4 papers
Spectral-Aware Analytic Class-Incremental Learning for Long-Tailed Distributions
Quyen Tran, Hai Nguyen, Quan Dao +4
Analytic Continual Learning (ACL) offers a computationally efficient alternative to gradient-based approaches. Recent ACL methods are based on Recursive Least Squares (RLS) and hav…
Finite-horizon quantile martingale posteriors: raw-urn laws and matrix-gain regression
Nam Anh Le
Martingale posteriors quantify uncertainty by forward-imputing observations from one-step-ahead predictive distributions, but implementations stop after finitely many imputations.…
When can a posterior predictive check identify the learning rate? Exact degeneracy in Gaussian models and implications for Generalised Bayesian Inerence
Nam Anh Le
Generalised Bayesian inference tempers the likelihood by a learning rate to mitigate model misspecification, and the choice of is consequential. Zafar and Nicholls (2024)…
TED++: Submanifold-Aware Backdoor Detection via Layerwise Tubular-Neighbourhood Screening
Nam Le, Leo Yu Zhang, Kewen Liao +2
As deep neural networks power increasingly critical applications, stealthy backdoor attacks, where poisoned training inputs trigger malicious model behaviour while appearing benign…