Strong Generalization

Strong generalization, the ability of machine learning models to perform well on unseen data, is a central objective in current research. Active areas of investigation include improving the robustness of self-supervised learning, understanding the optimization dynamics of transformers and other architectures (including CNNs and RNNs), and developing methods to enhance generalization through data augmentation, regularization techniques (e.g., logical regularization, consistency regularization), and improved training strategies (e.g., few-shot learning, meta-learning). These advancements are crucial for building reliable and adaptable AI systems across diverse applications, from image classification and natural language processing to healthcare and robotics.

Papers

May 19, 2023

Characterizing tradeoffs between teaching via language and demonstrations in multi-agent systems
Dhara Yu, Noah D. Goodman, Jesse Mu
Strong Generalization Human Language Multi Agent System Noisy Demonstration Neural Agent Human Communication Communication Round

May 17, 2023

Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalization
Haohui Wang, Baoyu Jing, Kaize Ding, Yada Zhu, Wei Cheng, Si Zhang, Yonghui Fan, Liqing Zhang, Dawei Zhou
LeArning Abstract Strong Generalization Graph Drawing Multi Task Learning Generalization Performance New Characterization Long Tail Tail Class

May 16, 2023

A Scalable Walsh-Hadamard Regularizer to Overcome the Low-degree Spectral Bias of Neural Networks
Ali Gorji, Andisheh Amrollahi, Andreas Krause
Neural Network Strong Generalization Gradient Descent Spectral Bias Standard Deep Functional Regularization

May 14, 2023

Towards Understanding the Generalization of Graph Neural Networks
Huayi Tang, Yong Liu
Graph Neural Network Strong Generalization Graph Structured Data Generalization Gap

May 8, 2023

Unjustified Sample Sizes and Generalizations in Explainable AI Research: Principles for More Inclusive User Studies
Uwe Peters, Mary Carman
Strong Generalization Explainable Artificial Intelligence General Principle User Study XAI Research Ethical Framework

May 4, 2023

Learning Generalizable Pivoting Skills
Xiang Zhang, Siddarth Jain, Baichuan Huang, Masayoshi Tomizuka, Diego Romeres
Reinforcement Learning Strong Generalization Robotic System Real World Object

May 1, 2023

Discover and Cure: Concept-aware Mitigation of Spurious Correlation
Shirley Wu, Mert Yuksekgonul, Linjun Zhang, James Zou
Strong Generalization Inherent Interpretability Spurious Correlation Interpretable Concept Adaptive Mitigation

April 28, 2023

Generalization for slowly mixing processes
Andreas Maurer
Strong Generalization Sample Complexity Complex Process Class Loss

April 26, 2023

April 25, 2023

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

April 22, 2023

Understanding and Improving Feature Learning for Out-of-Distribution Generalization
Yongqiang Chen, Wei Huang, Kaiwen Zhou, Yatao Bian, Bo Han, James Cheng
Strong Generalization Human Understanding Distribution Generalization Empirical Risk Minimization Feature Learning Augmented Sample

Strong Generalization

Papers

Characterizing tradeoffs between teaching via language and demonstrations in multi-agent systems

Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalization

A Scalable Walsh-Hadamard Regularizer to Overcome the Low-degree Spectral Bias of Neural Networks

Towards Understanding the Generalization of Graph Neural Networks

The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain

Generalization bounds for neural ordinary differential equations and deep residual networks

Semantic uncertainty guides the extension of conventions to new referents

Testing for Overfitting

Metric Space Magnitude and Generalisation in Neural Networks

Towards Understanding Generalization of Macro-AUC in Multi-label Learning

Unjustified Sample Sizes and Generalizations in Explainable AI Research: Principles for More Inclusive User Studies

Learning Generalizable Pivoting Skills

Discover and Cure: Concept-aware Mitigation of Spurious Correlation

Generalization for slowly mixing processes

CROP: Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing

Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories

On the Generalization of Learned Structured Representations

Learning Trajectories are Generalization Indicators

More Communication Does Not Result in Smaller Generalization Error in Federated Learning

Understanding and Improving Feature Learning for Out-of-Distribution Generalization