Improved efficient learning of neighbor representations for large datasets.
problem Efficiently learn neighbor representations for large datasets.
method Differentiable Boundary Sets algorithm that overcomes computational issues and improves accuracy.
result Significant reduction in training time and improved classification accuracy.
A new method uses nearest neighbors for importance weighting.
problem Data covariate shift problems in machine learning.
method Nearest neighbor classification scheme for determining importance weights.
result Demonstrated effectiveness through comparative experiments on various classification tasks.
A reject option improves partial-label learning's accuracy.
problem Ambiguously labeled data in real-world applications.
method Risk-consistent nearest-neighbor algorithm with a reject option.
result Our method provides the best trade-off between non-rejected predictions' number and accuracy.
The paper develops methods for constructing confidence regions for regression functions in binary classification.
problem Building distribution-free confidence regions for regression functions in binary classification.
method Resampling test and empirical risk minimization approach for model classes with finite pseudo-dimensions and inverse Lipschitz parameterizations.
result Strong uniform consistency and exponential probably approximately correct bounds on the L 2 L_2 L 2 sizes of the regions. A new GCN model learns higher-order neighbors without explicit adjacency matrix computation.
problem GCN's performance drops for deeper structures due to limited neighborhood information.
method Assumes higher-order neighbors are similar to first-order neighbors, learns weights through Lasso to minimize feature loss.
result HWGCN achieves state-of-the-art results on various datasets.
Enhances graph neural networks by considering feature similarities in node aggregation.
problem Ignoring node feature similarities in traditional graph aggregation schemes.
method Interprets node aggregation as kernel weighting, proposing a framework that considers feature similarities.
result Proposed framework outperforms traditional GCNs in real-world applications.
A new graph-based clustering method for moderate-dimensional data.
problem Performance degradation of existing graph-based clustering methods in high dimensions.
method Introduces UN-CCDs using NND-based MC-SRT for covering radii determination.
result UN-CCDs provide stable and competitive performance in moderate-sized datasets.
Enhanced KNN-TSVM reduces noise and overfitting with stable learning rules.
problem High computational cost and overfitting in KNN-based TSVM classifiers.
method Weighted KNN with stabilizer term and LDMDBA for efficient computation.
result Effective in both classification accuracy and computational time, with up to 14x speedup.
DANCE improves prediction set efficiency for deep learning models.
problem Inefficient, overly conservative prediction sets for pre-trained models.
method DANCE combines adaptive kernel regression and nearest-neighbor approach.
result DANCE produces more efficient and robust prediction sets.
Simple k-NN filtering improves model accuracy on noisy labels.
problem Training models with noisy labels reduces performance and is hard to identify.
method A simple k k k -nearest neighbor-based filtering approach on the logit layer. result Improves model accuracy compared to recent methods.
Deep nearest neighbors outperform self-supervised methods in anomaly detection.
problem Anomaly detection using self-supervised deep methods.
method Simple nearest-neighbor approach on Imagenet pretrained features.
result Nearest-neighbor method outperforms self-supervised methods in accuracy, few shot generalization, training time, and noise robustness.
The paper explains how nearest neighbor methods succeed in prediction.
problem Explaining the success of nearest neighbor methods in prediction.
method The paper covers both theoretical and practical aspects of nearest neighbor methods, including statistical guarantees and practical algorithms.
result The paper provides nonasymptotic statistical guarantees and practical algorithms for nearest neighbor methods.
Paper develops multivariate time series similarity and distance measures.
problem Compensating for misalignments in multivariate time series data.
method Adapted Independent and Dependent DTW strategies to seven elastic similarity and distance measures.
result Each measure achieves highest accuracy on at least one dataset, supporting their value.
HGNN learns augmented features for deep multi-task learning.
problem Feature learning for deep multi-task learning.
method Hierarchical Graph Neural Network (HGNN) with two levels of graph neural networks.
result Significant performance improvement in classification tasks.
Proposes robust ABC method for outlier detection.
problem Outliers sensitivity in ABC methods.
method γ-divergence estimator with redescending property.
result Significantly higher robustness than existing methods.
Paper uses a mix of deep and kernel learning to personalize sepsis treatment.
problem Managing sepsis in ICU patients due to individual variability.
method A mixture-of-experts framework combining kernel-based and deep reinforcement learning.
result The mixture-based approach outperforms individual methods on a large sepsis patient cohort.
