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.

168,657 papers · 148 categories

Trend · papers per month

2955908851,180 · Jun 202019922001200920172026
48 results for reconstruction-based methods

New study on time series anomaly detection shows overlapping inference improves performance.

problem Heterogeneous evaluation practices and inference procedures in time series anomaly detection.
method Unified training, tuning, and evaluation protocol on TSB-AD benchmark, analyzing overlapping vs. disjoint inference.
result Overlapping inference yields consistent improvements, with average relative gain up to +28%.

Reconstruction based subspace clustering methods compute a self reconstruction matrix over the samples and use it for spectral clustering to obtain the final clustering result. Their success largely relies on the assumption that the underlying subspaces are independent, which, however, does not always hold in the appli…

2012-06-18abs ↗pdf ↗

PaRCE estimates model confidence for CNNs across various uncertainties.

problem Limited holistic approach to estimating perception model confidence in CNNs.
method Probabilistic and reconstruction-based competency estimation.
result PaRCE best distinguishes between various types of samples and regions.

We consider the traffic data reconstruction problem. Suppose we have the traffic data of an entire city that are incomplete because some road data are unobserved. The problem is to reconstruct the unobserved parts of the data. In this paper, we propose a new method to reconstruct incomplete traffic data collected from …

2013-06-27abs ↗pdf ↗

AER combines auto-encoder and LSTM for better time series anomaly detection.

problem Anomaly detection in time series data with limited labeled data and ambiguous definitions.
method AER (Auto-Encoder with Regression) integrates auto-encoder and LSTM for joint predictions and reconstructions.
result AER achieves the highest F1 score across 12 datasets with comparable runtime.

Reconstruction-based learning produces uninformative features for perception tasks.

problem Misalignment between reconstruction-based learning and perception tasks.
method Investigated the impact of input space reconstruction on feature learning for perception tasks.
result Reconstruction-based learning allocates model capacity to a subspace with uninformative features for perception tasks.

Proposes a new VAE framework for anomaly detection in time series data.

problem Data scarcity leads to latent holes and discontinuous regions in latent space, causing non-robust reconstructions.
method Combines VAEs with self-supervised learning to address data scarcity and improve anomaly detection.
result Improves robustness of anomaly detection in time series data by addressing latent holes and discontinuities.

RADAR uses diffusion models to detect anomalies without reconstruction, improving accuracy and efficiency.

problem Challenges in anomaly detection and segmentation, especially in real-time applications.
method RADAR uses attention-based diffusion models to directly produce anomaly maps from the diffusion process, bypassing reconstruction.
result RADAR improves F1 score by 7% on MVTec-AD and 13% on 3D-printed material compared to state-of-the-art methods.

si4onnx enables selective inference on deep learning models.

problem Establishing the reliability of AI systems through statistical significance of identified regions.
method Selective inference techniques implemented through a Python package.
result Controlled type I error rates for hypothesis testing on deep learning models.

In this paper, we address the problem of data reconstruction from privacy-protected templates, based on recent concept of sparse ternary coding with ambiguization (STCA). The STCA is a generalization of randomization techniques which includes random projections, lossy quantization, and addition of ambiguization noise t…

2019-05-08abs ↗pdf ↗

CASTLE learns causal DAG to improve model generalization.

problem Improving model generalization to out-of-sample data.
method CASTLE learns causal relationships via adjacency matrix embedded in neural network input layers, reconstructing only causal features.
result CASTLE leads to better out-of-sample predictions compared to other regularizers.

MET learns tabular data representations without data augmentations.

problem Lack of effective self-supervised learning methods for tabular data.
method Reconstruction-based approach using masked encoding, with separate representations for each coordinate and adversarial reconstruction loss.
result MET achieves state-of-the-art performance on five diverse tabular datasets, improving up to 9% over current methods.

Bayesian layer improves image segmentation and out-of-distribution detection.

problem Outlier detection in image segmentation.
method Parameter-efficient hierarchical convolutional Gaussian Processes in Wasserstein-2 space.
result Uncertainty estimates improve out-of-distribution detection.

