4 papers
Recovery Guarantees for Continual Learning of Dependent Tasks: Memory, Data-Dependent Regularization, and Data-Dependent Weights
Liangzu Peng, Uday Kiran Reddy Tadipatri, Ziqing Xu +2
Continual learning (CL) is concerned with learning multiple tasks sequentially without forgetting previously learned tasks. Despite substantial empirical advances over recent years…
Mathematics of Continual Learning
Liangzu Peng, René Vidal
Continual learning is an emerging subject in machine learning that aims to solve multiple tasks presented sequentially to the learner without forgetting previously learned tasks. R…
LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learning
Liangzu Peng, Juan Elenter, Joshua Agterberg +2
The goal of continual learning (CL) is to train a model that can solve multiple tasks presented sequentially. Recent CL approaches have achieved strong performance by leveraging la…
Scalable 3D Registration via Truncated Entry-wise Absolute Residuals
Tianyu Huang, Liangzu Peng, René Vidal +1
Given an input set of D point pairs, the goal of outlier-robust D registration is to compute some rotation and translation that align as many point pairs as possible. This is…