Unsupervised Learning

AI automates mathematical constant formula discovery by analyzing convergence dynamics, revealing known and novel formulas for π, ln(2), and other constants.

ImAD: An end-to-end unsupervised anomaly detection method conquering missing data’s challenge by integrating imputation and detection in a unified framework, achieving superior accuracy!

PCA tree: a novel hierarchical dimensionality reduction model visualized using oblique trees and local PCAs, offering speed and interpretability.

Star geometry reveals optimal data-driven regularizers!

Neuromap leverages graph neural networks to optimize the map equation for community detection, achieving competitive performance and automatically determining the optimal number of clusters.

CANDY refines contrastive multi-view clustering by cleverly using inter-view similarities to identify and correct false negatives and a spectral method to remove false positives, resulting in signific…

NewImp boosts diffusion models’ missing data imputation by curbing sample diversity and eliminating data masking, achieving superior accuracy.

Unsupervised learning predicts protein-nucleic acid binding using contact map prediction, significantly improving aptamer screening via FAFormer, a novel equivariant transformer.

Single diffusion model achieves competitive out-of-distribution detection across diverse tasks by analyzing diffusion path characteristics.

Oja’s algorithm achieves minimax optimal error rates for streaming sparse PCA using a simple single-pass thresholding method, requiring only O(d) space and O(nd) time.

Neural receptive fields’ localization emerges from nonlinear learning dynamics driven by naturalistic data’s higher-order statistics, not just sparsity.

Contrastive Divergence algorithms achieve near-optimal parameter estimation rates, matching the Cramér-Rao lower bound under specific conditions, as proven by a novel non-asymptotic analysis.

Multidimensional Fractional Programming (MFP) efficiently solves the challenging Normalized Cut (NCut) problem for multi-class clustering, outperforming existing methods.

Learn optimal data-dependent distribution kernels via Maximum Kernel Entropy, eliminating manual kernel selection and boosting performance on various downstream tasks.

This research introduces an Expectation-Maximization algorithm to train diffusion models from incomplete and noisy data, enabling their use in data-scarce scientific applications.

LaSCal, a novel label-free calibration method, ensures reliable model predictions under label shift by using a consistent calibration error estimator, achieving effective and robust unsupervised calib…

Interactive Deep Clustering (IDC) significantly boosts deep clustering performance by strategically incorporating minimal user interaction to resolve ambiguous sample classifications.

New gradient flow geometry improves MMD-based sampling by teleporting particle mass, guaranteeing global exponential convergence, and yielding superior empirical results.

Fair Kernel K-Means (FKKM) framework ensures fair data partitioning by integrating a novel fairness regularization term into the kernel k-means algorithm, extending this to multiple kernel settings fo…

Expected Probabilistic Hierarchies (EPH) offers a novel, scalable approach to hierarchical clustering by optimizing expected scores under a probabilistic model, outperforming existing methods on vario…