@Preamble{"\input bibnames.sty" #
"\def \TM {${}^{\sc TM}$}"
}
@String{ack-nhfb = "Nelson H. F. Beebe,
University of Utah,
Department of Mathematics, 110 LCB,
155 S 1400 E RM 233,
Salt Lake City, UT 84112-0090, USA,
Tel: +1 801 581 5254,
e-mail: \path|beebe@math.utah.edu|,
\path|beebe@acm.org|,
\path|beebe@computer.org| (Internet),
URL: \path|https://www.math.utah.edu/~beebe/|"}
@String{j-ACM-IMS-J-DATA-SCI = "ACM\slash IMS Journal of Data Science"}
@Article{Bradic:2024:AIJ,
author = "Jelena Bradic and Stratos Idreos and John Lafferty",
title = "{{ACM\slash} IMS} Journal of Data Science: Inaugural
Issue Editorial",
journal = j-ACM-IMS-J-DATA-SCI,
volume = "1",
number = "1",
pages = "1:1--1:??",
month = mar,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3644102",
ISSN = "2831-3194",
ISSN-L = "2831-3194",
bibdate = "Wed Apr 3 11:24:34 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/jds.bib",
URL = "https://dl.acm.org/doi/10.1145/3644102",
acknowledgement = ack-nhfb,
ajournal = "ACM\slash IMS J. Data Sci.",
articleno = "1e",
fjournal = "ACM\slash IMS Journal of Data Science",
journal-URL = "https://dl.acm.org/loi/jds",
}
@Article{Gu:2024:BNB,
author = "Quanquan Gu and Amin Karbasi and Khashayar Khosravi
and Vahab Mirrokni and Dongruo Zhou",
title = "Batched Neural Bandits",
journal = j-ACM-IMS-J-DATA-SCI,
volume = "1",
number = "1",
pages = "1:1--1:??",
month = mar,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3592474",
ISSN = "2831-3194",
ISSN-L = "2831-3194",
bibdate = "Wed Apr 3 11:24:34 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/jds.bib",
URL = "https://dl.acm.org/doi/10.1145/3592474",
abstract = "In many sequential decision-making problems, the
individuals are split into several batches and the
decision-maker is only allowed to change her policy at
the end of batches. These batch problems have a large
number of applications, ranging from clinical
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM\slash IMS J. Data Sci.",
articleno = "1",
fjournal = "ACM\slash IMS Journal of Data Science",
journal-URL = "https://dl.acm.org/loi/jds",
}
@Article{Heidari:2024:RFI,
author = "Alireza Heidari and George Michalopoulos and Ihab F.
Ilyas and Theodoros Rekatsinas",
title = "Record Fusion via Inference and Data Augmentation",
journal = j-ACM-IMS-J-DATA-SCI,
volume = "1",
number = "1",
pages = "2:1--2:??",
month = mar,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3593579",
ISSN = "2831-3194",
ISSN-L = "2831-3194",
bibdate = "Wed Apr 3 11:24:34 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/jds.bib",
URL = "https://dl.acm.org/doi/10.1145/3593579",
abstract = "We introduce a learning framework for the problem of
unifying conflicting data in multiple records referring
to the same entity --- we call this problem ``record
fusion.'' Record fusion generalizes two known problems:
``data fusion'' and ``golden record.'' Our \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM\slash IMS J. Data Sci.",
articleno = "2",
fjournal = "ACM\slash IMS Journal of Data Science",
journal-URL = "https://dl.acm.org/loi/jds",
}
@Article{Opipari:2024:DDN,
author = "Anthony Opipari and Jana Pavlasek and Chao Chen and
Shoutian Wang and Karthik Desingh and Odest Chadwicke
Jenkins",
title = "{DNBP}: Differentiable Nonparametric Belief
Propagation",
journal = j-ACM-IMS-J-DATA-SCI,
volume = "1",
number = "1",
pages = "3:1--3:??",
month = mar,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3592762",
ISSN = "2831-3194",
ISSN-L = "2831-3194",
bibdate = "Wed Apr 3 11:24:34 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/jds.bib",
URL = "https://dl.acm.org/doi/10.1145/3592762",
abstract = "We present a differentiable approach to learn the
probabilistic factors used for inference by a
nonparametric belief propagation algorithm. Existing
nonparametric belief propagation methods rely on
domain-specific features encoded in the probabilistic
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM\slash IMS J. Data Sci.",
articleno = "3",
fjournal = "ACM\slash IMS Journal of Data Science",
journal-URL = "https://dl.acm.org/loi/jds",
}
@Article{Kang:2024:DMM,
author = "Daniel Kang and John Guibas and Peter Bailis and
Tatsunori Hashimoto and Yi Sun and Matei Zaharia",
title = "Data Management for {ML}-Based Analytics and Beyond",
journal = j-ACM-IMS-J-DATA-SCI,
volume = "1",
number = "1",
pages = "4:1--4:??",
month = mar,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3611093",
ISSN = "2831-3194",
ISSN-L = "2831-3194",
bibdate = "Wed Apr 3 11:24:34 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/jds.bib",
URL = "https://dl.acm.org/doi/10.1145/3611093",
abstract = "The increasing capabilities of machine learning (ML)
has enabled the deployment of ML methods in a variety
of applications, ranging from unstructured data
analytics to autonomous vehicles. Due to the volumes of
data over which ML is deployed, it is \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM\slash IMS J. Data Sci.",
articleno = "4",
fjournal = "ACM\slash IMS Journal of Data Science",
journal-URL = "https://dl.acm.org/loi/jds",
}
@Article{Miao:2024:ISE,
author = "Wang Miao and Lan Liu and Yilin Li and Eric J.
