Lazy Learning

Lazy learning is a machine learning paradigm focusing on updating model parameters only when necessary, unlike traditional methods that update on every data point. Current research explores lazy learning's application across diverse areas, including online learning with privacy constraints, neural network training inspired by biological learning mechanisms, and large language model analysis to understand shortcut learning. This approach offers significant advantages in terms of computational efficiency, reduced energy consumption, and improved performance in specific contexts, particularly with large datasets or resource-limited environments.

Papers

June 5, 2024

Private Online Learning via Lazy Algorithms
Hilal Asi, Tomer Koren, Daogao Liu, Kunal Talwar
Online Convex Optimization Private Algorithm Private Learning Lazy Search Online Prediction Lazy Learning

October 12, 2023

How connectivity structure shapes rich and lazy learning in neural circuits
Yuhan Helena Liu, Aristide Baratin, Jonathan Cornford, Stefan Mihalas, Eric Shea-Brown, Guillaume Lajoie
Sparse Connectivity Neural Circuit Connectivity Pattern Rank Initialization Lazy Learning

May 26, 2023

Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning
Ruixiang Tang, Dehan Kong, Longtao Huang, Hui Xue
Large Language Model Context Learning Shortcut Pattern Avoidance Loss Extraction Task Lazy Learning

March 26, 2023

Lazy learning: a biologically-inspired plasticity rule for fast and energy efficient synaptic plasticity
Aaron Pache, Mark CW van Rossum
Back Propagation Energy Policy Research Synaptic Plasticity Human Learning MNIST Canadian Institute for Advanced Lazy Learning

March 21, 2022

Classifications of Skull Fractures using CT Scan Images via CNN with Lazy Learning Approach
Md Moniruzzaman Emon, Tareque Rahman Ornob, Moqsadur Rahman
Convolutional Neural Network Classification Code CT Image CNN Network Lazy Learning Skull Fracture

March 7, 2022

Fast and Data Efficient Reinforcement Learning from Pixels via Non-Parametric Value Approximation
Alexander Long, Alan Blair, Herke van Hoof
Reinforcement Learning Algorithm Value Function Tetromino Pixel Data Efficient Episodic Reinforcement Learning Polygonal Environment Lazy Learning

Lazy Learning

Papers

Private Online Learning via Lazy Algorithms

How connectivity structure shapes rich and lazy learning in neural circuits

Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning

Lazy learning: a biologically-inspired plasticity rule for fast and energy efficient synaptic plasticity

Classifications of Skull Fractures using CT Scan Images via CNN with Lazy Learning Approach

Fast and Data Efficient Reinforcement Learning from Pixels via Non-Parametric Value Approximation