An assumption-free automatic check of medical images for potentially overseen anomalies would be a valuable assistance for a radiologist. Deep learning and especially Variational Auto-Encoders (VAEs) have shown great potential in the unsupervised learning of data distributions. In principle, this allows for such a chec…

2019-07-04abs ↗pdf ↗

Theoretical analysis of vision transformers' performance with MAE and CL objectives.

problem Understanding the distinct representations learned by vision transformers with MAE and CL objectives.
method Modeling visual data distribution and analyzing ViTs training dynamics with gradient descent.
result ViTs trained with MAE objectives learn both global and local features, while CL-trained ViTs favor global features.

Self-supervised learning improves by predicting known information, reducing labeled data needs.

problem Efficiently learn useful semantic representations without labeled data.
method Develops a mechanism exploiting statistical connections between pretext tasks to learn representations that solve downstream tasks.
result Proves linear layer yields small approximation error and drastically reduces labeled sample complexity.

PULSE learns representations from physiological time series.

problem Lack of effective pretraining objectives for physiological time series.
method Proposes a pretraining framework exploiting dynamical systems generative model.
result PULSE learns representations that distinguish semantic classes and improve transfer learning.

Generative Adversarial Networks (GANs) can achieve state-of-the-art sample quality in generative modelling tasks but suffer from the mode collapse problem. Variational Autoencoders (VAE) on the other hand explicitly maximize a reconstruction-based data log-likelihood forcing it to cover all modes, but suffer from poore…

2019-09-27abs ↗pdf ↗

Contrastive Code Representation Learning improves code summarization and type inference.

problem Code representations are sensitive to edits, hindering downstream semantic understanding tasks.
method ContraCode: a contrastive pre-training task that learns code functionality.
result Contrastive pre-training improves code summarization and type inference accuracy.

Dictionary learning algorithms have been successfully used for both reconstructive and discriminative tasks, where an input signal is represented with a sparse linear combination of dictionary atoms. While these methods are mostly developed for single-modality scenarios, recent studies have demonstrated the advantages …

2015-02-04abs ↗pdf ↗

IMPACT optimizes LLM compression by focusing on activation importance, reducing model size up to 55.4%.

problem Resource constraints in deploying large language models (LLMs).
method IMPACT integrates activation importance into low-rank compression, optimizing for both size and accuracy.
result IMPACT achieves up to 55.4% greater model size reduction while maintaining comparable or better accuracy.

Bayesian Gaussian Processes layer detects out-of-distribution data in medical imaging.

problem Detecting out-of-distribution data in medical imaging tasks.
method Parameter-efficient hierarchical convolutional Gaussian Processes in Wasserstein-2 space.
result Uncertainty estimates enable superior out-of-distribution detection compared to previous methods.

Modern Hopfield networks help prevent forgetting in generative models after task changes.

problem How to prevent forgetting in generative models after task changes.
method Introduce intrinsic forgetting as an increase in Hopfield energy after task change, analyze memory replay effectiveness, and validate predictions in experiments.
result High-energy, outlier-like samples are more forgettable than cluster-like samples, and energy-based selection of replay samples mitigates forgetting.

DCAE learns compact latent representations for one-class novelty detection.

problem Learning compact latent representations for one-class novelty detection.
method DCAE learns compact and collapse-free latent representations through internal discriminative layers of GANs, reconstructing in-class data finely and exclusively.
result DCAE achieves state-of-the-art performance on novelty and adversarial example detection.

This study predicts parking availability using multi-source data and a self-supervised learning enhanced transformer.

problem Accurate parking availability prediction to support urban planning and management.
method Proposes SST-iTransformer, a self-supervised learning enhanced spatio-temporal inverted transformer, integrating multi-source data.
result SST-iTransformer achieves state-of-the-art performance in parking availability prediction.

New study analyzes security of neural network data reconstruction attacks.

problem Data reconstruction attacks pose a threat to private training data.
method Analyzes security boundary of data reconstruction attacks via neuron exclusivity state.
result Characterizes insecure/secure boundary of data reconstruction attacks.

We describe a novel optimization method for finite sums (such as empirical risk minimization problems) building on the recently introduced SAGA method. Our method achieves an accelerated convergence rate on strongly convex smooth problems. Our method has only one parameter (a step size), and is radically simpler than o…

2016-02-08abs ↗pdf ↗