Vocabulary for Universal Approximation: A Linguistic Perspective of
Mapping Compositions
May 20, 2023
Computer Science
Mathematics
Machine Learning
Numerical Analysis
Dynamical Systems
Numerical Analysis
In recent years, deep learning-based sequence modelings, such as language
models, have received much attention and success, which pushes researchers to
explore the possibility of transforming non-sequential problems into a
sequential form. ...
MGL2Rank: Learning to Rank the Importance of Nodes in Road Networks
Based on Multi-Graph Fusion
May 20, 2023
|
Computer Science
Machine Learning
Artificial Intelligence
Social and Information Networks
The identification of important nodes with strong propagation capabilities in
road networks is a vital topic in urban planning. Existing methods for
evaluating the importance of nodes in traffic networks only consider
topological informatio...
How Spurious Features Are Memorized: Precise Analysis for Random and NTK
Features
May 20, 2023
|
Statistics
Computer Science
Machine Learning
Machine Learning
Deep learning models are known to overfit and memorize spurious features in
the training dataset. While numerous empirical studies have aimed at
understanding this phenomenon, a rigorous theoretical framework to quantify it
is still missing...
Human-annotated label noise and their impact on ConvNets for remote
sensing image scene classification
May 20, 2023
| | | | | | |
Computer Science
Computer Vision and Pattern Recognition
Artificial Intelligence
Convolutional neural networks (ConvNets) have been successfully applied to
satellite image scene classification. Human-labeled training datasets are
essential for ConvNets to perform accurate classification. Errors in
human-annotated traini...
Quantum simulation of lattice gauge theories via deterministic duality
transformations assisted by measurements
May 20, 2023
|
Physics
Quantum Physics
Strongly Correlated Electrons
High Energy Physics - Lattice
High Energy Physics - Theory
Quantum simulation is one of the major applications of quantum devices. In
the noisy intermediate-scale quantum era, however, the general quantum
simulation is not yet feasible, such as that of lattice gauge theories, which
is likely limite...
Post-Quantum Hybrid Digital Signatures with Hardware-Support for Digital
Twins
May 20, 2023
|
Computer Science
Cryptography and Security
Digital Twins (DT) virtually model cyber-physical objects using Internet of
Things (IoT) components (e.g., sensors) to gather and process senstive
information stored in the cloud. Trustworthiness of the streamed data is
crucial which requir...
Can Public Large Language Models Help Private Cross-device Federated
Learning?
May 20, 2023
| | | | | | |
Computer Science
Machine Learning
We study (differentially) private federated learning (FL) of language models.
The language models in cross-device FL are relatively small, which can be
trained with meaningful formal user-level differential privacy (DP) guarantees
when mass...
Annealing Self-Distillation Rectification Improves Adversarial Training
May 20, 2023
| |
Computer Science
Machine Learning
Artificial Intelligence
In standard adversarial training, models are optimized to fit one-hot labels
within allowable adversarial perturbation budgets. However, the ignorance of
underlying distribution shifts brought by perturbations causes the problem of
robust o...
EE-TTS: Emphatic Expressive TTS with Linguistic Information
May 20, 2023
| | | | | |
Computer Science
Electrical Engineering and Systems Science
Sound
Computation and Language
Audio and Speech Processing
While Current TTS systems perform well in synthesizing high-quality speech,
producing highly expressive speech remains a challenge. Emphasis, as a critical
factor in determining the expressiveness of speech, has attracted more
attention now...
CryptoVampire: Automated Reasoning for the Complete Symbolic Attacker
Cryptographic Model
May 20, 2023
| | |
Computer Science
Cryptography and Security
Logic in Computer Science
Cryptographic protocols are hard to design and prove correct, as witnessed by
the ever-growing list of attacks even on protocol standards. Symbolic models of
cryptography enable automated formal security proofs of such protocols against
an ...