Research
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

18365472 · Jun 202019922001200920172026
48 results for overconfidence mitigation

Bayesian ReLU nets fix asymptotic overconfidence with infinite features.

problem Bayesian ReLU nets can be asymptotically overconfident far from training data.
method Extend finite ReLU BNNs with infinite ReLU features via a Gaussian process.
result The resulting model is asymptotically maximally uncertain far from the data.

The thesis tackles overconfident approximations in simulation-based inference.

problem Overconfident conclusions from machine learning approximations in statistical analyses.
method Introduces balancing and Bayesian neural networks to reduce overconfidence.
result Balancing and Bayesian neural networks lead to less overconfident approximations.

Combines Laplace approximations of deep networks for better uncertainty quantification.

problem Overconfident predictions on outliers in deep learning models.
method Gaussian mixture model posterior using weighted sum of Laplace approximations of pre-trained deep networks.
result Mitigates overconfidence 'far away' from training data.

Assessing the predictive accuracy of black box classifiers is challenging in the absence of labeled test datasets. In these scenarios we may need to rely on a human oracle to evaluate individual predictions; presenting the challenge to create query algorithms to guide the search for points that provide the most informa…

2018-10-12abs ↗pdf ↗

Paper proposes a method to improve deep neural networks' confidence estimates.

problem Overconfident predictions limit practical use of deep neural networks in safety-critical applications.
method Proposes a novel loss function, Correctness Ranking Loss, to regularize class probabilities.
result The method produces well-ranked confidence estimates and is effective for out-of-distribution detection and active learning.

A novel post-hoc calibration method reduces neural network calibration errors.

problem Neural networks produce poorly calibrated probabilities, leading to underconfidence and overconfidence.
method Probability bounding (PB) via box-constrained softmax (BCSoftmax) function.
result Consistently reduces calibration errors on four real-world datasets.

New method improves OOD detection by integrating diffusion models into discriminator models.

problem Overconfidence in discriminator models leads to poor OOD detection.
method Integrates diffusion models into discriminator and generation models to mitigate overconfidence.
result Demonstrates significant improvement in AUROC scores for challenging datasets.

ePF improves PF for ITS by balancing exploration and exploitation, outperforming baselines.

problem Premature exploitation in PF leads to suboptimal solutions under constrained budgets.
method Integrates Entropic Annealing and Look-ahead Modulation to preserve diversity and evaluate potential.
result Significant improvement in task reward (up to 50% relative) on math benchmarks.

Regularized mixtures improve inflation and interest rate forecasts, especially correcting overconfidence.

problem Improving density forecasts of Eurozone inflation and real interest rates.
method Construct regularized mixtures of density forecasts with various objectives and penalties.
result Regularized mixtures outperform individual forecasters, especially correcting overconfidence.

This work extends balancing to various simulation-based inference algorithms for more conservative posterior approximations.

problem Overconfident posterior approximations in simulation-based inference.
method Introduces a balanced version of neural posterior estimation and contrastive neural ratio estimation.
result Balanced versions tend to produce conservative posterior approximations on various benchmarks.

Simulation-based inference methods can produce unreliable posterior approximations.

problem Reliability of simulation-based inference methods for scientific use cases.
method Benchmarked algorithms including Neural Posterior Estimation, Neural Ratio Estimation, Sequential Neural Likelihood, and Approximate Bayesian Computation.
result Ensembling posterior surrogates provides more reliable approximations.

DRO-NPE improves neural posterior estimation by reducing overconfidence and overfitting.

problem Overconfident and unreliable posteriors in simulation-based inference with limited simulation budgets.
method Distributionally robust approach using Wasserstein ambiguity set and KL-based metrics.
result Consistently improves coverage and calibration across benchmark tasks.

We describe a limitation in the expressiveness of the predictive uncertainty estimate given by mean-field variational inference (MFVI), a popular approximate inference method for Bayesian neural networks. In particular, MFVI fails to give calibrated uncertainty estimates in between separated regions of observations. Th…

2019-06-27abs ↗pdf ↗

Regularization is an effective way to promote the generalization performance of machine learning models. In this paper, we focus on label smoothing, a form of output distribution regularization that prevents overfitting of a neural network by softening the ground-truth labels in the training data in an attempt to penal…

2020-01-07abs ↗pdf ↗

FreB protocol uses AI to infer hidden parameters with valid confidence regions.

problem Generating biased or overconfident conclusions from AI-generated posterior distributions.
method Frequentist-Bayes (FreB) protocol reshapes AI-generated posterior distributions into valid confidence regions.
result FreB provides valid confidence regions that consistently include true parameters with expected probability.

This work improves neural network trustworthiness through uncertainty estimation.

problem Overconfident neural networks lead to poor performance under distribution shifts.
method Develops a general uncertainty framework for neural networks, including classification with rejection.
result Improves model trustworthiness and robustness in decision-making tasks.

New method uses neural networks to efficiently approximate Bayesian inference for complex models.

problem Efficiently approximating Bayesian inference for complex models with varying temperatures.
method Fully amortized neural posterior estimator trained on a single forward pass.
result Achieves competitive posterior approximations across various temperatures and benchmarks.

