Zobrazeno 1 - 10 of 55 pro vyhledávání: '"Adish Singla"'
1
Generating High-Precision Feedback for Programming Syntax Errors using Large Language Models
Autor: Phung, Tung, Cambronero, José, Gulwani, Sumit, Kohn, Tobias, Rupak Majumdar, Adish Singla, Soares, Gustavo
Large language models (LLMs), such as Codex, hold great promise in enhancing programming education by automatically generating feedback for students. We investigate using LLMs to generate feedback for fixing syntax errors in Python programs, a key sc
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7ee56fa082310568938966b76822eae9
Zobrazit plný text záznamu
2
On the Fairness of Time-Critical Influence Maximization in Social Networks
Autor: Krishna P. Gummadi, Adish Singla, Junaid Ali, Abhijnan Chakraborty, Mahmoudreza Babaei, Baharan Mirzasoleiman
Publikováno v: IEEE Transactions on Knowledge and Data Engineering
Influence maximization has found applications in a wide range of real-world problems, for instance, viral marketing of products in an online social network, and information propagation of valuable information such as job vacancy advertisements and he
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::707eba42885c3e4675655dd1f6bdb311
https://hdl.handle.net/21.11116/0000-000C-B657-521.11116/0000-000C-B659-3
Zobrazit plný text záznamu
4
Bayesian Persuasion in Sequential Decision-Making
Autor: Jiarui Gan, Rupak Majumdar, Goran Radanovic, Adish Singla
Publikováno v: Proceedings of the 36th AAAI Conference on Artificial Intelligence
We study a dynamic model of Bayesian persuasion in sequential decision-making settings. An informed principal observes an external parameter of the world and advises an uninformed agent about actions to take over time. The agent takes actions in each
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8fe4df97d3c85520773588d658e505b1
http://arxiv.org/abs/2106.05137
Zobrazit plný text záznamu
5
The Sample Complexity of Teaching by Reinforcement on {Q}-Learning
Autor: Xuezhou Zhang, Shubham Bharti, Yuzhe Ma, Adish Singla, Xiaojin Zhu
Publikováno v: AAAI Technical Track on Machine Learning V
We study the sample complexity of teaching, termed as ``teaching dimension" (TDim) in the literature, for the teaching-by-reinforcement paradigm, where the teacher guides the student through rewards. This is distinct from the teaching-by-demonstratio
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b56ca4ace92a28b0dc28fd83f51aae4e
https://ojs.aaai.org/index.php/AAAI/article/view/17306
Zobrazit plný text záznamu
6
Loss-Aversively Fair Classification
Autor: Adish Singla, Muhammad Bilal Zafar, Junaid Ali, Krishna P. Gummadi
Publikováno v: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society-AIES 19
Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society -AIES '19
AIES
Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society
AIES'19
The use of algorithmic (learning-based) decision making in scenarios that affect human lives has motivated a number of recent studies to investigate such decision making systems for potential unfairness, such as discrimination against subjects based
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2fb9593a93e1e235751693628cf91dba
Zobrazit plný text záznamu
7
Can A User Guess What Her Followers Want?
Autor: Utkarsh Upadhyay, Abir De, Adish Singla, Manuel Gomez-Rodriguez
Publikováno v: WSDM
Whenever a social media user decides to share a story, she is typically pleased to receive likes, comments, shares, or, more generally, feedback from her followers. As a result, she may feel compelled to use the feedback she receives to (re-)estimate
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::ddc05f1ea890944e6f77b214049245b4
https://doi.org/10.1145/3336191.3371803
Zobrazit plný text záznamu
8
Understanding the Power and Limitations of Teaching with Imperfect Knowledge
Autor: Luis Haug, Adish Singla, Rati Devidze, Yuxin Chen, Farnam Mansouri
Publikováno v: IJCAI
Machine teaching studies the interaction between a teacher and a student/learner where the teacher selects training examples for the learner to learn a specific task. The typical assumption is that the teacher has perfect knowledge of the task---this
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::145e2057539c283c6036fca35e380cba
Zobrazit plný text záznamu
9
Interactive Teaching Algorithms for Inverse Reinforcement Learning
Autor: Rati Devidze, Adish Singla, Volkan Cevher, Parameswaran Kamalaruban
Publikováno v: IJCAI
We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner is assisted by a helpful teacher. More formally, we tackle the following algorithmic question: How could a teacher provide an informative sequence of d
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3d120d3f6dfa56e02a9f837445ca14ec
http://arxiv.org/abs/1905.11867
Zobrazit plný text záznamu
10
Evaluating Task-Dependent Taxonomies for Navigation
Autor: Yuyin Sun, Adish Singla, Tori Yan, Andreas Krause, Dieter Fox
Publikováno v: Proceedings of the AAAI Conference on Human Computation and Crowdsourcing. 4:229-238
Taxonomies of concepts are important across many application domains, for instance, online shopping portals use catalogs to help users navigate and search for products. Task-dependent taxonomies, e.g., adapting the taxonomy to a specific cohort of us
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b46947741cee47eecca93a1c25a7cc56
https://doi.org/10.1609/hcomp.v4i1.13286
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje