5 papers
Finding Time Series Anomalies using Granular-ball Vector Data Description
Lifeng Shen, Liang Peng, Ruiwen Liu +2
Modeling normal behavior in dynamic, nonlinear time series data is challenging for effective anomaly detection. Traditional methods, such as nearest neighbor and clustering approac…
SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
Buyun Liang, Liangzu Peng, Jinqi Luo +3
Large Language Models (LLMs) are increasingly deployed in high-risk domains. However, state-of-the-art LLMs often exhibit hallucinations, raising serious concerns about their relia…
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…
Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares
Liangzu Peng, Wotao Yin
Block coordinate descent is a powerful algorithmic template suitable for big data optimization. This template admits a lot of variants including block gradient descent (BGD), which…