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.

169,341 papers · 148 categories

Trend · papers per month

16314762 · Feb 202019922001200920182026
48 results for neighbor retrieval

New methods use vector search and nearest-neighbor matching for policy learning in causal inference.

problem Learning optimal policies in causal inference with limited data.
method RAG-based policy learning with vector search and nearest-neighbor matching.
result The methods bound the within-candidate choice regret and evaluate the one-step method directly as a policy.

Exemplar VAEs link generative models with nearest neighbor retrieval and data augmentation.

problem Improving generative model performance and data augmentation effectiveness.
method Exemplar VAEs with Parzen window prior, retrieval augmented training, exemplar leave-one-out, and subsampling.
result Generative data augmentation reduces classification error on MNIST and Fashion MNIST.

New method finds dependent subspaces of multiple views for better data retrieval.

problem Finding relationships between multiple data views for analysis and prediction.
method Optimizes mappings for each view to maximize cross-view similarity between neighborhoods of data samples.
result The method outperforms alternatives in preserving cross-view neighborhood similarities and detecting local dependencies.

A new ranking algorithm learns data affinity and ranking scores simultaneously.

problem Retrieving similar objects in large databases is challenging.
method Proposes a ranking algorithm that learns data affinity and ranking scores simultaneously, using adaptive neighbors and smoothness constraints.
result The proposed algorithm outperforms existing methods in synthetic and real datasets.

Paper shows how to efficiently summarize large datasets using sparsity.

problem Efficiently summarize large datasets using submodular optimization.
method Develops a sparsified submodular optimization method and analyzes a new sparsification technique.
result Proves that sparsified submodular optimization is almost optimal under standard assumptions.

The paper analyzes how much data points can be altered to change their rank in nearest neighbor searches.

problem Vulnerability of nearest neighbor search in high-dimensional data.
method Statistical analysis of perturbation needed to change neighbor rank.
result Derived statistical distribution of perturbation needed to modify neighbor rank.

Improved text embeddings enhance retrieval from a knowledge base.

problem Efficiently retrieving relevant paragraphs from a large knowledge base.
method Used Stanford Question Answering Dataset (SQuAD) for open-domain question answering. Compared various text-embedding methods and trained deep residual neural models for retrieval.
result Training deep residual neural models for retrieval purposes significantly improves paragraph recall.

Random convolutional neural network improves image classification and retrieval.

problem Improving image classification and retrieval performance.
method Random depthwise signed convolutional neural network.
result Higher accuracy in image classification and retrieval compared to baseline models.

A new multilabel classification framework improves ANN search performance.

problem Efficiently finding approximate nearest neighbors in large datasets.
method Formulated ANN search as a multilabel classification problem, using partitioning classifiers.
result Natural classifier leads to strictly improved performance in ANN search.

Paper proposes SAN and SN for zero-shot sketch-based image retrieval.

problem Handling unseen classes in sketch-based image retrieval.
method Generative approach using Stacked Adversarial Network (SAN) and Siamese Network (SN).
result Significant improvement in standard and generalized ZSL settings.

kNN-MTS improves MTS forecasting by using nearest neighbor retrieval over a large dataset.

problem Limited ability of current MTS forecasting methods to identify similar patterns and handle sparsely distributed correlations.
method kNN-MTS framework using nearest neighbor retrieval over a large datastore of cached series, with representations from MTS model for similarity search.
result Significant improvement in forecasting performance on real-world datasets.

Deep Retrieval learns a retrievable structure for efficient large-scale recommendations.

problem Efficiently retrieving top relevant candidates in large-scale recommendation systems.
method Deep Retrieval learns a retrievable structure directly from user-item interaction data, encoding candidates into a discrete latent space and optimizing a model to maximize accuracy.
result Deep Retrieval achieves almost the same accuracy as brute-force baseline and significantly outperforms ANN baselines in a live production system.

Neighbor-encoder learns representations by reconstructing neighbors, outperforming autoencoders.

problem Learning effective representations for various data types.
method Reconstructs neighbors instead of inputs, incorporating domain knowledge through similarity definitions.
result Neighbor-encoder outperforms autoencoders in diverse domains and tasks.

A new method for fast XMLC using IR vector space model.

problem Handling many labels in extreme multi-label classification.
method Sparse Weighted Nearest-Neighbor Method derived from SOTA linear classifiers.
result Equivalent performance to SOTA models on large datasets.

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.