Tchetgen Tchetgen and Zhi Geng",
title = "Identification and Semiparametric Efficiency Theory of
Nonignorable Missing Data with a Shadow Variable",
journal = j-ACM-IMS-J-DATA-SCI,
volume = "1",
number = "2",
pages = "5:1--5:??",
month = jun,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3592389",
ISSN = "2831-3194",
ISSN-L = "2831-3194",
bibdate = "Tue Aug 20 09:27:05 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/jds.bib",
URL = "https://dl.acm.org/doi/10.1145/3592389",
abstract = "We consider identification and estimation with an
outcome missing not at random (MNAR). We study an
identification strategy based on a so-called shadow
variable. A shadow variable is assumed to be correlated
with the outcome but independent of the \ldots{}
Highlights Problem statement Missingness not at random
(MNAR) arises in many empirical studies in biomedical,
socioeconomic, and epidemiological researches. A
fundamental problem of MNAR is the identification
problem, that is, the parameter of interest \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM\slash IMS J. Data Sci.",
articleno = "5",
fjournal = "ACM\slash IMS Journal of Data Science",
journal-URL = "https://dl.acm.org/loi/jds",
}
@Article{Zhou:2024:ORU,
author = "Lijia Zhou and Frederic Koehler and Danica J.
Sutherland and Nathan Srebro",
title = "Optimistic Rates: a Unifying Theory for Interpolation
Learning and Regularization in Linear Regression",
journal = j-ACM-IMS-J-DATA-SCI,
volume = "1",
number = "2",
pages = "6:1--6:??",
month = jun,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3594234",
ISSN = "2831-3194",
ISSN-L = "2831-3194",
bibdate = "Tue Aug 20 09:27:05 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/jds.bib",
URL = "https://dl.acm.org/doi/10.1145/3594234",
abstract = "We study a localized notion of uniform convergence
known as an ``optimistic rate'' [ 34 , 39 ] for linear
regression with Gaussian data. Our refined analysis
avoids the hidden constant and logarithmic factor in
existing results, which are known to be crucial
\ldots{} Highlights Problem Statement Generalization
theory proposes to explain the ability of machine
learning models to generalize to fresh examples by
bounding the gap between the test error (error on new
examples) and training error (error on the data they
\ldots{})",
acknowledgement = ack-nhfb,
ajournal = "ACM\slash IMS J. Data Sci.",
articleno = "6",
fjournal = "ACM\slash IMS Journal of Data Science",
journal-URL = "https://dl.acm.org/loi/jds",
}
@Article{Smith:2024:LML,
author = "Ryan Smith and Jason A. Fries and Braden Hancock and
Stephen H. Bach",
title = "Language Models in the Loop: Incorporating Prompting
into Weak Supervision",
journal = j-ACM-IMS-J-DATA-SCI,
volume = "1",
number = "2",
pages = "7:1--7:??",
month = jun,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3617130",
ISSN = "2831-3194",
ISSN-L = "2831-3194",
bibdate = "Tue Aug 20 09:27:05 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/jds.bib",
URL = "https://dl.acm.org/doi/10.1145/3617130",
abstract = "We propose a new strategy for applying large
pre-trained language models to novel tasks when labeled
training data is limited. Rather than apply the model
in a typical zero-shot or few-shot fashion, we treat
the model as the basis for labeling functions \ldots{}
Highlights Problem statement The goal of this paper is
to use large language models to create smaller,
specialized models. These specialized models can be
better suited to specific tasks because they are tuned
for them and are less expensive to serve in \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM\slash IMS J. Data Sci.",
articleno = "7",
fjournal = "ACM\slash IMS Journal of Data Science",
journal-URL = "https://dl.acm.org/loi/jds",
}
@Article{Waleffe:2024:PCN,
author = "Roger Waleffe and Theodoros Rekatsinas",
title = "Principal Component Networks: Utilizing Low-Rank
Activation Structure to Reduce Parameters Early in
Training",
journal = j-ACM-IMS-J-DATA-SCI,
volume = "1",
number = "2",
pages = "8:1--8:??",
month = jun,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3617778",
ISSN = "2831-3194",
ISSN-L = "2831-3194",
bibdate = "Tue Aug 20 09:27:05 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/jds.bib",
URL = "https://dl.acm.org/doi/10.1145/3617778",
