Improving Domain Generalization with Domain Relations
February 6, 2023
| | | | |
Computer Science
Machine Learning
Distribution shift presents a significant challenge in machine learning,
where models often underperform during the test stage when faced with a
different distribution than the one they were trained on. This paper focuses on
domain shifts, ...
Determinantally equivalent nonzero functions
February 5, 2023
|
Mathematics
Physics
Classical Analysis and ODEs
Mathematical Physics
Mathematical Physics
Classical Analysis and ODEs
Mathematical Physics
Mathematical Physics
We solve the problem posed in [Random Matrices: Theory and Applications,
10(03):2150027, 2021]. Plainly, let K and Q be two F-valued
functions over Λ2, where Λ is some abstract set (of arbitrary
cardinality) ...
On humanization of mathematics: aesthetic mathematics
February 5, 2023
|
Mathematics
History and Overview
History and Overview
This paper examines various methods and ideas for humanizing mathematics. The
term 'humanizing mathematics' which includes elements of 'aesthetic
mathematics' refers to approaches that emphasize the aesthetic, philosophical,
and subjective ...
Notes on the Golden Ratio: The Golden Rule of Vector Similarities in
Space
February 5, 2023
| | |
Mathematics
General Mathematics
General Mathematics
In this work, we have abstractly generalized the similarity law for
multidimensional vectors. Initially, the law of similarity was derived for
one-dimensional vectors. Although it operated with such values of the ratio of
parts of the whole...
Variational Inference on the Final-Layer Output of Neural Networks
February 5, 2023
|
Computer Science
Statistics
Machine Learning
Machine Learning
Traditional neural networks are simple to train but they typically produce
overconfident predictions. In contrast, Bayesian neural networks provide good
uncertainty quantification but optimizing them is time consuming due to the
large param...
First Constraints from DAMIC-M on Sub-GeV Dark-Matter Particles
Interacting with Electrons
February 5, 2023
| | | | | | | | | | and others
Physics
High Energy Physics - Experiment
Cosmology and Nongalactic Astrophysics
We report constraints on sub-GeV dark matter particles interacting with
electrons from the first underground operation of DAMIC-M detectors. The search
is performed with an integrated exposure of 85.23 g days, and exploits the
subelectron c...
A three-state coupled Markov switching model for COVID-19 outbreaks
across Quebec based on hospital admissions
February 5, 2023
| | |
Statistics
Quantitative Biology
Applications
Populations and Evolution
Recurrent COVID-19 outbreaks have placed immense strain on the hospital
system in Quebec. We develop a Bayesian three-state coupled Markov switching
model to analyze COVID-19 outbreaks across Quebec based on admissions in the 30
largest hos...
Circular and Spherical Projected Cauchy Distributions: A Novel Framework
for Circular and Directional Data Modeling
February 5, 2023
|
Statistics
Methodology
We introduce a novel family of projected distributions on the circle and the
sphere, namely the circular and spherical projected Cauchy distributions, as
promising alternatives for modelling circular and spherical data. The circular
distrib...
Know, Grow, and Protect Net Worth: Using ML for Asset Protection by
Preventing Overdraft Fees
February 5, 2023
|
Statistics
Computer Science
Machine Learning
Computers and Society
Machine Learning
When a customer overdraws their bank account and their balance is negative
they are assessed an overdraft fee. Americans pay approximately \$15 billion in
unnecessary overdraft fees a year, often in \$35 increments; users of the Mint
person...
Causal Estimation of Exposure Shifts with Neural Networks
February 5, 2023
| | |
Computer Science
Statistics
Machine Learning
Methodology
Machine Learning
A fundamental task in causal inference is estimating the effect of
distribution shift in the treatment variable. We refer to this problem as
shift-response function (SRF) estimation. Existing neural network methods for
causal inference lack...