We develop mask iterative hard thresholding algorithms (mask IHT and mask DORE) for sparse image reconstruction of objects with known contour. The measurements follow a noisy underdetermined linear model common in the compressive sampling literature. Assuming that the contour of the object that we wish to reconstruct i…
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
48 results for “mask reconstruction”
Mask-reconstruction pretraining helps in downstream tasks by capturing more semantic features.
problem How mask-reconstruction pretraining helps in downstream tasks and why it surpasses supervised learning.
method Theoretical analysis and experimental validation of mask-reconstruction pretraining (MRP) on auto-encoders.
result MRP provably captures more semantic features than supervised learning, leading to better performance in downstream tasks.
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.
This paper proposes an end-to-end approach for single-channel speaker-independent multi-speaker speech separation, where time-frequency (T-F) masking, the short-time Fourier transform (STFT), and its inverse are represented as layers within a deep network. Previous approaches, rather than computing a loss on the recons…
A deep generative model improves imputation of MNAR data by treating missing and complete data equally.
problem Missing Not At Random (MNAR) data in analysis.
method A generative model-specific joint probability decomposition method (conjunction model) and a deep generative imputation model (GNR).
result GNR surpasses state-of-the-art MNAR baselines with significant margins in RMSE and better mask reconstruction.
Expands MLM by masking token positions, improving performance and convergence.
problem Improving language model performance and convergence.
method Masking token positions along with [MASK] tokens, using a fully connected classifier stage.
result Shows .3% improvement and 50% faster convergence for BERT Base with position masking.
Deep learning based speech enhancement and source separation systems have recently reached unprecedented levels of quality, to the point that performance is reaching a new ceiling. Most systems rely on estimating the magnitude of a target source by estimating a real-valued mask to be applied to a time-frequency represe…
A novel method for feature selection using a reparameterized logitNormal distribution.
problem Feature selection for reconstruction in high-dimensional data.
method Introducing a reparameterization of the logitNormal distribution to address differentiability and covariance issues.
result The method provides an effective exploration scheme and efficient feature selection for reconstruction.
ST-MTM: Masked Time Series Modeling with Seasonal-Trend Decomposition for Time Series Forecastingcs.LG
ST-MTM models complex time series by decomposing and masking seasonal and trend components.
problem Forecasting complex time series with intricate temporal variations.
method Seasonal-Trend Decomposition with Masking and Contrastive Learning.
result ST-MTM achieves superior forecasting performance compared to existing methods.
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.
LightSecAgg reduces secure aggregation complexity in FL.
problem Complexity in secure aggregation protocols for FL systems.
method One-shot aggregate-mask reconstruction via mask encoding/decoding.
result Significantly reduces overhead for resiliency against dropped users.
Proposes a new approach to time series representation learning by embedding patches independently.
problem Capturing dependencies between time series patches is not optimal for representation learning.
method 1) Patch reconstruction task, 2) Patch-wise MLP, 3) Complementary contrastive learning.
result Improves time series forecasting and classification performance compared to state-of-the-art models.
In compressed sensing MRI (CS-MRI), k-space measurements are under-sampled to achieve accelerated scan times. CS-MRI presents two fundamental problems: (1) where to sample and (2) how to reconstruct an under-sampled scan. In this paper, we tackle both problems simultaneously for the specific case of 2D Cartesian sampli…
Enhanced Sampling Scheme improves masked generative modeling.
problem Limitations of existing sampling schemes in masked non-autoregressive generative modeling.
method ESS consists of three stages: Naive Iterative Decoding, Critical Reverse Sampling, and Critical Resampling.
result ESS achieves significant performance gains in unconditional and class-conditional sampling.
We consider the effect of structure-agnostic and structure-dependent masking schemes when training a universal marginaliser (arXiv:1711.00695) in order to learn conditional distributions of the form , where is a given random variable and is some arbitrary sub…
MoCA uses a novel autoencoder to analyze multi-modal health data.
problem Challenges in analyzing continuous multi-modal health data from wearable devices.
method Proposes MoCA, a self-supervised learning framework combining transformer and masked autoencoder methods.
result Demonstrates strong performance boosts across reconstruction and classification tasks.
StrTransformer recovers sources without labels by optimizing latent matrices and enforcing structural constraints.
problem Unsupervised blind source recovery in signal processing.
method Source-wise structured Transformer framework with latent source matrix optimization, structural regularization, and branch-specific weights.
result StrTransformer learns distinct temporal-scale structures and recovers source-aligned latent trajectories.
