Learning Model

Learning models encompass a broad range of computational methods designed to extract patterns and make predictions from data, with primary objectives focused on accuracy, efficiency, and robustness. Current research emphasizes improving model scalability and transferability across diverse data types and domains, exploring architectures like graph neural networks, transformers, and mixtures-of-experts, as well as techniques such as federated learning and curriculum learning. These advancements have significant implications for various fields, including robotics, natural language processing, and healthcare, by enabling more efficient data analysis, improved decision-making, and the development of more adaptable and reliable systems.

Papers

April 28, 2023

A feature selection method based on Shapley values robust to concept shift in regression
Carlos Sebastián, Carlos E. González-Guillén
Feature Selection Novel Regression Shapley Value Learning Model Two Shift Dataset Shift Concept Shift

April 24, 2023

More Communication Does Not Result in Smaller Generalization Error in Federated Learning
Romain Chor, Milad Sefidgaran, Abdellatif Zaidi
Strong Generalization Stochastic Gradient Descent Generalization Error Learning Model

March 27, 2023

Conjunction Data Messages for Space Collision Behave as a Poisson Process
Francisco Caldas, Cláudia Soares, Cláudia Nunes, Marta Guimarães
Learning Model Collision Scenario Space Debris Poisson Process Message Flow

March 23, 2023

March 14, 2023

Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models
Alberto Testolin
Neural Network Deep Learning Timely Survey Deep Learning Model Neural Architecture Mathematical Reasoning State of the Art Deep Learning Model

March 3, 2023

EZtune: A Package for Automated Hyperparameter Tuning in R
Jill Lundell
Hyperparameter Optimization Support Vector Machine Related Hyperparameters Learning Model SPR Package

January 31, 2023

Personalized Privacy Auditing and Optimization at Test Time
Cuong Tran, Ferdinando Fioretto
Optimization Purpose Scientific Inference Test Time Learning Model Empirical Privacy accuratE Prediction Input Feature Consequential Decision Making

January 28, 2023

Learning Optimal Features via Partial Invariance
Moulik Choraria, Ibtihal Ferwana, Ankur Mani, Lav R. Varshney
Feature Selection Robust Model Learning Model Invariant Risk Minimization Invariant Model

January 24, 2023

Minimal Value-Equivalent Partial Models for Scalable and Robust Planning in Lifelong Reinforcement Learning
Safa Alver, Doina Precup
Model Based Reinforcement Learning Learning Model Lifelong Reinforcement Learning Robust Planning

December 16, 2022

Fast Learning of Dynamic Hand Gesture Recognition with Few-Shot Learning Models
Niels Schlüsener, Michael Bücker
Hand Gesture Recognition High Quality Gesture Learning Model Hand Gesture Fast Learning

December 9, 2022

December 5, 2022

Distributed Stochastic Gradient Descent with Cost-Sensitive and Strategic Agents
Abdullah Basar Akbay, Cihan Tepedelenlioglu
Stochastic Gradient Descent Reward Function Learning Model Gradient Computation Cooperative Game Theory Strategic Agent

November 23, 2022

Unsupervised Unlearning of Concept Drift with Autoencoders
André Artelt, Kleanthis Malialis, Christos Panayiotou, Marios Polycarpou, Barbara Hammer
Supervised Autoencoder Incremental Learning Concept Drift Learning Model Concept Drift Adaptation

October 13, 2022

Data augmentation on-the-fly and active learning in data stream classification
Kleanthis Malialis, Dimitris Papatheodoulou, Stylianos Filippou, Christos G. Panayiotou, Marios M. Polycarpou
Data Augmentation Active Learning Learning Model Data Stream Classification Augmented Graph

October 10, 2022

A Hybrid Active-Passive Approach to Imbalanced Nonstationary Data Stream Classification
Kleanthis Malialis, Manuel Roveri, Cesare Alippi, Christos G. Panayiotou, Marios M. Polycarpou
Incremental Learning Concept Drift Drift Detection Imbalanced Datasets Learning Model Dynamic Rebalancing

September 19, 2022

State-driven Implicit Modeling for Sparsity and Robustness in Neural Networks
Alicia Y. Tsai, Juliette Decugis, Laurent El Ghaoui, Alper Atamtürk
Neural Network Native Robustness Sparsity Increase Learning Model Implicit Model Backward Propagation Implicit Differentiation

September 4, 2022

Communication Efficient Distributed Learning over Wireless Channels
Idan Achituve, Wenbo Wang, Ethan Fetaya, Amir Leshem
LeArning Abstract Wireless Network Communication Efficiency Learning Framework Learning Model Wireless Channel Max Pooling Pooling Operator

July 12, 2022

Logistics, Graphs, and Transformers: Towards improving Travel Time Estimation
Natalia Semenova, Vadim Porvatov, Vladislav Tishin, Artyom Sosedka, Vladislav Zamkovoy
Transformer Megatron Decepticons Graph Drawing Transformer Architecture Temporal Dynamic Learning Model Logistics System Travel Time Estimation