uncertainty quantification
PulseAugur coverage of uncertainty quantification — every cluster mentioning uncertainty quantification across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
New methods advance uncertainty quantification in machine learning · 5 sources tracked
Researchers have introduced new methods for evaluating uncertainty quantification (UQ) in machine learning models. One approach, termed "decision-alignment," aims to ensure that UQ metrics meaningfully correlate with do…
-
New QUEST framework offers improved uncertainty quantification in ML
A new framework called QUEST (Quantifying Uncertainty via highest dEnSiTy regions) has been proposed for uncertainty quantification in machine learning. This approach characterizes uncertainty by the volume of the most …
-
Survey paper highlights need for uncertainty quantification in symbolic regression
A new survey paper addresses the critical gap in uncertainty quantification (UQ) for symbolic regression (SR) methods. The paper aims to introduce UQ concepts and review existing literature, categorizing current researc…
-
New method improves LLM error prediction by handling ambiguity
Researchers have developed a new method to improve error prediction in Large Language Models (LLMs) by distinguishing between input ambiguity and uncertainty quantification (UQ) signals. The study, conducted on question…
-
Last-layer linearization matches full-network UQ performance
A new research paper explores the effectiveness of using only the last layer of a deep neural network for uncertainty quantification. The study found that this simplified approach, known as last-layer linearization, pro…
-
New Bayesian Knowledge Distillation Framework Enhances Model Compression
Researchers have introduced Multi-Teacher Bayesian Knowledge Distillation (MT-BKD), a novel framework designed to improve model compression and uncertainty quantification. This method allows a student model to learn fro…
-
Bayesian deep learning advances with new sampling and inference methods
Two new research papers propose advancements in Bayesian deep learning, focusing on improving inference methods for neural networks. The first paper argues that sampling-based inference (SAI) has reached computational p…
-
Deep ensembles fail to capture uncertainty in graph neural networks
A new research paper questions the effectiveness of deep ensembles for uncertainty quantification in graph neural networks. The study found that ensembles offer minimal improvement over single models, with gains primari…
-
Paper: LLM uncertainty quantification is flawed unsupervised clustering
A new paper argues that current methods for quantifying uncertainty in large language models (LLMs) are fundamentally flawed, likening them to unsupervised clustering algorithms. These methods primarily measure internal…
-
New framework generates context-aware Gaussian overbounds for AI uncertainty
Researchers have developed a novel learning framework to generate context-aware Gaussian overbounds for uncertainty quantification. This method trains neural networks to produce mean and scale estimates that offer prova…
-
Geometric Autoencoders Enhance Bayesian Inversion for Engineering Inference
Researchers have developed Geometric Autoencoders for Bayesian Inversion (GABI), a novel framework designed to improve uncertainty quantification in engineering inference tasks. GABI learns geometry-aware generative mod…
-
AI system enhances semiconductor quality control with efficient retraining
Researchers have developed a robust AI system for predictive quality control in semiconductor manufacturing, utilizing MLOps and uncertainty quantification. Their study, based on five years of manufacturing data, found …
-
LLM research tackles uncertainty in function calls and system propagation
Two new research papers explore the critical issue of uncertainty in Large Language Models (LLMs). The first paper investigates uncertainty quantification methods specifically for LLM function-calling, finding that simp…