We construct a partial order relation which acts on the set of 3-cliques of a maximal planar graph G and defines a unique hierarchy. We demonstrate that G is the union of a set of special subgraphs, named `bubbles', that are themselves maximal planar graphs. The graph G is retrieved by connecting these bubbles in a tre…

2009-06-26abs ↗pdf ↗

Diversifies reply suggestions for IM systems using M-CVAE.

problem Improving diversity of automated reply suggestions in instant messaging systems.
method Formulated a generative latent variable model with Conditional Variational Auto-Encoder (M-CVAE) to diversify responses.
result Increased diversity by ~30-40% without significant impact on relevance.

Paper improves full-text search engines for fast exact NNS in binary codes.

problem Efficient nearest neighbor search in Hamming space for full-text search engines.
method Revisits and combines three techniques from information retrieval: bit operation, subs-code filtering, and data preprocessing with permutation.
result Significant speed-ups for NNS in binary codes over state-of-the-art term match approach.

Method embeds numeric tabular datasets into a shared vector space for similarity and retrieval.

problem Lack of meaningful representation for numeric tabular datasets in large language models.
method Structured exploratory data analysis descriptors, sentence transformer embedding, CCA for cross-dataset alignment.
result Total P@1 score of 0.9 across 15 datasets, robust nearest-neighbor retrieval and cluster structure.

Minwise hashing (Minhash) is a widely popular indexing scheme in practice. Minhash is designed for estimating set resemblance and is known to be suboptimal in many applications where the desired measure is set overlap (i.e., inner product between binary vectors) or set containment. Minhash has inherent bias towards sma…

2014-11-14abs ↗pdf ↗

Proposes CSRN for better news recommendation by integrating RNN and UserCF.

problem Lack of societal influence in news recommendation.
method Integrates RNN-based sequential recommendation and UserCF, using a directed co-reading network.
result Significantly outperforms state-of-the-art approaches in news recommendation.

The study evaluates and tests kk-NN models in various applications.

problem The relation between parameters and accuracy of kk-NN models is not well understood.
method Developed a randomized algorithm to test the kk-NN property with a complexity of O(nk2/ε2)O(\sqrt{n} k^2 / ε^2).
result The algorithm can detect kk-NN models with bad accuracy in significantly less time than building the model.

This work investigates how GCNs should handle local structure discrepancies in testing nodes.

problem GCNs assume homophily but real graphs often have discrepancies in local structure.
method Using causal graph analysis, the study intervenes the graph structure to assess the local structure's impact on predictions.
result The method effectively enhances GCN predictions by eliminating local structure discrepancies.

CMT efficiently manages memory by inserting and querying memories in logarithmic time.

problem Managing large memory stores efficiently for quick access and updates.
method Designing a Contextual Memory Tree (CMT) that inserts and retrieves memories in logarithmic time.
result CMT improves classification algorithms and image-captioning tasks, demonstrating better computational efficiency.

Improves retrieval accuracy for hierarchical documents, especially for distant matches.

problem Limited expressive power of dual encoder models in hierarchical retrieval.
method Proves feasibility of DEs for HR, introduces pretrain-finetune recipe to improve long-distance retrieval.
result Pretrain-finetune boosts recall on long-distance pairs from 19% to 76%.

This paper improves image retrieval accuracy through novel relevance feedback methods.

problem Improving image retrieval accuracy in Content-Based Image Retrieval (CBIR).
method Novel addition to feature re-weighting and classification techniques, focusing on 0-th iteration improvement.
result Significantly improved retrieval accuracy from relevance feedback.

A new framework for personalized ad retrieval in e-commerce search.

problem Difficulty in measuring ads retrieved using multiple signals (e.g. user profiles, clicks).
method Employing historical click data to initialize a hierarchical network representing signals, keys, and ads. Training a model to learn weights of edges and selecting the best edges.
result Framework achieves good performance, improving RPM/CTR.

Study improves image-caption retrieval by quantifying feature and posterior uncertainty.

problem Improving reliability in image-caption retrieval tasks with deep learning models.
method Quantified feature and posterior uncertainty for model averaging and reliability measure in image-caption retrieval.
result Consistent improvement in retrieval performance with different datasets and architectures.

Transformer models improve query-document retrieval efficiency and accuracy.

problem Efficiently retrieve relevant documents from large corpora for query matching.
method Designed paragraph-level pre-training tasks to optimize embedding-based Transformer models.
result Transformer models significantly outperform BM-25 and non-Transformer embedding models.