Model Class

Model classes, encompassing various architectures and algorithms used in machine learning, are a central focus of current research, aiming to improve efficiency, interpretability, and performance. Active areas include developing faster training methods for specific model classes like tree ensembles and ReLU networks, exploring meta-models that learn from classes of systems rather than individual instances, and investigating the limitations of existing interpretability techniques. These advancements have significant implications for diverse applications, ranging from improving the robustness of AI systems to enhancing the understanding and trustworthiness of machine learning models.

Papers

November 5, 2024

Deep learning-based modularized loading protocol for parameter estimation of Bouc-Wen class models
Sebin Oh, Junho Song, Taeyong Kim
Estimation Task Many Parameter Hysteresis Compensation Dynamic Loading Model Class

October 28, 2024

Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings
Milad Khademi Nori, Il-Min Kim
LeArning Abstract Catastrophic Forgetting Class Incremental Learning Generative Question Generative Replay Discriminative Reply Generative Classifier Task Ambiguity Model Class

February 13, 2024

Faster Repeated Evasion Attacks in Tree Ensembles
Lorenzo Cascioli, Laurens Devos, Ondřej Kuželka, Jesse Davis
Adversarial Example Related Problem Tree Ensemble Evasion Attack Model Class

August 25, 2023

From system models to class models: An in-context learning paradigm
Marco Forgione, Filippo Pura, Dario Piga
Context Learning Dynamical System Encoder Decoder System Identification Meta Model Model Class

May 9, 2023

Multilevel Sentence Embeddings for Personality Prediction
Paolo Tirotta, Akira Yuasa, Masashi Morita
Multi Class Classification Personality Prediction Japanese Sentence Group Structure Model Class

December 22, 2022

Impossibility Theorems for Feature Attribution
Blair Bilodeau, Natasha Jaques, Pang Wei Koh, Been Kim
Feature Attribution Interpretability Method Feature Attribution Method Plausible Explanation Model Class Impossibility Theorem

March 12, 2022

Categories of Differentiable Polynomial Circuits for Machine Learning
Paul Wilson, Fabio Zanasi
Machine Learning Machine Learning Model Category Shift Categorical Structure Polynomial Complexity Model Class

February 16, 2022

Diagnosing Batch Normalization in Class Incremental Learning
Minghao Zhou, Quanziang Wang, Jun Shu, Qian Zhao, Deyu Meng
Deep Neural Network Incremental Learning Class Incremental Learning Batch Normalization Model Class

February 2, 2022

Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions
Aaron Mishkin, Arda Sahiner, Mert Pilanci
Convex Optimization ReLU Layer Proximal Gradient ReLU Activation Two Layer ReLU Convex Problem ReLU Regression Model Class Cone Detection