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

69138206275 · Jun 202019922001200920172026
48 results for embedding uncertainty

DINOSAUR improves retrieval by accounting for embedding uncertainty in recommender systems.

problem Retrieval bias towards popular items due to noisy embeddings.
method Samples multiple embeddings per item and queries with sampled embeddings to account for uncertainty.
result Improves coverage of long-tail niche content without sacrificing recall.

Unified deep framework for personalized recommendations with uncertainty.

problem Uncertainty in user preferences in recommendation systems.
method Gaussian embeddings, Monte-Carlo sampling, convolutional neural networks.
result Superior performance in recommendation accuracy compared to state-of-the-art models.

The paper addresses data uncertainty in graph embedding by modeling data points as Gaussian distributions.

problem Data uncertainty in machine learning pipelines leads to misleading embeddings and lower accuracy.
method The paper proposes modeling data uncertainty using Gaussian distributions and reformulates graph embedding techniques.
result The proposed methods improve the accuracy of graph embedding by accounting for data uncertainty.

Instance embeddings are an efficient and versatile image representation that facilitates applications like recognition, verification, retrieval, and clustering. Many metric learning methods represent the input as a single point in the embedding space. Often the distance between points is used as a proxy for match confi…

2018-09-30abs ↗pdf ↗

Study shows uncertainty of deep learning models can be measured from their embeddings.

problem Uncertainty in contrastive learning models for critical applications.
method Estimating the distribution of training data in embedding space and accounting for local consistency.
result Uncertainty of an embedding vector correlates strongly with downstream accuracy.

To investigate objects without a describable notion of distance, one can gather ordinal information by asking triplet comparisons of the form "Is object xx closer to yy or is xx closer to zz?" In order to learn from such data, the objects are typically embedded in a Euclidean space while satisfying as many triplet …

2019-06-27abs ↗pdf ↗

Validates network bootstraps for uncertainty quantification in network visualisation.

problem Quantifying uncertainty in network embeddings when only a single observation is available.
method Statistical indistinguishable embeddings using k-nearest neighbour smoothing, validated by an exchangeable network test.
result Proposes a principled, distribution-free network bootstrap that passes the exchangeable network test.

Probabilistic embeddings improve speaker diarization accuracy.

problem Improving speaker diarization accuracy using embeddings.
method Extracting x-vectors and precision matrices from speech segments, interfacing with PLDA model, applying agglomerative clustering, joint training of PLDA and extractor.
result Joint training of PLDA and probabilistic x-vector extractor yields accuracy gains.

Graph embedding methods transform high-dimensional and complex graph contents into low-dimensional representations. They are useful for a wide range of graph analysis tasks including link prediction, node classification, recommendation and visualization. Most existing approaches represent graph nodes as point vectors i…

2019-12-02abs ↗pdf ↗

BIGUE algorithm provides credible intervals for hyperbolic network embeddings.

problem Uncertainty in hyperbolic network embeddings.
method Markov chain Monte Carlo (MCMC) algorithm for Bayesian hyperbolic random graph model.
result Samples from the posterior distribution provide credible intervals for hyperbolic coordinates and network properties.

New model predicts radiative properties of nanoparticle layers with high accuracy and uncertainty.

problem Predicting radiative properties of nanoparticle embedded layers accurately and with uncertainty.
method Conditional normalizing flows learn conditional distributions of optical outputs given input parameters.
result The model achieves high predictive accuracy and reliable uncertainty estimates.

Supervised deep-embedding methods project inputs of a domain to a representational space in which same-class instances lie near one another and different-class instances lie far apart. We propose a probabilistic method that treats embeddings as random variables. Extending a state-of-the-art deterministic method, Protot…

2019-09-25abs ↗pdf ↗

FedGTEA learns new tasks in federated learning with task embeddings and alignment.

problem Federated class-incremental learning with task-specific knowledge and model uncertainty.
method Cardinality-Agnostic Task Encoder (CATE) for Gaussian task embeddings, 2-Wasserstein distance for inter-task alignment.
result FedGTEA achieves superior classification performance and mitigates forgetting.