A clustering algorithm for natural hierarchical clusters with near-linear time complexity.
problem Hierarchical clustering with near-linear time complexity.
method Nearest neighbor based clustering algorithm that defines clusters naturally.
result Near-linear time and space complexity for certain datasets.
In this paper we investigate the problem of estimating the cluster tree for a density f f f supported on or near a smooth d d d -dimensional manifold M M M isometrically embedded in R D \mathbb{R}^D R D . We analyze a modified version of a k k k -nearest neighbor based algorithm recently proposed by Chaudhuri and Dasgupta. The main res…
The conditional mutual information I(X;Y|Z) measures the average information that X and Y contain about each other given Z. This is an important primitive in many learning problems including conditional independence testing, graphical model inference, causal strength estimation and time-series problems. In several appl…
We derive Gaussian approximations for random forest predictions using region-based stabilization.
problem Improving the accuracy of random forest predictions for Poisson process data.
method Region-based stabilization and Malliavin-Stein method for multivariate Gaussian approximation.
result Established Gaussian approximation bounds for random forest predictions under Poisson process.
A new method for efficient Gaussian process inference using sparse approximations.
problem Scalable and accurate inference for latent Gaussian processes.
method Variational approximation with sparse inverse Cholesky factors and double Kullback-Leibler minimization.
result The proposed method can achieve highly accurate approximations with polylogarithmic time complexity.
New method generates novel samples from closed-form diffusion models.
problem Closed-form SGMs memorize training data and cannot generate novel samples.
method Explicitly smooth closed-form score, use nearest-neighbor estimator.
result Efficient method generates novel samples without training.
A new approach to L 2 L_2 L 2 -consistent estimation of a general density functional using k k k -nearest neighbor distances is proposed, where the functional under consideration is in the form of the expectation of some function f f f of the densities at each point. The estimator is designed to be asymptotically unbiased, using t…
ResMem improves model generalization by explicitly memorizing residuals.
problem Improving model generalization in neural networks.
method ResMem algorithm that augments a model with a k-nearest neighbor based regressor fitted to residuals.
result ResMem consistently improves test set generalization across various benchmarks.
The success of various applications including robotics, digital content creation, and visualization demand a structured and abstract representation of the 3D world from limited sensor data. Inspired by the nature of human perception of 3D shapes as a collection of simple parts, we explore such an abstract shape represe…
We consider machine learning in a comparison-based setting where we are given a set of points in a metric space, but we have no access to the actual distances between the points. Instead, we can only ask an oracle whether the distance between two points i i i and j j j is smaller than the distance between the points i i i an…
Unified Python package N 2 ^2 2 benchmarks NN-based matrix completion methods.
problem Matrix completion with robust NN methods across diverse applications.
method Unified Python package N 2 ^2 2 consolidates NN-based methods. result NN-based techniques outperform classical methods in real-world settings.
A new MARL framework for community-based cooperation with transfer and active exploration.
problem Flexible coordination patterns in multi-agent systems with community structures.
method Community-based multi-agent reinforcement learning with transfer and active exploration.
result Provably convergent actor-critic algorithms for structured information sharing and transfer learning.
Universal Bayes consistency proved in metric spaces.
problem Proving universal Bayes consistency in metric spaces.
method Extending a multiclass learning algorithm and proving its Bayes-consistency in all metric spaces.
result First learning algorithm universally strongly Bayes-consistent in all metric spaces.
Unified meta-learning framework from supervised learning.
problem Difficulty in comparing and evaluating meta-learning approaches.
method Treating meta-learning as supervised learning, reducing algorithms to supervised learning instances.
result Unified framework and improved model performance on few-shot learning.
Study on online learning with networked agents, showing how network structure affects performance.
problem Understanding how network structure impacts performance in online learning settings.
method Characterized the effect of network structure on regret in both stochastic and adversarial settings.
result Optimal regret bound of order α T \sqrt{αT} α T when activations are stochastic and network structure is known. Scalable Gaussian Process Operator tackles high-dimensional PDEs.
problem Scaling Gaussian Process Operators to high-dimensional, data-intensive regimes.
method Nearest-neighbor-based local kernel approximations, sparse kernel approximation, structured Kronecker factorizations, operator-aware kernel structures, task-informed mean functions.
result Consistently achieves high accuracy across varying discretization scales.
Improves PU learning for imbalanced data with practical AUL estimation and new training method.
problem Training binary classifiers on datasets with only positive and unlabeled samples.
method Asymptotic unbiased AUL estimation and ProbTagging for imbalanced data.
result ProbTagging increases AUC by up to 10% on industrial and artificial data sets.
