Search Results for author:
Found 34 papers, 13 papers with code
Uncertainty Estimation of Transformer Predictions for Misclassification Detection
Uncertainty estimation (UE) of model predictions is a crucial step for a variety of tasks such as active learning, misclassification detection, adversarial attack detection, out-of-distribution detection, etc.
Generalization error of spectral algorithms
In the present work, we consider the training of kernels with a family of $\textit{spectral algorithms}$ specified by profile $h(\lambda)$, and including KRR and GD as special cases.
Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification
Uncertainty scores leverage information encapsulated in the output of a neural network or its layers to detect unreliable predictions, and we show that they can be used to fact-check the atomic claims in the LLM output.
Predictive Uncertainty Quantification via Risk Decompositions for Strictly Proper Scoring Rules
Distinguishing sources of predictive uncertainty is of crucial importance in the application of forecasting models across various domains.
Efficient Conformal Prediction under Data Heterogeneity
Conformal Prediction (CP) stands out as a robust framework for uncertainty quantification, which is crucial for ensuring the reliability of predictions.
Dirichlet-based Uncertainty Quantification for Personalized Federated Learning with Improved Posterior Networks
This paper presents a new approach to federated learning that allows selecting a model from global and personalized ones that would perform better for a particular input point.
LM-Polygraph: Uncertainty Estimation for Language Models
Recent advancements in the capabilities of large language models (LLMs) have paved the way for a myriad of groundbreaking applications in various fields.
Selective Nonparametric Regression via Testing
Prediction with the possibility of abstention (or selective prediction) is an important problem for error-critical machine learning applications.
Optimal Estimation in Mixed-Membership Stochastic Block Models
Community detection is one of the most critical problems in modern network science.
Conformal Prediction for Federated Uncertainty Quantification Under Label Shift
Federated Learning (FL) is a machine learning framework where many clients collaboratively train models while keeping the training data decentralized.
Scalable Batch Acquisition for Deep Bayesian Active Learning
In deep active learning, it is especially important to choose multiple examples to markup at each step to work efficiently, especially on large datasets.
Active Learning for Abstractive Text Summarization
Active Learning (AL) is a technique developed to reduce the amount of annotation required to achieve a certain level of machine learning model performance.
Learning Confident Classifiers in the Presence of Label Noise
We evaluate the proposed method on a series of classification tasks such as noisy versions of MNIST, CIFAR-10, Fashion-MNIST datasets as well as CIFAR-10N, which is real-world dataset with noisy human annotations.
ScaleFace: Uncertainty-aware Deep Metric Learning
The performance of modern deep learning-based systems dramatically depends on the quality of input objects.
Towards OOD Detection in Graph Classification from Uncertainty Estimation Perspective
The problem of out-of-distribution detection for graph classification is far from being solved.
Scalable computation of prediction intervals for neural networks via matrix sketching
Accounting for the uncertainty in the predictions of modern neural networks is a challenging and important task in many domains.
Embedded Ensembles: Infinite Width Limit and Operating Regimes
In this limit, we identify two ensemble regimes - independent and collective - depending on the architecture and initialization strategy of ensemble models.
Nonparametric Uncertainty Quantification for Single Deterministic Neural Network
This paper proposes a fast and scalable method for uncertainty quantification of machine learning models' predictions.
Monte Carlo Variational Auto-Encoders
Variational auto-encoders (VAE) are popular deep latent variable models which are trained by maximizing an Evidence Lower Bound (ELBO).
How Certain is Your Transformer?
In this work, we consider the problem of uncertainty estimation for Transformer-based models.
Nonreversible MCMC from conditional invertible transforms: a complete recipe with convergence guarantees
This paper fills the gap by developing general tools to ensure that a class of nonreversible Markov kernels, possibly relying on complex transforms, has the desired invariance property and leads to convergent algorithms.
EWS-GCN: Edge Weight-Shared Graph Convolutional Network for Transactional Banking Data
In this paper, we discuss how modern deep learning approaches can be applied to the credit scoring of bank clients.
Dropout Strikes Back: Improved Uncertainty Estimation via Diversity Sampling
Uncertainty estimation for machine learning models is of high importance in many scenarios such as constructing the confidence intervals for model predictions and detection of out-of-distribution or adversarially generated points.
MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference
In this contribution, we propose a new computationally efficient method to combine Variational Inference (VI) with Markov Chain Monte Carlo (MCMC).
NCVis: Noise Contrastive Approach for Scalable Visualization
Modern methods for data visualization via dimensionality reduction, such as t-SNE, usually have performance issues that prohibit their application to large amounts of high-dimensional data.
Linking Bank Clients using Graph Neural Networks Powered by Rich Transactional Data
Financial institutions obtain enormous amounts of data about user transactions and money transfers, which can be considered as a large graph dynamically changing in time.
Geometry-Aware Maximum Likelihood Estimation of Intrinsic Dimension
The existing approaches to intrinsic dimension estimation usually are not reliable when the data are nonlinearly embedded in the high dimensional space.
Deeper Connections between Neural Networks and Gaussian Processes Speed-up Active Learning
Active learning methods for neural networks are usually based on greedy criteria which ultimately give a single new design point for the evaluation.
Constructing Graph Node Embeddings via Discrimination of Similarity Distributions
The problem of unsupervised learning node embeddings in graphs is one of the important directions in modern network science.
Dropout-based Active Learning for Regression
Active learning is relevant and challenging for high-dimensional regression models when the annotation of the samples is expensive.
Sparse Group Inductive Matrix Completion
We consider the problem of matrix completion with side information (\textit{inductive matrix completion}).
Simultaneous Matrix Diagonalization for Structural Brain Networks Classification
This paper considers the problem of brain disease classification based on connectome data.
Consistent Estimation of Mixed Memberships with Successive Projections
This paper considers the parameter estimation problem in Mixed Membership Stochastic Block Model (MMSB), which is a quite general instance of random graph model allowing for overlapping community structure.
Statistics Theory Statistics Theory
GTApprox: surrogate modeling for industrial design
We describe GTApprox - a new tool for medium-scale surrogate modeling in industrial design.