The paper addresses poor calibration in fine-tuned LLMs after preference alignment.

problem Poor calibration in fine-tuned Large Language Models (LLMs) after preference alignment.
method Proposes a calibration-aware fine-tuning approach to restore calibration without compromising model performance.
result Demonstrates the effectiveness of the proposed methods through extensive experiments.

Paper proposes methods to help autonomous vehicles adapt to unexpected driving scenarios.

problem Autonomous vehicles struggle with unexpected driving conditions.
method Robust imitative planning (RIP) and adaptive robust imitative planning (AdaRIP) methods to detect and adapt to distribution shifts.
result Methods outperform current state-of-the-art approaches in nuScenes prediction challenge.

We look at a collection of conjectures with the unifying message that smaller social systems, tend to be less complex and can be aligned better, towards fulfilling their intended objectives. We touch upon a framework, referred to as the four pronged approach that can aid the analysis of social systems. The four prongs …

2016-03-19abs ↗pdf ↗

New metrics CWSA and CWSA+ improve model evaluation under confidence thresholds.

problem Lack of metrics capturing model reliability under confidence thresholds.
method Introducing CWSA and CWSA+ metrics that reward confident accuracy and penalize overconfident mistakes.
result CWSA and CWSA+ outperform classical metrics in trust-sensitive tests.

FMCPE improves SBI accuracy by correcting posterior estimators with flow matching.

problem Model misspecification in SBI leads to biased or overconfident posteriors.
method Flow Matching Corrected Posterior Estimation (FMCPE) trains a posterior approximator and corrects it using calibration samples.
result FMCPE consistently mitigates misspecification effects, improving inference accuracy and uncertainty quantification.

Bayesian models for networks are often misspecified, leading to overconfident inference.

problem Real-world networks violate assumptions of geometry and link function in latent space models.
method Proposes a generalized posterior framework for random geometric graphs, using Link-Sequential R-SafeBayes to adaptively tune posterior regularization.
result Improved calibration and better link prediction performance demonstrated on synthetic and real-world networks.

Time series foundation models are well-calibrated, improving over baseline models.

problem Calibration of time series foundation models for practical applications.
method Systematic evaluations of five time series foundation models and two baselines, assessing calibration, prediction heads, and long-term forecasting.
result Time series foundation models are consistently better calibrated than baseline models and do not show over- or under-confidence.

New research challenges the independence assumption in neurosymbolic learning, leading to overconfident predictions and unrepresentable uncertainty.

problem The independence assumption in neurosymbolic learning systems can lead to overconfident predictions and hinder uncertainty quantification.
method The study proves the limitations of the independence assumption and introduces new loss functions that are non-convex and difficult to optimise.
result Neurosymbolic learning systems using the independence assumption are prone to overconfidence and cannot represent uncertainty over multiple valid options.

Proposes DSM priors for Bayesian neural networks to improve interpretability and robustness.

problem Bayesian neural networks struggle with interpretability, overconfidence, and adversarial attacks.
method Introduces Dirichlet scale mixture (DSM) priors to address these issues.
result DSM priors lead to sparse networks, robustness against adversarial attacks, and competitive predictive performance.

Modern deep artificial neural networks have achieved great success in the domain of computer vision and beyond. However, their application to many real-world tasks is undermined by certain limitations, such as overconfident uncertainty estimates on out-of-distribution data or performance deterioration under data distri…

2019-10-07abs ↗pdf ↗

QLA improves Bayesian uncertainty estimation for DNNs without increasing computational cost.

problem Overconfident out-of-distribution predictions from DNNs.
method Proposes Quadratic Laplace Approximation (QLA) to improve Bayesian uncertainty quantification.
result QLA yields modest yet consistent uncertainty estimation improvements over Linearized Laplace Approximation (LLA) on five regression datasets.

Flexible evidential deep learning improves uncertainty quantification in machine learning.

problem Overconfident predictions in machine learning models can lead to serious consequences.
method Proposes flexible evidential deep learning (F-EDL) to model uncertainty over class probabilities using a flexible Dirichlet distribution.
result Empirically demonstrates state-of-the-art uncertainty quantification performance across diverse scenarios.

New method calibrates neural SBI to avoid overconfident posteriors.

problem Overconfident posteriors in SBI due to inaccurate uncertainty quantification.
method Introduces a calibration term into neural model training objective, enabling end-to-end backpropagation.
result Achieves competitive or better coverage and posterior density than existing methods.

A post-hoc framework improves model performance by calibrating different feature spaces.

problem Improving AUC performance on binary classification tasks for overconfident models.
method Identifies heterogeneous partitions of the feature space and applies post-hoc calibration techniques to each partition.
result Theoretical optimality of the framework for any model, demonstrated on deep neural networks.

Pseudo-label selection affects semi-supervised learning performance.

problem Selection of pseudo-labeled data impacts semi-supervised learning's generalization performance.
method Embedding pseudo-label selection into decision theory, deriving a novel selection criterion based on posterior predictive.
result BPLS (Bayesian pseudo-label selection) outperforms traditional methods in overfitting-prone data.

Improved Bayesian FL method calibrates predictions for federated learning.

problem Overconfident predictions in Bayesian FL methods for federated learning.
method β-Predictive Bayes algorithm interpolates between mixture and product of local predictive posteriors, tuning parameter β for better calibration.
result Demonstrated superior calibration compared to other baselines, even with increased data heterogeneity.