We consider inpainting in an unsupervised setting where there is neither access to paired nor unpaired training data. The only available information is provided by the uncomplete observations and the inpainting process statistics. In this context, an observation should give rise to several plausible reconstructions whi…
MARGE learns to reconstruct text by paraphrasing, achieving strong performance across multiple tasks.
problem Training sequence-to-sequence models with limited supervision.
method Unsupervised multi-lingual multi-document paraphrasing objective.
result Strong zero-shot performance on document translation and various tasks in multiple languages.
There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our method masks the autoencoder's parameters to respect autoregressive constraints: ea…
A hybrid Convolutional VAE predicts crypto volatility surfaces, outperforming single-symbol approaches.
problem Predicting crypto volatility surfaces
method Convolutional VAE with hybrid predictor
result Model achieves 0.94-1.56 vol-point RMSE across BTC and ETH markets
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.
A new method uses conformal prediction to create reliable confidence masks for image super-resolution.
problem Uncertainty quantification in image super-resolution using generative models.
method Conformal prediction techniques applied to a confidence mask for reliable uncertainty communication.
result Strong theoretical guarantees and empirical solid performance in image super-resolution.
PMI-Masking improves MLM pretraining by masking correlated spans efficiently.
problem Uniform token masking leads to inefficient and suboptimal performance in MLMs.
method PMI-Masking uses Pointwise Mutual Information to mask n-grams with high collocation.
result PMI-Masking reaches half the training time and improves performance.
PRAE identifies outliers and reconstructs inliers in autoencoders.
problem Accurately identifying anomalies in data.
method Probabilistic Robust AutoEncoder (PRAE) approach.
result PRAE effectively removes outliers and reconstructs inliers.
We propose a new STAcked and Reconstructed Graph Convolutional Networks (STAR-GCN) architecture to learn node representations for boosting the performance in recommender systems, especially in the cold start scenario. STAR-GCN employs a stack of GCN encoder-decoders combined with intermediate supervision to improve the…
SiamJEPA uses Siamese student encoders to improve JEPA-based representation learning.
problem Improving self-supervised representation learning in JEPA models.
method Proposes SiamJEPA with masked Siamese student encoders and EMA teacher network.
result Siamese student encoders improve representation separability and learning speed.
Compressive sensing (CS) has been studied and applied in structural health monitoring for wireless data acquisition and transmission, structural modal identification, and spare damage identification. The key issue in CS is finding the optimal solution for sparse optimization. In the past years, many algorithms have bee…
Inpainting the Neural Picture: Inferring Unrecorded Brain Area Dynamics from Multi-Animal Datasetsq-bio.NC
NeuroPaint infers missing brain area dynamics from multi-animal datasets.
problem Leveraging multi-animal datasets to understand interactions between brain areas.
method Masked autoencoding approach trained across animals with partial observations.
result Models can successfully reconstruct dynamics of unrecorded brain areas.
T-JEPA learns tabular data representations without augmentations, outperforming traditional methods.
problem Challenges in self-supervised learning for tabular data due to lack of data augmentations.
method T-JEPA uses a Joint Embedding Predictive Architecture (JEPA) to predict latent representations of different subsets of features within the same sample.
result Significant improvement in classification and regression tasks, outperforming traditional methods.
This paper extends the recently proposed and theoretically justified iterative thresholding and residual means algorithm ITKrM to learning dicionaries from incomplete/masked training data (ITKrMM). It further adapts the algorithm to the presence of a low rank component in the data and provides a strategy for recove…
New method reduces diffusion model function evaluations for discrete data.
problem High computational burden in generating samples from masked diffusion models.
method Modified causal attention mask and speculative sampling mechanism for non-factorized predictions.
result Achieved ~2x reduction in required network forward passes.
Proposes a proportional masking strategy for better tabular data imputation.
problem Heterogeneity of tabular data disrupts uniform random masking in MAEs.
method Computes missingness statistics, generates proportional masks, uses MLP token mixing.
result Proportional masking preserves missingness distribution, improves imputation performance.
Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of clean speech. To improve speech enhancement performance, we tackle the phase estima…
New analysis reveals masked self-supervised learning's effectiveness in extracting data structure.
problem Analyzing masked self-supervised learning in high-dimensional data.
method Developed precise high-dimensional analysis of masked modeling objectives.
result Identified phase transitions and structured regimes for masked self-supervised learning.
The recently proposed mask-predict decoding algorithm has narrowed the performance gap between semi-autoregressive machine translation models and the traditional left-to-right approach. We introduce a new training method for conditional masked language models, SMART, which mimics the semi-autoregressive behavior of mas…
This paper connects masked pre-training to Bayesian model selection.
problem Understanding the success of masked pre-training and its generalization.
method The paper shows masked pre-training corresponds to maximizing the marginal likelihood.
result Masked pre-training with a suitable scoring function maximizes the marginal likelihood.
Optimizes pruning masks for neural networks using probabilistic fine-tuning and PAC-Bayes bounds.
problem Improving neural network performance through adaptive pruning of weights.
method Optimizes stochastic pruning masks by minimizing expected loss, considering data-adaptive regularization and feature alignment.
result Probabilistic fine-tuning leads to improved test error over baseline methods in neural networks.
We consider the problem of selecting an optimal mask for an image manifold, i.e., choosing a subset of the pixels of the image that preserves the manifold's geometric structure present in the original data. Such masking implements a form of compressive sensing through emerging imaging sensor platforms for which the pow…
Recent object detectors use four-coordinate bounding box (bbox) regression to predict object locations. Providing additional information indicating the object positions and coordinates will improve detection performance. Thus, we propose two types of masks: a bbox mask and a bounding shape (bshape) mask, to represent t…
SSMBA generates synthetic data to improve robustness in natural language tasks.
problem Improving out-of-domain generalization of models trained on natural language data.
method SSMBA uses corruption and reconstruction functions to generate synthetic data points on the manifold assumption.
result SSMBA consistently outperforms existing methods on robustness benchmarks across multiple tasks and datasets.
EarnMore uses masked stock representations to train RL agents for customizable stock pools efficiently.
problem Training RL agents for customizable stock pools (CSPs) is computationally expensive and unstable.
method EarnMore introduces a mechanism to mask out stocks outside the target pool, learns meaningful stock representations, and uses a re-weighting mechanism to focus on favorable stocks.
result EarnMore significantly outperforms state-of-the-art baselines in profit metrics with over 40% improvement.
The paper investigates the effects of invalid action masking in policy gradient algorithms.
problem Invalid actions in policy gradient algorithms can lead to suboptimal performance.
method The paper provides theoretical justification and empirical demonstrations of the importance of invalid action masking.
result Invalid action masking is crucial as the number of invalid actions increases.
Diffusion Autoencoders with Perceivers for Long, Irregular and Multimodal Astronomical Sequencesstat.ML
daep learns from irregular, multimodal astronomical data.
problem Learning from irregular, multimodal astronomical sequences.
method Diffusion Autoencoder with Perceivers (daep) tokenizes, compresses, and reconstructs data.
result daep outperforms VAE and maep baselines in reconstruction and fine-scale structure preservation.
Improved YOLOv5 model detects mask-wearing with enhanced accuracy.
problem Detecting mask-wearing in high traffic public places.
method Improved YOLOv5l with Multi-Head Attentional Self-Convolution, Swin Transformer Block, I-CBAM module, and enhanced feature fusion.
result 1.1% improvement in mAP(0.5) and 1.3% improvement in mAP(0.5:0.95) compared to YOLOv5l.
Simplified masked diffusion models improve discrete data generation.
problem Complex model formulations and unclear relationships hinder discrete data generative modeling.
method Developed a simple and general framework for masked diffusion models.
result Models trained on OpenWebText surpass prior diffusion language models and outperform autoregressive models.
Language models trained on chess board states outperform those on moves, even with causal masking.
problem Applying causal masking to spatial data for training unimodal language models.
method Trained bidirectional and causal self-attention models on both spatial (board-based) and sequential (move-based) chess data.
result Models trained on spatial board states achieve stronger playing strength than those trained on sequential data, even with causal masking.
LLMs can memorize economic data and recall exact values before their training cutoff.
problem Evaluating the trustworthiness of LLMs' economic forecasts during their training period.
method Demonstrated through counterfactual forecasting and analysis of LLMs' recall ability.
result LLMs have memorized economic and financial data, leading to recall-level accuracy before their knowledge cutoff.