CosPGD: an efficient white-box adversarial attack for pixel-wise
prediction tasks
February 4, 2023
| |
Computer Science
Computer Vision and Pattern Recognition
While neural networks allow highly accurate predictions in many tasks, their
lack of robustness towards even slight input perturbations often hampers their
deployment. Adversarial attacks such as the seminal projected gradient descent
(PGD)...
Federated Temporal Difference Learning with Linear Function
Approximation under Environmental Heterogeneity
February 4, 2023
| | | |
Computer Science
Mathematics
Machine Learning
Optimization and Control
We initiate the study of federated reinforcement learning under environmental
heterogeneity by considering a policy evaluation problem. Our setup involves
N agents interacting with environments that share the same state and action
space b...
Shedding light on the pion production in heavy-ion collisions and
application into the neutron star matter properties
February 4, 2023
| | | | |
Physics
Nuclear Theory
Within the framework of the quantum molecular dynamics transport model, the
pion production and constraint of the high-density symmetry energy in heavy-ion
collisions near threshold energy have been thoroughly investigated. The energy
conse...
A Modified CTGAN-Plus-Features Based Method for Optimal Asset Allocation
February 4, 2023
| | | |
Quantitative Finance
Computer Science
Portfolio Management
Computational Engineering, Finance, and Science
We propose a new approach to portfolio optimization that utilizes a unique
combination of synthetic data generation and a CVaR-constraint. We formulate
the portfolio optimization problem as an asset allocation problem in which each
asset cl...
Digital Over-the-Air Federated Learning in Multi-Antenna Systems
February 4, 2023
| | | |
Computer Science
Mathematics
Information Theory
Artificial Intelligence
Machine Learning
Information Theory
In this paper, the performance optimization of federated learning (FL), when
deployed over a realistic wireless multiple-input multiple-output (MIMO)
communication system with digital modulation and over-the-air computation
(AirComp) is stu...
On 2-strong connectivity orientations of mixed graphs and related
problems
February 4, 2023
| |
Computer Science
Mathematics
Data Structures and Algorithms
Combinatorics
A mixed graph G is a graph that consists of both undirected and directed
edges. An orientation of G is formed by orienting all the undirected edges of
G, i.e., converting each undirected edge {u,v} into a directed edge that
is eit...
Referential communication in heterogeneous communities of pre-trained
visual deep networks
February 4, 2023
| | |
Computer Science
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
As large pre-trained image-processing neural networks are being embedded in
autonomous agents such as self-driving cars or robots, the question arises of
how such systems can communicate with each other about the surrounding world,
despite ...
Efficient Adaptive Joint Significance Test and Sobel-Type Confidence
Interval for Mediation Effect
February 4, 2023
Statistics
Methodology
Applications
Mediation analysis is an important statistical tool in many research fields.
Its aim is to investigate the mechanism along the causal pathway between an
exposure and an outcome. The joint significance test is widely utilized as a
prominent ...
Multi-Source Diffusion Models for Simultaneous Music Generation and
Separation
February 4, 2023
| | | | |
Computer Science
Electrical Engineering and Systems Science
Sound
Machine Learning
Audio and Speech Processing
In this work, we define a diffusion-based generative model capable of both
music synthesis and source separation by learning the score of the joint
probability density of sources sharing a context. Alongside the classic total
inference task...
Conformalized Semi-supervised Random Forest for Classification and
Abnormality Detection
February 4, 2023
| |
Computer Science
Machine Learning
The Random Forests classifier, a widely utilized off-the-shelf classification
tool, assumes training and test samples come from the same distribution as
other standard classifiers. However, in safety-critical scenarios like medical
diagnosi...