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.

169,051 papers · 148 categories

Trend · papers per month

18.8%37.5%56.3%75.0% · Jul 199319922001200920182026
48 results for noise embedding

Unified framework for word embedding models using noise examples.

problem Improving word embedding models with negative sampling.
method Formulated a Word-Context Classification (WCC) framework that generalizes SkipGram word embedding models.
result The best noise distribution is the data distribution, improving both performance and training speed.

A method to approximate instance-dependent label noise using instance-confidence embedding.

problem Real-world label noise that depends on individual instances.
method Variational approximation with instance embedding to capture instance-specific label corruption.
result ICE method effectively approximates instance-dependent noise and detects ambiguous instances.

SymNoise improves language model fine-tuning by 6.7% over NEFTune, using symmetric noise.

problem Improving performance of language models through noise-based fine-tuning.
method Introducing SymNoise, a new fine-tuning method using symmetric noise in embeddings.
result SymNoise increases model performance by 69.04% on AlpacaEval compared to NEFTune's 64.69%.

Enhances speech recognition in new environments by embedding noise and scaling training data.

problem Improving speech recognition in unseen noisy environments.
method Embedding noise from unseen environments and scaling training data to 16,784 environments.
result Reduced word error rate from 34.04% to 15.46% on enhanced speech.

Proposes a text perturbation method using a Mahalanobis metric to balance privacy and utility.

problem Low utility of text analysis when using spherical noise for privacy-preserving text embedding.
method Regularized Mahalanobis metric to add elliptical noise, accounting for embedding space density.
result Improves privacy statistics while maintaining utility, outperforming Laplace mechanism.

Meta-learning for estimating complex conditional distributions.

problem Estimating conditional densities in multimodal distributions.
method Noise contrastive estimation with kernel mean embeddings.
result Meta-learning can share representations across tasks for conditional density estimation.

In this paper, benefiting from the strong ability of deep neural network in estimating non-linear functions, we propose a discriminative embedding function to be used as a feature extractor for clustering tasks. The trained embedding function transfers knowledge from the domain of a labeled set of morphologically-disti…

2018-05-07abs ↗pdf ↗

Manifold learning and dimensionality reduction techniques are ubiquitous in science and engineering, but can be computationally expensive procedures when applied to large data sets or when similarities are expensive to compute. To date, little work has been done to investigate the tradeoff between computational resourc…

2016-03-12abs ↗pdf ↗

The goal of ordinal embedding is to represent items as points in a low-dimensional Euclidean space given a set of constraints in the form of distance comparisons like "item ii is closer to item jj than item kk". Ordinal constraints like this often come from human judgments. To account for errors and variation in jud…

2016-06-22abs ↗pdf ↗

Generative Adversarial Nets (GANs) and Variational Auto-Encoders (VAEs) provide impressive image generations from Gaussian white noise, but the underlying mathematics are not well understood. We compute deep convolutional network generators by inverting a fixed embedding operator. Therefore, they do not require to be o…

2018-05-17abs ↗pdf ↗

The paper analyzes side effects of learning from low-dimensional data embedded in a Euclidean space.

problem Learning from data distributed in a linear subspace of high-dimensional space.
method Derives estimates on the variation of the learning function and studies regularization effects.
result Potential regularization effects associated with network depth and noise in codimension of data manifold.

Proposes EOT eigenmaps for aligning and embedding multiple datasets.

problem Aligning and embedding multiple datasets with shared structures but individual distortions.
method Entropic Optimal Transport (EOT) eigenmaps, leveraging leading singular vectors of EOT plan matrix.
result Proves theoretical guarantees and favorable properties for aligning and embedding datasets.

Vector embedding is a foundational building block of many deep learning models, especially in natural language processing. In this paper, we present a theoretical framework for understanding the effect of dimensionality on vector embeddings. We observe that the distributional hypothesis, a governing principle of statis…

2018-03-01abs ↗pdf ↗

The paper presents a method to preserve privacy in text analysis using calibrated noise.

problem Accurately learning from user data while maintaining privacy.
method Calibrated multivariate perturbations applied to word embeddings to achieve geo-indistinguishability.
result The method provides better privacy guarantees than baseline models with minimal utility loss.

Compressed LLM embeddings improve noisy regression tasks without overfitting.

problem Noisy regression tasks with high signal-to-noise ratios.
method Comparison of embedding compression techniques using autoencoder hidden representations.
result Compression improves performance on noisy tasks like financial return prediction.

GraphZoom improves graph embedding accuracy and scalability.

problem Node attribute noise and scalability issues in graph embedding models.
method GraphZoom combines graph fusion and multi-level coarsening to improve accuracy and scalability.
result GraphZoom significantly increases classification accuracy and speeds up the embedding process.

I-BBS identifies latent sub-manifolds from distance matrices, robust to noise.

problem Identifying latent sub-manifolds from distance matrices in high-dimensional spaces.
method Coordinate-free inference using random distance matrix theory and generative noise models.
result Recovering latent geometry from integer-stable signatures of eigenvalues.