CGMMD generates conditional samples in one shot with MMD and nearest neighbors.
problem Generating samples from a conditional distribution unseen in training.
method CGMMD uses MMD for a direct minimization problem, producing samples in one forward pass.
result CGMMD achieves convergence to the true conditional distribution with theoretical bounds.
Generative Latent Nearest Neighbors (GLANN) generates better images without adversarial training.
problem Stability and mode collapse issues in GANs for image generation.
method Combines IMLE and GLO strengths to avoid GAN's weaknesses.
result Generative Latent Nearest Neighbors (GLANN) generates better images than GLO and IMLE.
The paper explores how word embeddings affect the stability of downstream NLP models.
problem Small changes in training data can cause significant changes in model predictions.
method Empirical and theoretical analysis of embedding instability, including the introduction of eigenspace instability measure.
result Increasing embedding memory can reduce the disagreement in predictions by 5% to 37%.
Improved manifold-adaptive dimension estimator for better data complexity assessment.
problem Estimating intrinsic dimensionality of complex data.
method Revised and improved Farahmand-Szepesvári-Audibert (FSA) estimator, incorporating probability density function and median.
result Median-FSA estimator outperforms existing methods in accuracy and robustness.
A novel algorithm minimizes regret in a multi-agent bandit problem with time-varying random graphs and heterogeneous rewards.
problem Minimizing regret in a multi-agent multi-armed bandit problem with time-varying random graphs and heterogeneous rewards.
method Introduces a novel algorithmic framework combining averaging-based consensus with a weighting technique and upper confidence bound.
result Derives optimal instance-dependent regret upper bounds of order log T \log{T} log T in both sub-gaussian and sub-exponential environments. New algorithms detect outliers in high-dimensional data with arbitrary shapes.
problem Challenges of high dimensionality and varying cluster shapes in traditional outlier detection methods.
method Cluster Catch Digraphs (CCDs) and their variants (U-MCCD, UN-MCCD, SU-MCCD, SUN-MCCD).
result U-MCCD efficiently identifies outliers with high true negative rates, and SU-MCCD improves handling of non-uniform clusters.
A new method predicts links better across various networks.
problem Adaptive link prediction for diverse network types.
method MOLI method using local information from neighbors of different distances.
result MOLI outperforms other link prediction algorithms.
A new outlier measure CFOF avoids concentration in high dimensions.
problem Outlier detection in high-dimensional data.
method Formalizes concentration of outlier scores, determines closed form distribution, and introduces fast-CFOF algorithm.
result CFOF is immune to concentration in high dimensions and has a clear statistical characterization.
A method for dynamic ranking using BTL model and nearest neighbor rank centrality.
problem Aggregating evolving pairwise comparisons to recover item strengths over time.
method Adapting Rank Centrality method to handle dynamic pairwise outcomes.
result Consistency of the method in estimating latent strengths over time.
Paper presents a new framework for sequence classification.
problem Sequence classification in real-world applications.
method Reference-based sequence classification framework.
result New sequence classification algorithms achieve comparable accuracy.
Dual-stage sEMG classification improves gesture recognition accuracy.
problem Improving accuracy in hand gesture recognition from sEMG signals.
method Dual-stage classification approach: first stage groups similar activities, second stage classifies within groups.
result Dual-stage classification yields significantly higher accuracy than single-stage approach.
A novel method for classification with rejection using ensemble of cost-sensitive classifiers.
problem Avoid risky misclassification in error-critical applications.
method Learning an ensemble of cost-sensitive classifiers.
result Improved classification accuracy and flexibility in loss selection.
The number of possible methods of generalizing binary classification to multi-class classification increases exponentially with the number of class labels. Often, the best method of doing so will be highly problem dependent. Here we present classification software in which the partitioning of multi-class classification…
Few-shot image classification is improved by correcting CNNs' texture bias.
problem Few-shot image classification performance is hindered by CNNs' texture bias.
method Corrected CNNs' texture bias using a simpler method than state-of-the-art approaches.
result State-of-the-art performance on miniImageNet task achieved.
Paper introduces LPCs for robust classification with performance bounds.
problem Conventional classification techniques constrain rules and use surrogate losses.
method Robust risk minimization (RRM) for unconstrained classification rules, optimizing 0-1 loss.
result LPCs provide performance bounds and competitive performance with state-of-the-art techniques.