably-Fair Welfare-Centric Machine Learning [article]

Cyrus Cousins
2021 arXiv   pre-print
We address an inherent difficulty in welfare-theoretic fair machine learning by proposing an equivalently axiomatically-justified alternative and studying the resulting computational and statistical learning  ...  Unfortunately, many machine-learning problems are more naturally cast as loss minimization tasks, rather than utility maximization, which complicates direct application of welfare-centric methods to fair  ...  between computational learning theory and fair machine learning research.  ... 
arXiv:2104.14504v2 fatcat:k562rqjc3vdf5ilfvv5yddoauq

Uncertainty and the Social Planner's Problem: Why Sample Complexity Matters

Cyrus Cousins
2022 2022 ACM Conference on Fairness, Accountability, and Transparency  
We show novel bounds on the expectations and tail probabilities of estimators of welfare, malfare, and regret of per-group (dis)utility values, where estimates are made from a finite sample drawn from  ...  We then study algorithmic fairness through the lens of sample complexity, finding that because marginalized or minority groups are often understudied, and fewer data are therefore available, the social  ...  PAC learning [7, 39] , and fair-PAC learning [14] settings, while enjoying rigorous statistical learning guarantees and the axiomatization of cardinal welfare theory.  ... 
doi:10.1145/3531146.3533243 fatcat:ifq6sxlcqvcgxh2uuzvpbi55im

The Objective Function: Science and Society in the Age of Machine Intelligence [article]

Emanuel Moss
2022 arXiv   pre-print
This naive empiricism eschews other forms of knowledge and theory formation in order for applied machine learning researchers to enact data performances that bring objects of analysis into existence as  ...  to support the work of applied machine learning researchers.  ...  a range of metrical analyses to demonstrate the validity of their techniques, and to support their overall claim that their "model could learn the perceived  ... 
arXiv:2209.10418v1 fatcat:rx3a75ut2bgmlfuqfqd6vuwt6u

Enabling Long-term Fairness in Dynamic Resource Allocation [article]

T. Si Salem, G. Iosifidis, G. Neglia
2022 arXiv   pre-print
We argue that horizon-fairness comes at a lower price in terms of social welfare.  ...  We study horizon-fairness with the regret as a performance metric and show that vanishing regret cannot be achieved in presence of an unrestricted adversary.  ...  Online Learning Achieving horizon-fairness in our setup requires technical extensions to the theory of OCO [31] .  ... 
arXiv:2208.05898v1 fatcat:q4reoflchzh3xozmyykunagzay

Technology and Consciousness [article]

John Rushby, Daniel Sanchez
2022 arXiv   pre-print
In the body of the report, we summarize most of the basic themes that were discussed: the structure and function of the brain, theories of consciousness, explicit attempts to construct conscious machines  ...  An appendix outlines the topics of each workshop and provides abstracts of the talks delivered.  ...  The present authors are beneficiaries of their hard work.  ... 
arXiv:2209.03956v1 fatcat:o3hnlo7aibdhhb27vk7kr7exwe

The Conference Paper Assignment Problem: Using Order Weighted Averages to Assign Indivisible Goods

Jing Wu Lian, Nicholas Mattei, Renee Noble, Toby Walsh
2018 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We show an algorithm for finding an SUM-OWA assignment in polynomial time, in contrast to the NP-hardness of finding an egalitarian assignment.  ...  Drawing inspiration from work in multi-criteria decision making and social choice theory we use order weighted averages (OWAs), a parameterized class of mean aggregators, to propose a novel and flexible  ...  Data61 is supported by the Australian Government through the Department of Communications and the Australian Research Council through the ICT Centre of Excellence Program.  ... 
doi:10.1609/aaai.v32i1.11484 fatcat:tsicmalhdvcnlgt33gshfwaaii

An Old Discipline with a New Twist: The Course "Logic in Action"

Johan van Benthem
2017 IfColog journal of logics and their applications (FLAP)  
tremendously importance of this topic at the crossing of many established disciplines.  ...  We would like to also thank again all the reviewers for the conference TTL 2015 as well as all the members of the organizing committee of TTL2015, M.  ...  He introduces the notion of logical completeness -both weak and strong-as an extension of the notion already introduced of "completeness of an axiomatic theory".  ... 
dblp:journals/flap/Benthem17 fatcat:e5d54ekdhrbmjcs3ywmfzhaslm

Toxicity Analysis and Cry Gene Profiling of Bacillus Thuringiensis Isolated from Western Ghats of Tamil Nadu State, India

