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

January 28, 2024

January 26, 2024

Understanding Domain Generalization: A Noise Robustness Perspective
Rui Qiao, Bryan Kian Hsiang Low
Strong Generalization Domain Generalization Label Noise Noise Robustness Label Noise Robustness

January 24, 2024

How to Collaborate: Towards Maximizing the Generalization Performance in Cross-Silo Federated Learning
Yuchang Sun, Marios Kountouris, Jun Zhang
Strong Generalization Generalization Performance Non Convex Loss Function Cross Silo Federated Learning Collaborative Training

January 23, 2024

Generalization of Heterogeneous Multi-Robot Policies via Awareness and Communication of Capabilities
Pierce Howell, Max Rudolph, Reza Torbati, Kevin Fu, Harish Ravichandar
Strong Generalization Multi Agent Reinforcement Learning Multi Robot Multi Robot System Timely Communication Capability Evolution Social Awareness Heterogeneous Robot Team Unknown Teammate

January 22, 2024

January 20, 2024

Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View
Raj Ghugare, Matthieu Geist, Glen Berseth, Benjamin Eysenbach
Reinforcement Learning Strong Generalization Supervised Learning Best View TD Learning Combinatorial Generalization

January 19, 2024

January 17, 2024

DaFoEs: Mixing Datasets towards the generalization of vision-state deep-learning Force Estimation in Minimally Invasive Robotic Surgery
Mikel De Iturrate Reyzabal, Mingcong Chen, Wei Huang, Sebastien Ourselin, Hongbin Liu
Data Set Strong Generalization Force Estimation Minimally Invasive Tactile Dataset Force Perception

January 16, 2024

January 15, 2024

Concept-Guided Prompt Learning for Generalization in Vision-Language Models
Yi Zhang, Ce Zhang, Ke Yu, Yushun Tang, Zhihai He
Vision Language Model Strong Generalization Prompt Learning Contrastive Language Image Task Generalization

January 12, 2024

Microphone Conversion: Mitigating Device Variability in Sound Event Classification
Myeonghoon Ryu, Hongseok Oh, Suji Lee, Han Park
Strong Generalization Training Data Voice Conversion Event Classification Input Spectrogram Device Variation Recording Device

January 9, 2024

January 8, 2024

Convex SGD: Generalization Without Early Stopping
Julien Hendrickx, Alex Olshevsky
Strong Generalization Gradient Descent Generalization Error Stochastic Way Early Stopping Strong Convexity Smooth Convex

January 5, 2024

Class-wise Generalization Error: an Information-Theoretic Analysis
Firas Laakom, Yuheng Bu, Moncef Gabbouj
Strong Generalization Generalization Performance Generalization Bound Generalization Error

Strong Generalization

Papers

Generalisations of Euler's Tonnetz on triangulated surfaces

Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization

Understanding Domain Generalization: A Noise Robustness Perspective

How to Collaborate: Towards Maximizing the Generalization Performance in Cross-Silo Federated Learning

Generalization of Heterogeneous Multi-Robot Policies via Awareness and Communication of Capabilities

The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimization

Generalization and Informativeness of Conformal Prediction

Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View

Neglected Hessian component explains mysteries in Sharpness regularization

Stochastic Dynamic Power Dispatch with High Generalization and Few-Shot Adaption via Contextual Meta Graph Reinforcement Learning

DaFoEs: Mixing Datasets towards the generalization of vision-state deep-learning Force Estimation in Minimally Invasive Robotic Surgery

The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images

lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning

Enhancing Evolving Domain Generalization through Dynamic Latent Representations

Concept-Guided Prompt Learning for Generalization in Vision-Language Models

Microphone Conversion: Mitigating Device Variability in Sound Event Classification

A novel framework for generalization of deep hidden physics models

Setting the Record Straight on Transformer Oversmoothing

Convex SGD: Generalization Without Early Stopping

Class-wise Generalization Error: an Information-Theoretic Analysis