Uncertainty Quantification

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

5 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 832 papers with code (2,366 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
  6 Jun 2015 29 repositories listed Syntology ran 4 of 4 samples · 0 unverified · 4 pointer-only (licence)
  In comparison, Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with a prohibitive computational cost.
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
  5 Dec 2016 26 repositories listed Syntology ran 9 of 11 samples · 2 unverified · 6 pointer-only (licence)
  Deep neural networks (NNs) are powerful black box predictors that have recently achieved impressive performance on a wide spectrum of tasks.
• Evidential Deep Learning to Quantify Classification Uncertainty
  5 Jun 2018 10 repositories listed Syntology ran 4 of 5 samples · 1 unverified
  Deterministic neural nets have been shown to learn effective predictors on a wide range of machine learning problems.
• A Simple Baseline for Bayesian Uncertainty in Deep Learning
  7 Feb 2019 8 repositories listed Syntology ran 6 of 17 samples · 11 unverified
  We propose SWA-Gaussian (SWAG), a simple, scalable, and general purpose approach for uncertainty representation and calibration in deep learning.
• Laplace Redux -- Effortless Bayesian Deep Learning
  28 Jun 2021 6 repositories listed Syntology ran 1 of 5 samples · 4 unverified · 1 pointer-only (licence)
  Bayesian formulations of deep learning have been shown to have compelling theoretical properties and offer practical functional benefits, such as improved predictive uncertainty quantification and model selection.
• Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules
  28 Nov 2020 6 repositories listed Syntology ran 5 of 9 samples · 4 unverified · 9 pointer-only (licence)
  Many important tasks in chemistry revolve around molecules during reactions.
• Deep Evidential Regression
  7 Oct 2019 6 repositories listed Syntology ran 4 of 6 samples · 2 unverified · 3 pointer-only (licence)
  We demonstrate learning well-calibrated measures of uncertainty on various benchmarks, scaling to complex computer vision tasks, as well as robustness to adversarial and OOD test samples.
• Uncertainty Sets for Image Classifiers using Conformal Prediction
  29 Sep 2020 5 repositories listed Syntology ran 19 of 63 samples · 44 unverified · 19 pointer-only (licence)
  Convolutional image classifiers can achieve high predictive accuracy, but quantifying their uncertainty remains an unresolved challenge, hindering their deployment in consequential settings.
• BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning
  17 Feb 2020 5 repositories listed Syntology ran 1 of 3 samples · 2 unverified · 3 pointer-only (licence)
  We also apply BatchEnsemble to lifelong learning, where on Split-CIFAR-100, BatchEnsemble yields comparable performance to progressive neural networks while having a much lower computational and memory costs.
• A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
  15 Jul 2021 4 repositories listed Syntology ran 0 of 12 samples · 12 unverified
  Conformal prediction is a user-friendly paradigm for creating statistically rigorous uncertainty sets/intervals for the predictions of such models.
• Deep Deterministic Uncertainty: A Simple Baseline
  23 Feb 2021 4 repositories listed
  Reliable uncertainty from deterministic single-forward pass models is sought after because conventional methods of uncertainty quantification are computationally expensive.
• COMBO: Conservative Offline Model-Based Policy Optimization
  16 Feb 2021 4 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  We overcome this limitation by developing a new model-based offline RL algorithm, COMBO, that regularizes the value function on out-of-support state-action tuples generated via rollouts under the learned model.
• Masksembles for Uncertainty Estimation
  15 Dec 2020 4 repositories listed
  Our central intuition is that there is a continuous spectrum of ensemble-like models of which MC-Dropout and Deep Ensembles are extreme examples.
• Rule-based Bayesian regression
  2 Aug 2020 4 repositories listed
  We introduce a novel rule-based approach for handling regression problems.
• Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness
  17 Jun 2020 4 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  Bayesian neural networks (BNN) and deep ensembles are principled approaches to estimate the predictive uncertainty of a deep learning model.
• Unsupervised Quality Estimation for Neural Machine Translation
  21 May 2020 4 repositories listed
  Quality Estimation (QE) is an important component in making Machine Translation (MT) useful in real-world applications, as it is aimed to inform the user on the quality of the MT output at test time.
• Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph
  21 Jun 2024 3 repositories listed Syntology ran 2 of 4 samples · 2 unverified
  Using our benchmark, we conduct a large-scale empirical investigation of UQ and normalization techniques across eleven tasks, identifying the most effective approaches.
• Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models
  3 Jul 2023 3 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  Large Language Models (LLMs) show promising results in language generation and instruction following but frequently "hallucinate", making their outputs less reliable.
• MAPIE: an open-source library for distribution-free uncertainty quantification
  25 Jul 2022 3 repositories listed Syntology ran 1 of 16 samples · 15 unverified
  Estimating uncertainties associated with the predictions of Machine Learning (ML) models is of crucial importance to assess their robustness and predictive power.
• Simple Techniques Work Surprisingly Well for Neural Network Test Prioritization and Active Learning (Replicability Study)
  2 May 2022 3 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  Test Input Prioritizers (TIP) for Deep Neural Networks (DNN) are an important technique to handle the typically very large test datasets efficiently, saving computation and labeling costs.
• MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks
  2 Mar 2022 3 repositories listed
  However, disentangling the different types and sources of uncertainty is non trivial for most datasets, especially since there is no ground truth for uncertainty.
• Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
  15 Jul 2021 3 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  However, many tasks of practical interest have different modalities, such as tabular data, audio, text, or sensor data, which offer significant challenges involving regression and discrete or continuous structured…
• Learning by example: fast reliability-aware seismic imaging with normalizing flows
  13 Apr 2021 3 repositories listed
  To arrive at this result, we train the NF on pairs of low- and high-fidelity migrated images.
• Distribution-Free, Risk-Controlling Prediction Sets
  7 Jan 2021 3 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  While improving prediction accuracy has been the focus of machine learning in recent years, this alone does not suffice for reliable decision-making.
• Hyperparameter Ensembles for Robustness and Uncertainty Quantification
  24 Jun 2020 3 repositories listed Syntology ran 2 of 4 samples · 2 unverified
  Ensembles over neural network weights trained from different random initialization, known as deep ensembles, achieve state-of-the-art accuracy and calibration.
• Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification
  17 Jan 2020 3 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  In this work, firstly, we develop the theory and methodology of IB-INNs, a class of conditional normalizing flows where INNs are trained using the IB objective: Introducing a small amount of {\em controlled} information…
• Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels
  11 Oct 2019 3 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  Recently, different machine learning methods have been introduced to tackle the challenging few-shot learning scenario that is, learning from a small labeled dataset related to a specific task.
• Deep learning observables in computational fluid dynamics
  7 Mar 2019 3 repositories listed
  Under the assumption that the underlying neural networks generalize well, we prove that the deep learning MC and QMC algorithms are guaranteed to be faster than the baseline (quasi-) Monte Carlo methods.
• Deep Uncertainty Quantification: A Machine Learning Approach for Weather Forecasting
  22 Dec 2018 3 repositories listed
  We cast the weather forecasting problem as an end-to-end deep learning problem and solve it by proposing a novel negative log-likelihood error (NLE) loss function.
• C-Adapter: Adapting Deep Classifiers for Efficient Conformal Prediction Sets
  12 Oct 2024 2 repositories listed
  Conformal prediction, as an emerging uncertainty quantification technique, typically functions as post-hoc processing for the outputs of trained classifiers.

Syntology lines on 21 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.