A. Ramalakshmi, P. Annakodi, V. Udayasurian, V. Balasubramani
2018 Proceedings of the Indian National Science Academy  
Turing -British mathematician established that there is no method to solve this problem through a formal definition of an abstract machine, now referred to as Turing Machine.  ...  or that can be built in future) requiring unbounded amounts of resource is also solvable by a Turing Machine.  ...  Machine Learning and Deep Learning has been offered as a standard package on varieties of systems.  ... 
doi:10.16943/ptinsa/2018/49413 fatcat:2w6rohpbava5zh6m26tsiz7qky

What Should We Do After Work? Automation and Employment Law

Cynthia L. Estlund
2017 Social Science Research Network  
welfare state); GØSTA ESPING-ANDERSEN: THE THREE WORLDS OF WELFARE CAPITALISM (1990) (distinguishing three major types of welfare state in advanced Western countries).  ...  that equips them to learn how to learn.  ... 
doi:10.2139/ssrn.3007972 fatcat:7rdb6pux6vdpbdqgin5ujlhq3u

Marxism and Deconstruction: A Critical Articulation

Andrew Parker, Michael Ryan
1982 MLN: Modern Language Notes  
The problem is Habermas's starting point, that his theory depends on a normative starting point that constitutes an assumed, self-evident axiomatic origin around which the rest of the theory is built.  ...  that posits the centricity of the penis and the marginality of woman.  ... 
doi:10.2307/2905987 fatcat:ulk3yg45g5fb5lgg64clzo72za

Dagstuhl Reports, Volume 9, Issue 9, September 2019, Complete Issue

2020
Machine Learning, including the study of problems that can be solved using either logic-based techniques or via machine learning, an exploration of the trade-offs between these techniques, and the development  ...  We observe that the traditional roles of humans and machines are subject to change due to the availability of data and advances in machine learning.  ...  What partial orders for a class of graph polynomials arise from these? What can we learn from the structure of such a poset?  ... 
doi:10.4230/dagrep.9.9 fatcat:yxieovrp4zbxvhjyyiah6znqxm

Dagstuhl Reports, Volume 6, Issue 6, June 2016, Complete Issue [article]

2016
Funding by the CITEC center of excellence is gratefully acknowledged. References  ...  We thank all attendees of this Dagstuhl Perspectives Workshop, who have made this into a successful workshop with so many outcomes.  ...  Nash Social Welfare Approximation for Strategic Agents The fair division of resources among strategic agents is an important age-old problem that has led to a rich body of literature.  ... 
doi:10.4230/dagrep.6.6 fatcat:bahw4gi2tjfdth3kvsi3k2uc6i

Equity and Efficiency in Computational Social Choice

Johannes Benade
2019
An algorithm has vanishing envy if the ratio of envy over time goes to zero as time goes to infinity.  ...  Next,we take a very different approach, and assume votes are noisy estimates of an unknown ground truth.  ...  For example, a growing part in the machine learning community works on how to eliminate forms of bias from machine learning algorithms.  ... 
doi:10.1184/r1/9546908 fatcat:p4xgtldyknhilds4sjujdlgkxm

Dagstuhl Reports, Volume 9, Issue 1, January 2019, Complete Issue [article]

2019
Our notion of fairness is Nash social welfare, i.e., the goal is to maximize the geometric mean of the utilities of the agents.  ...  as data-driven machine learning approaches.  ...  Such insights may refer to different aspects, e. g. machine learning insights or general MIR insights.  ... 
doi:10.4230/dagrep.9.1 fatcat:m3grhk5hanccbg7oxkhos7kv4e

2015 Jahresbericht Annual Report

Registernummer Amtsgericht, Saarbrücken Hrb, Vorsitzender Des Aufsichtsrates, Ing, Jähnichen Stefan, Raimund Geschäftsführung, Seidel, Meißner Heike, Gesellschafter
unpublished
Martin Rinard for his support and contribution to the organization of the seminar. We thank Sara Achour for her help with preparing the full report.  ...  We would like to thank Dagmar Glaser and the staff at Schloss Dagstuhl for their continuous support and great hospitality which was the basis for the success of this seminar. Acknowledgements.  ...  Most of the body of work on machine learning theory is on learning with i.i.d. data.  ... 
fatcat:tzkatxrngzbj7j3qvr7j7znvla
« Previous Showing results 1 — 15 out of 27 results