Conformal prediction
PulseAugur coverage of Conformal prediction — every cluster mentioning Conformal prediction across labs, papers, and developer communities, ranked by signal.
- instance of alphaXiv 90%
- instance of uncertainty quantification 90%
- used by ScienceCast 70%
- instance of Gotit.pub 70%
- developed by Weighted Conformal Prediction 70%
- affiliated with uncertainty quantification 70%
- instance of Weighted Conformal Prediction 70%
- used by random forest 70%
- instance of ScienceCast 60%
- affiliated with Deep Ensembles 60%
- competes with Monte Carlo Dropout 60%
- used by CORE Recommender 60%
8 day(s) with sentiment data
-
Conformal Risk Control bounds prediction errors for AI models
A new paper introduces Conformal Risk Control, a method that can bound prediction errors, particularly useful for tasks like medical image analysis where precise error margins are crucial. This technique works with any …
-
Conformal prediction faces challenges with time-dependent PDEs
Researchers have identified a critical issue with conformal prediction methods when applied to time-dependent partial differential equations (PDEs). Standard conformal prediction, which offers distribution-free coverage…
-
New framework generates interpretable prediction sets for multivariate conformal prediction
Researchers have developed a new framework for multivariate conformal prediction that generates generalized hyperrectangular prediction sets. This method extends the concept of simple hyperrectangles to Cartesian produc…
-
New Conformal Prediction Framework for Distribution-to-Distribution Regression
Researchers have developed a new conformal prediction framework designed for Distribution-to-Distribution Regression, a setting increasingly relevant in various application domains. The proposed method operates in an or…
-
New CoCP method improves adaptive conformal prediction for regression
Researchers have introduced CoCP, a novel method for adaptive conformal prediction in regression tasks. This approach addresses inefficiencies caused by fixed interval centering in heteroscedastic and skewed data by par…
-
New Conformal Prediction Method Adapts to Data Shifts
Researchers have developed a new method for conformal prediction intervals designed to adapt to population shifts, particularly in applications like air-quality monitoring. This approach assumes that the measurement dis…
-
New Macro Mondrian Conformal Risk Control method targets rare objects
Researchers have introduced Macro Mondrian Conformal Risk Control (Macro Mondrian CRC), an advancement over existing Conformal Risk Control (CRC) methods. While standard CRC ensures average risk control across a dataset…
-
New framework tackles predictive inference with missing data
Researchers have developed a new framework for predictive inference that handles coarsened or missing data in training and calibration sets. The proposed methods, Robust Split Prediction (RSP) and Robust Split Conformal…
-
New 'inference-time model shift' concept challenges language model CP evaluation
A new paper introduces the concept of "inference-time model shift" to describe how changes in language model inference configurations can affect conformal prediction (CP) performance. The researchers argue that standard…
-
New research explores online conformal prediction for data streams
A new paper on arXiv details practical advantages of online conformal prediction for data streams, comparing four sequential regression procedures against a weighted full-conformal benchmark. The study evaluates empiric…
-
New loss function improves AI set-valued classifiers on imbalanced data
Researchers have developed a modified version of the odd-K-out (OKO) loss function to improve the performance of set-valued classifiers on imbalanced datasets. This adapted OKO loss function enhances sample efficiency a…
-
New Conformal Social Choice method enhances safety in multi-agent AI deliberation
Researchers have introduced Conformal Social Choice, a novel post-hoc layer designed to enhance the safety and reliability of multi-agent deliberation systems. This method addresses the issue of consensus stopping, wher…
-
Robots use conformal prediction for adaptive LLM reasoning
Researchers have developed CovNav, a novel framework for object goal navigation in robotics that utilizes conformal prediction to guide adaptive inference. This approach addresses the latency and privacy concerns of clo…
-
New SGCP framework enhances AI model reliability across subgroups
Researchers have developed Stochastic Grouping Conformal Prediction (SGCP), a new framework designed to improve the reliability of uncertainty quantification in machine learning models, particularly for sensitive applic…
-
New research advances conformal prediction methods for efficiency and accuracy
Three new research papers explore advancements in conformal prediction, a method for generating prediction sets with finite-sample guarantees. The first paper introduces CASA (Conformal Adaptive Sample Allocation) to op…
-
New Conformal Prediction Method Tackles Spatially Dependent Data
Researchers have developed a new method for conformal prediction designed to handle spatially dependent data, which is common in environmental and geographical applications. This technique, called sequential whitening, …
-
New research tackles knowledge graph embedding challenges and uncertainty
Two new arXiv papers delve into the complexities of knowledge graph embedding (KGE) and representation learning. The first paper introduces KGATE, a modular Python library designed to streamline the training and compari…
-
Conformal Prediction Theory Links Uncertainty Quantification to Information Gain
Researchers have developed a theoretical framework to connect conformal prediction, a method for quantifying uncertainty, with information theory. The study introduces generalized information measures derived from the s…
-
New conformal prediction methods for time series using deep learning
This paper introduces three novel approaches to conformal prediction for time series data, addressing the challenge of violated exchangeability assumptions inherent in time series. The proposed methods leverage deep seq…
-
New Conformal Calibration Method Boosts Efficiency in Neural Architecture Search
Researchers have developed a new method called Online Conformal Calibration (OCC) to improve the efficiency of hardware-aware neural architecture search (NAS). Traditional NAS methods are costly because they require tra…