abstract = "Recent works show that overparameterized neural
networks contain small subnetworks that exhibit
comparable accuracy to the full model when trained in
isolation. These results highlight the potential to
reduce the computational costs of deep neural network
\ldots{} Highlights Problem Statement Many recent
results show that large neural networks can lead to
improved generalization. Yet, training these large
models comes with increased computational costs. In an
effort to address this issue, several works have show
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM\slash IMS J. Data Sci.",
articleno = "8",
fjournal = "ACM\slash IMS Journal of Data Science",
journal-URL = "https://dl.acm.org/loi/jds",
}
@Article{Li:2024:PIN,
author = "Zongyi Li and Hongkai Zheng and Nikola Kovachki and
David Jin and Haoxuan Chen and Burigede Liu and Kamyar
Azizzadenesheli and Anima Anandkumar",
title = "Physics-Informed Neural Operator for Learning Partial
Differential Equations",
journal = j-ACM-IMS-J-DATA-SCI,
volume = "1",
number = "3",
pages = "9:1--9:??",
month = sep,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3648506",
ISSN = "2831-3194",
ISSN-L = "2831-3194",
bibdate = "Tue Aug 20 09:27:05 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/jds.bib",
URL = "https://dl.acm.org/doi/10.1145/3648506",
abstract = "In this article, we propose physics-informed neural
operators (PINO) that combine training data and physics
constraints to learn the solution operator of a given
family of parametric Partial Differential Equations
(PDE). PINO is the first hybrid approach \ldots{}
Highlights PROBLEM STATEMENT Machine learning methods
have recently shown promise in solving partial
differential equations (PDEs) raised in science and
engineering. They can be classified into two broad
categories: approximating the solution function
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM\slash IMS J. Data Sci.",
articleno = "9",
fjournal = "ACM\slash IMS Journal of Data Science",
journal-URL = "https://dl.acm.org/loi/jds",
}
@Article{Waudby-Smith:2024:AVP,
author = "Ian Waudby-Smith and Lili Wu and Aaditya Ramdas and
Nikos Karampatziakis and Paul Mineiro",
title = "Anytime-valid off-policy Inference for Contextual
Bandits",
journal = j-ACM-IMS-J-DATA-SCI,
volume = "1",
number = "3",
pages = "10:1--10:??",
month = sep,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3643693",
ISSN = "2831-3194",
ISSN-L = "2831-3194",
bibdate = "Tue Aug 20 09:27:05 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/jds.bib",
URL = "https://dl.acm.org/doi/10.1145/3643693",
abstract = "Contextual bandit algorithms are ubiquitous tools for
active sequential experimentation in healthcare and the
tech industry. They involve online learning algorithms
that adaptively learn policies over time to map
observed contexts X$_t$ to actions A$_t$ in an \ldots{}
Highlights PROBLEM STATEMENT Contextual bandits and
adaptive experimentation are becoming increasingly
commonplace in the tech industry and health sciences.
The problem setting consists of (at each time t )
observing a context X$_t$, taking a randomized
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM\slash IMS J. Data Sci.",
articleno = "10",
fjournal = "ACM\slash IMS Journal of Data Science",
journal-URL = "https://dl.acm.org/loi/jds",
}
@Article{Belkin:2024:NML,
author = "Mikhail Belkin",
title = "The Necessity of Machine Learning Theory in Mitigating
{AI} Risk",
journal = j-ACM-IMS-J-DATA-SCI,
volume = "1",
number = "3",
pages = "11:1--11:??",
month = sep,
year = "2024",
CODEN = "????",
DOI = "https://doi.org/10.1145/3643694",
ISSN = "2831-3194",
ISSN-L = "2831-3194",
bibdate = "Tue Aug 20 09:27:05 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/jds.bib",
URL = "https://dl.acm.org/doi/10.1145/3643694",
abstract = "Highlights SUMMARY In the last years we have witnessed
rapidly accelerating progress in Neural Network-based
Artificial Intelligence. Yet our fundamental
understanding of these methods has lagged far behind.
Never before had a technology been developed \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM\slash IMS J. Data Sci.",
articleno = "11",
fjournal = "ACM\slash IMS Journal of Data Science",
journal-URL = "https://dl.acm.org/loi/jds",
}
