On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “inlier-memorization”

Memorize Early, Then Query: Inlier-Memorization-Guided Active Outlier Detectionstat.ML

A novel framework IMBoost improves outlier detection by leveraging the inlier memorization effect.

problem Challenges in unsupervised outlier detection, especially when inliers and outliers are not well-separated or form dense clusters.

method IMBoost framework that incorporates active learning to selectively acquire informative labels and explicitly reinforce the inlier memorization effect.

result IMBoost significantly outperforms state-of-the-art active outlier detection methods and requires less computational cost.

outlier detection inlier memorization active learning deep generative models unsupervised learning

2026-01-16abs ↗pdf ↗

ALTBI: Constructing Improved Outlier Detection Models via Optimization of Inlier-Memorization Effectstat.ML

ALTBI enhances outlier detection by maximizing the inlier-memorization effect.

problem Improving outlier detection models via optimization of inlier-memorization effect.

method ALTBI introduces two techniques: increasing mini-batch size and using adaptive threshold for truncated loss function.

result ALTBI achieves state-of-the-art performance in identifying outliers with lower computation costs.

outlier detection inlier-memorization mini-batch size adaptive threshold privacy-preserving

2024-08-19abs ↗pdf ↗

What Drives the Inlier-Memorization Effect? A Theory of Outlier Detection via Early Training Dynamicscs.LG

The IM effect helps detect anomalies by memorizing inliers early.

problem Challenges in fully unsupervised outlier detection.

method Theoretical study of a simple autoencoder, focusing on early training dynamics.

result Characterization of IM effect emergence, strength, and persistence.

outlier detection inlier-memorization early training autoencoder data distribution

2026-06-29abs ↗pdf ↗

ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Modelsstat.ML

ODIM detects outliers by under-fitting generative models, outperforming other methods.

problem Identifying outliers in unlabeled data without supervision.

method Develops ODIM, a method that uses under-fitted deep generative models to detect outliers.

result ODIM outperforms other methods in detecting outliers efficiently and accurately.

outlier detection unsupervised learning deep generative models likelihood under-fitting

2023-01-11abs ↗pdf ↗