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

June 21, 2023

Inverse Constraint Learning and Generalization by Transferable Reward Decomposition
Jaehwi Jang, Minjae Song, Daehyung Park
Strong Generalization Task Transferability Constraint Learning Policy Constraint rEward Decomposition Adaptivity Constraint

June 20, 2023

June 19, 2023

June 16, 2023

Studying Generalization on Memory-Based Methods in Continual Learning
Felipe del Rio, Julio Hurtado, Cristian Buc, Alvaro Soto, Vincenzo Lomonaco
Strong Generalization Continual LEArning Distribution Generalization Memory Replay Memory Based Better Out of Distribution Generalization

June 15, 2023

June 14, 2023

June 10, 2023

Revealing Model Biases: Assessing Deep Neural Networks via Recovered Sample Analysis
Mohammad Mahdi Mehmanchi, Mahbod Nouri, Mohammad Sabokrou
Deep Neural Network Strong Generalization Model Bias Discriminative Reply Sample Reconstruction

June 9, 2023

June 7, 2023

June 6, 2023

Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters
Zhenyu Sun, Xiaochun Niu, Ermin Wei
Strong Generalization Stochastic Gradient Descent Generalization Performance Core Stability Unobserved Heterogeneity Centralized Machine Learning

June 5, 2023

Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization
Yibing Liu, Chris Xing Tian, Haoliang Li, Lei Ma, Shiqi Wang
Strong Generalization Distribution Detection Distribution Data Neuron Activation Neuron Coverage Output Activation

Strong Generalization

Papers

Inverse Constraint Learning and Generalization by Transferable Reward Decomposition

Generalization Across Experimental Parameters in Machine Learning Analysis of High Resolution Transmission Electron Microscopy Datasets

Blackbird language matrices (BLM), a new task for rule-like generalization in neural networks: Motivations and Formal Specifications

PAC-Chernoff Bounds: Understanding Generalization in the Interpolation Regime

Shape Guided Gradient Voting for Domain Generalization

Studying Generalization on Memory-Based Methods in Continual Learning

Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection

Language Aligned Visual Representations Predict Human Behavior in Naturalistic Learning Tasks

The Universal Law of Generalization Holds for Naturalistic Stimuli

Improving Generalization in Meta-Learning via Meta-Gradient Augmentation

Revealing Model Biases: Assessing Deep Neural Networks via Recovered Sample Analysis

Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!

The Role of Diverse Replay for Generalisation in Reinforcement Learning

PeFLL: Personalized Federated Learning by Learning to Learn

On the Importance of Exploration for Generalization in Reinforcement Learning

In-Context Learning through the Bayesian Prism

Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning

On the Generalization of Multi-modal Contrastive Learning

Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters

Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization