Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Aditya Krishna Menon"'
Autor:
Tiansheng Yao, Evan Ettinger, Derek Zhiyuan Cheng, Jieqi Kang, Lichan Hong, Felix X. Yu, Aditya Krishna Menon, Ed H. Chi, Ting Chen, Steve Tjoa, Xinyang Yi
Publikováno v:
CIKM
Large scale recommender models find most relevant items from huge catalogs, and they play a critical role in modern search and recommendation systems. To model the input space with large-vocab categorical features, a typical recommender model learns
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::85631df687a53adc2af25608c4eeba34
https://doi.org/10.1145/3459637.3481952
https://doi.org/10.1145/3459637.3481952
Autor:
Michal Lukasik, Felix X. Yu, Seungyeon Kim, Sanjiv Kumar, Aditya Krishna Menon, Srinadh Bhojanapalli, Himanshu Jain
Publikováno v:
EMNLP (1)
Label smoothing has been shown to be an effective regularization strategy in classification, that prevents overfitting and helps in label de-noising. However, extending such methods directly to seq2seq settings, such as Machine Translation, is challe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::706f72dba84fdb0867a3d9c4f66bcab6
http://arxiv.org/abs/2010.07447
http://arxiv.org/abs/2010.07447
Publikováno v:
Scopus-Elsevier
EMNLP (Findings)
EMNLP (Findings)
Most work on multi-document summarization has focused on generic summarization of information present in each individual document set. However, the under-explored setting of update summarization, where the goal is to identify the new information pres
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3431bf451ad96ed511c3254dc15dd13a
http://arxiv.org/abs/2010.02568
http://arxiv.org/abs/2010.02568
Autor:
Aditya Krishna Menon
Publikováno v:
Machine Learning. 108:627-658
Given a sample of instances with binary labels, the bipartite top ranking problem is to produce a ranked list of instances whose head is dominated by positives. One popular existing approach to this problem is based on constructing surrogates to a pe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6c3938c6bfb3b4b40bda7d773f007b9f
https://doi.org/10.1007/s10994-018-5759-4
https://doi.org/10.1007/s10994-018-5759-4
Publikováno v:
Machine Learning. 107:1561-1595
Supervised learning has seen numerous theoretical and practical advances over the last few decades. However, its basic assumption of identical train and test distributions often fails to hold in practice. One important example of this is when the tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c3ef1f6fcd405f05d258e913d2db4dbd
https://doi.org/10.1007/s10994-018-5715-3
https://doi.org/10.1007/s10994-018-5715-3
Publikováno v:
Transportation Research Record: Journal of the Transportation Research Board. 2595:98-107
Probes with GPS devices reveal useful information for traffic conditions, but the high level of noise and the sparsity of observations make it challenging to estimate speed distribution from the data collected. This paper proposes a Bayesian approach
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a1612befa505d67940a06211ffd1bbb1
https://doi.org/10.3141/2595-11
https://doi.org/10.3141/2595-11
Playlist recommendation involves producing a set of songs that a user might enjoy. We investigate this problem in three cold-start scenarios: (i) cold playlists, where we recommend songs to form new personalised playlists for an existing user; (ii) c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9cd73f7766b777948e27df2f06b690a2
Publikováno v:
Scopus-Elsevier
AAAI
AAAI
This paper considers extractive summarisation in a comparative setting: given two or more document groups (e.g., separated by publication time), the goal is to select a small number of documents that are representative of each group, and also maximal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3efc7c5efad3b9116cffecec92acade6
Publikováno v:
Transportation Research Part B: Methodological. 80:150-172
Given a road network, a fundamental object of interest is the matrix of origin destination (OD) flows. Estimation of this matrix involves at least three sub-problems: (i) determining a suitable set of traffic analysis zones, (ii) the formulation of a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b6bc2ff0baa276f52eb9c7d2a8c9163b
https://doi.org/10.1016/j.trb.2015.07.003
https://doi.org/10.1016/j.trb.2015.07.003
Autor:
Young Lee, Aditya Krishna Menon
Publikováno v:
CIKM
Forecasting short term passenger demand for public transport is a core problem in urban mobility. Typically, this is addressed using Poisson regression or homogeneous Poisson processes. However, such approaches have several limitations, including sus
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::50ad4d05df44ee594fc3e696c0676f58
https://doi.org/10.1145/3132847.3133058
https://doi.org/10.1145/3132847.3133058