By representing words with probability densities rather than point vectors, probabilistic word embeddings can capture rich and interpretable semantic information and uncertainty. The uncertainty information can be particularly meaningful in capturing entailment relationships -- whereby general words such as "entity" co…

2018-04-26abs ↗pdf ↗

Bayesian approach for modeling counterfactual distribution and off-policy evaluation.

problem Modeling the counterfactual distribution and off-policy evaluation.
method Bayesian conditional mean embeddings and novel Bayesian methods for estimating ultimate treatment effect.
result Quantifying epistemic uncertainty in the counterfactual distribution and off-policy evaluation.

VJE learns latent representations without contrastive learning, providing probabilistic semantics.

problem Learning latent representations without contrastive signals.
method VJE maximizes a symmetric conditional evidence lower bound (ELBO) on paired encoder embeddings, using a Student-t distribution on a polar representation.
result VJE outperforms standard non-contrastive baselines in ImageNet-1K, CIFAR-10/100, and STL-10.

The paper introduces a method to quantify uncertainty in neural networks without parametric assumptions.

problem Uncertainty quantification for neural network predictions.
method Nonparametric estimation of conditional label distribution using Nadaraya-Watson kernel.
result The method effectively disentangles aleatoric and epistemic uncertainties.

This work presents the concept of kernel mean embedding and kernel probabilistic programming in the context of stochastic systems. We propose formulations to represent, compare, and propagate uncertainties for fairly general stochastic dynamics in a distribution-free manner. The new tools enjoy sound theory rooted in f…

2019-11-25abs ↗pdf ↗

A new framework for lightweight BNNs learns heteroscedastic uncertainties efficiently.

problem Learning heteroscedastic uncertainties from BNNs for lightweight networks.
method Embedding heteroscedastic variances into BNN parameters and using moment propagation for inference.
result Improves predictive performance for lightweight BNNs without increasing parameter count.

New algorithm quantifies uncertainty in regression models for complex data types.

problem Uncertainty quantification in regression models for complex data types.
method Model-free uncertainty quantification algorithm based on conditional depth measures and kernel mean embeddings.
result Provides faster convergence rates and non-asymptotic guarantees for prediction regions.

Proposes MamBO for efficient high-dimensional large-scale optimization.

problem High-dimensional and large-scale optimization problems in machine learning and simulation.
method Combines subsampling and subspace embeddings with model aggregation to address uncertainty in surrogate models.
result Improves robustness of Bayesian optimization algorithm and achieves superior performance.

URL benchmark evaluates uncertainty quantification in pretrained models.

problem Need for reliable uncertainty estimates in transferable pretrained models.
method Proposes URL benchmark to measure transferability of representations and uncertainty estimates.
result Transferable uncertainty quantification remains challenging but not contradictory to traditional goals.

BayesIMP combines multiple causal graphs to estimate average treatment effects with uncertainty.

problem Uncertainty quantification in causal inference from multiple datasets.
method Bayesian Interventional Mean Processes (BayesIMP) integrating probabilistic integration and kernel mean embeddings.
result Improvements in average treatment effect estimation over state-of-the-art methods.

Proposes SDE framework for uncertainty quantification in graph neural networks.

problem Lack of uncertainty quantification in graph neural networks.
method Introduces Latent Graph Neural Stochastic Differential Equations (LGNSDE) with Bayesian prior-posterior mechanism and Brownian motion.
result LGNSDEs provide theoretically sensible guarantees for uncertainty estimates and are robust to perturbations.

New insights show embedding lengths correlate with semantic properties.

problem Contrastive embedding norms ignore embedding magnitudes but correlate with semantic properties.
method Formal theoretical framework and analysis of optimization dynamics.
result Embedding lengths encode semantic information as a byproduct of training.

A new algorithm for compressing latent representations in deep models.

problem Compressing continuous latent representations in deep models.
method Separates model design and training from quantization; uses adaptive quantization based on posterior uncertainty.
result Image compression with the proposed algorithm outperforms JPEG over a wide range of bit rates.

