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 4, 2024

A Survey Analyzing Generalization in Deep Reinforcement Learning
Ezgi Korkmaz
Timely Survey Deep Reinforcement Learning Strong Generalization Reinforcement Learning Research Robust Deep Reinforcement Learning

December 30, 2023

Symbolic Cognitive Diagnosis via Hybrid Optimization for Intelligent Education Systems
Junhao Shen, Hong Qian, Wei Zhang, Aimin Zhou
Strong Generalization Hybrid Optimization Intelligent Education Cognitive Diagnosis

December 28, 2023

Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space
Padmaksha Roy, Tyler Cody, Himanshu Singhal, Kevin Choi, Ming Jin
Strong Generalization Latent Space Multi Task Learning Intrusion Detection Domain Invariant Representation Domain Generalization Method

December 27, 2023

Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization
Sebastian Dziadzio, Çağatay Yıldız, Gido M. van de Ven, Tomasz Trzciński, Tinne Tuytelaars, Matthias Bethge
Strong Generalization Continual LEArning Catastrophic Forgetting Continual Learning Continual Text Classification Disentangled Learning Memory Editing

December 26, 2023

Generalization in Kernel Regression Under Realistic Assumptions
Daniel Barzilai, Ohad Shamir
Strong Generalization Modeling Assumption Kernel Regression Benign Overfitting Parameterized Model Kernel Regime

December 25, 2023

Mixture Data for Training Cannot Ensure Out-of-distribution Generalization
Songming Zhang, Yuxiao Luo, Qizhou Wang, Haoang Chi, Xiaofeng Chen, Bo Han, Jinyan Li
Strong Generalization Training Data Distribution Generalization Generalization Error Generalization Problem Data Mixture

December 23, 2023

December 21, 2023

Meta Transfer of Self-Supervised Knowledge: Foundation Model in Action for Post-Traumatic Epilepsy Prediction
Wenhui Cui, Haleh Akrami, Ganning Zhao, Anand A. Joshi, Richard M. Leahy
Self Supervised Learning Strong Generalization Foundation Model Functional Magnetic Resonance Imaging Action Feature Seizure Prediction Meta Transfer Traumatic Brain

December 20, 2023

SEER-ZSL: Semantic Encoder-Enhanced Representations for Generalized Zero-Shot Learning
William Heyden, Habib Ullah, M. Salman Siddiqui, Fadi Al Machot
Strong Generalization Representation Learning Semantic Description Generalization Gap Unseen Class Generalized Zero Shot Learning Semantic Class

December 19, 2023

Optimizing Neural Networks with Gradient Lexicase Selection
Li Ding, Lee Spector
Neural Network Strong Generalization Generalization Performance Lexicase Selection

December 14, 2023

Less is more -- the Dispatcher/ Executor principle for multi-task Reinforcement Learning
Martin Riedmiller, Tim Hertweck, Roland Hafner
Strong Generalization Generalization Property Design Principle Multi Task Reinforcement Learning Near Optimal Executor

December 12, 2023

December 10, 2023

The Generalization Gap in Offline Reinforcement Learning
Ishita Mediratta, Qingfei You, Minqi Jiang, Roberta Raileanu
Strong Generalization Offline Reinforcement Learning Online Reinforcement Learning Generalization Gap Offline Learning

December 8, 2023

LLM Interactive Optimization of Open Source Python Libraries -- Case Studies and Generalization
Andreas Florath
Large Language Model Strong Generalization Case Study LLM Based Source Code Code Optimization Open Source Python

December 7, 2023

Rapid Motor Adaptation for Robotic Manipulator Arms
Yichao Liang, Kevin Ellis, João Henriques
Strong Generalization Generalization Performance Manipulation Skill Motor Adaptation

December 6, 2023

Interpretability Illusions in the Generalization of Simplified Models
Dan Friedman, Andrew Lampinen, Lucas Dixon, Danqi Chen, Asma Ghandeharioun
Strong Generalization Transformer Model Generalization Gap Systematic Generalization Proxy Dataset Simple Model Interpretability Illusion

Strong Generalization

Papers

A Survey Analyzing Generalization in Deep Reinforcement Learning

Symbolic Cognitive Diagnosis via Hybrid Optimization for Intelligent Education Systems

Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space

Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization

Generalization in Kernel Regression Under Realistic Assumptions

Mixture Data for Training Cannot Ensure Out-of-distribution Generalization

MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning

Towards Generalization in Subitizing with Neuro-Symbolic Loss using Holographic Reduced Representations

A Theory of Non-Acyclic Generative Flow Networks

Meta Transfer of Self-Supervised Knowledge: Foundation Model in Action for Post-Traumatic Epilepsy Prediction

SEER-ZSL: Semantic Encoder-Enhanced Representations for Generalized Zero-Shot Learning

Optimizing Neural Networks with Gradient Lexicase Selection

Less is more -- the Dispatcher/ Executor principle for multi-task Reinforcement Learning

BIRB: A Generalization Benchmark for Information Retrieval in Bioacoustics

How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation

GenDet: Towards Good Generalizations for AI-Generated Image Detection

The Generalization Gap in Offline Reinforcement Learning

LLM Interactive Optimization of Open Source Python Libraries -- Case Studies and Generalization

Rapid Motor Adaptation for Robotic Manipulator Arms

Interpretability Illusions in the Generalization of Simplified Models