Kernel-spectral embedding learns low-dim. structures from noisy data.

problem Learning low-dimensional nonlinear structures from high-dimensional noisy data.
method Adaptive bandwidth spectral embedding using integral operators.
result Convergence to noiseless embeddings and eigenfunctions of integral operators.

Kernel embeddings of distributions and the Maximum Mean Discrepancy (MMD), the resulting distance between distributions, are useful tools for fully nonparametric two-sample testing and learning on distributions. However, it is rarely that all possible differences between samples are of interest -- discovered difference…

2017-03-22abs ↗pdf ↗

Regularization improves spectral embedding by focusing on the largest blocks.

problem Improving the quality of spectral embedding for graph data.
method Explained the impact of complete graph regularization on spectral embedding of a block model.
result Regularization forces spectral embedding to focus on the largest blocks, making it less sensitive to noise or outliers.

Proposes a new method for efficient manifold denoising robust to high dimensional noise.

problem Efficiently denoise manifolds in high dimensional spaces with complicated noise.
method Landmark diffusion and optimal shrinkage under high dimensional noise and compact manifold setup.
result Systematic comparison with other algorithms on simulated and real datasets shows superior performance.

We describe a new method called t-ETE for finding a low-dimensional embedding of a set of objects in Euclidean space. We formulate the embedding problem as a joint ranking problem over a set of triplets, where each triplet captures the relative similarities between three objects in the set. By exploiting recent advance…

2016-11-30abs ↗pdf ↗

Beta-SOD detects and corrects noisy object re-identification using cosine similarity and Beta mixtures.

problem Noisy object re-identification in image datasets.
method Reframed Re-ID as a similarity task, using Siamese networks and Beta mixture models.
result Superior performance in noisy conditions compared to state-of-the-art methods.

Multiplicative noise models are often used instead of additive noise models in cases in which the noise variance depends on the state. Furthermore, when Poisson distributions with relatively small counts are approximated with normal distributions, multiplicative noise approximations are straightforward to implement. Th…

2018-05-07abs ↗pdf ↗

New method embeds correlation networks to reveal underlying time series patterns.

problem Analyzing correlation networks derived from time series data.
method Spectral embedding of noisy correlation networks, leveraging Fourier basis elements.
result Spectral embedding recovers true vertex-level latent representations under suitable assumptions.

Generates low-dimensional node vectors for graphs with privacy while preserving structural preferences.

problem Publishing graph node vectors can leak sensitive individual information.
method SE-PrivGEmb, a skip-gram based technique with a unified noise tolerance mechanism and negative sampling probabilities.
result Our method outperforms existing methods in structural equivalence and link prediction tasks.

Robustly computes intrinsic coordinates on point clouds using resampling and averaging.

problem Computing intrinsic coordinates on noisy or outlier-prone point clouds.
method Subsample data, vary hyperparameters, cluster candidate embeddings, identify representative embeddings, and average them using Procrustes analysis.
result Robust to noise and outliers, validated on synthetic and real data.

The local linear embedding algorithm (LLE) is a non-linear dimension-reducing technique, widely used due to its computational simplicity and intuitive approach. LLE first linearly reconstructs each input point from its nearest neighbors and then preserves these neighborhood relations in the low-dimensional embedding. W…

2008-08-06abs ↗pdf ↗

A new deep metric learning method pulls embeddings towards dense clusters to improve classification accuracy.

problem Improving classification accuracy in deep metric learning models.
method Density Aware Metric Learning (DAML) which pulls embeddings towards the densest regions of clusters for each class.
result DAML achieves faster convergence and higher generalizability compared to existing methods.

Develops statistical confidence sets for multidimensional scaling.

problem Statistical uncertainty in multidimensional scaling of noisy data.
method Formal statistical framework, distributional convergence results, uniform confidence sets, bootstrap procedures.
result Construction of reliable confidence sets for latent configurations in multidimensional scaling.

We find the minimax rate of convergence in Hausdorff distance for estimating a manifold M of dimension d embedded in R^D given a noisy sample from the manifold. We assume that the manifold satisfies a smoothness condition and that the noise distribution has compact support. We show that the optimal rate of convergence …

2010-07-04abs ↗pdf ↗

This work analyzes label embedding for large multiclass classification problems.

problem Label embedding for large multiclass classification problems.
method Analysis of label embedding in extreme multiclass classification, presenting an excess risk bound and showing a trade-off between computational and statistical efficiency.
result The statistical penalty for label embedding vanishes with sufficiently low coherence under the Massart noise condition.

The paper establishes concentration bounds for embeddings of generative models.

problem Analyzing statistical properties of generative models.
method High probability concentration bounds on sample vector embeddings using Data Kernel Perspective Space.
result Determines the number of samples needed for accurate approximation of generative model embeddings.

New algorithm trains binary-activation, multi-level RNNs for noise-resilient, ADC-/DAC-free PIM inference.

problem Training noise-resilient, ADC-/DAC-free neural networks.
method Binary activations and multi-level weights for eNVM-based processing-in-memory circuits.
result Higher accuracy and noise resilience for recurrent networks compared to existing methods.