This work embeds annotations into a multidimensional space to measure classification difficulty.

problem Uncertainty in machine learning models during annotation phase.
method Develops a Bayesian Dirichlet-Multinomial framework to embed annotations and uses stochastic Expectation Maximization with MCMC.
result Embeddings reflect semantic similarities of original classes, aiding in measuring classification difficulty.

Word embeddings provide point representations of words containing useful semantic information. We introduce multimodal word distributions formed from Gaussian mixtures, for multiple word meanings, entailment, and rich uncertainty information. To learn these distributions, we propose an energy-based max-margin objective…

2017-04-27abs ↗pdf ↗

The paper tackles biases in session-based recommender systems by modeling user interest as a stochastic process.

problem Data uncertainty, popularity bias, and exposure bias in session-based recommender systems.
method The paper proposes treating user interest as a stochastic process in the latent space, debiasing item embeddings, modeling dense user interest, and introducing fake targets to simulate extended exposure.
result The proposed approach mitigates challenges in session-based recommender systems, as shown by computational experiments on various datasets.

A new method to break down insurance costs into risk and uncertainty.

problem Understanding and quantifying insurance costs in uncertain environments.
method An axiomatic approach to decompose premium principles into risk and deviation measures.
result Maximal risk and minimal deviation measures can be uniquely identified in decompositions.

A new probabilistic approach improves deep metric learning by considering image uncertainties and class-specific variances.

problem Proxy-based deep metric learning struggles with image uncertainties and class-specific structures.
method Introduces non-isotropic probabilistic proxy-based deep metric learning using directional von Mises-Fisher distributions.
result Improves generalization performance and competitive on standard benchmarks.

In medicine, both ethical and monetary costs of incorrect predictions can be significant, and the complexity of the problems often necessitates increasingly complex models. Recent work has shown that changing just the random seed is enough for otherwise well-tuned deep neural networks to vary in their individual predic…

2019-06-10abs ↗pdf ↗

UnKGCP generates prediction intervals for uncertain knowledge graphs with statistical guarantees.

problem Lack of quantified predictive uncertainty in existing UnKGE methods.
method Proposes extsc{UnKGCP} framework using conformal prediction with a novel nonconformity measure.
result Sharp prediction intervals effectively capture predictive uncertainty in diverse UnKGE methods.

New method calibrates probabilistic regression models without restrictive assumptions.

problem Ensuring predictive distributions accurately reflect true uncertainty.
method Nonparametric re-calibration algorithm based on conditional kernel mean embeddings.
result Consistently outperforms prior re-calibration approaches across various benchmarks.

The study models mortgage prepayment risk, accounting for behavioral uncertainty, and provides replication strategies.

problem Modeling and replicating the prepayment option of mortgages with behavioral uncertainty.
method Modeling behavioral uncertainty as a non-hedgeable risk factor, proving its impact on exposure value, and using IRSs and swaptions for replication.
result Including behavioral uncertainty reduces the exposure's value, and swaptions are necessary for optimal replication.

GUST framework improves self-training by estimating node uncertainty and generating pseudo-labels.

problem Over-confidence in pseudo-labels during self-training.
method Graph-based uncertainty-aware self-training with stochastic node labeling.
result GUST achieves state-of-the-art performance, especially in sparse labeled data settings.

Quantum Graphical Models (QGMs) generalize classical graphical models by adopting the formalism for reasoning about uncertainty from quantum mechanics. Unlike classical graphical models, QGMs represent uncertainty with density matrices in complex Hilbert spaces. Hilbert space embeddings (HSEs) also generalize Bayesian …

2018-10-29abs ↗pdf ↗

Ask-n-Learn uses gradient embeddings for active learning in image classification.

problem Efficiently labeling large amounts of training data for deep models.
method Gradient embeddings based on pseudo-labels, prediction calibration, and data augmentation.
result Significant improvements over state-of-the-art baselines on image classification tasks.