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

15294458 · Jun 202019922001200920172026
48 results for masked pre-training

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.

In this contribution, we present a novel approach for segmenting laser radar (lidar) imagery into geometric time-height cloud locations with a fully convolutional network (FCN). We describe a semi-supervised learning method to train the FCN by: pre-training the classification layers of the FCN with image-level annotati…

2018-05-02abs ↗pdf ↗

AaSP improves audio self-supervised learning by addressing aliasing issues.

problem Alias issues in audio spectrogram transformers.
method AaSP combines aliasing-aware patch representation, teacher-student masked modeling, cross-attention predictor, and contrastive regularization.
result AaSP learns more stable representations that integrate high-frequency cues.

Neural network interpretability is a vital component for applications across a wide variety of domains. In such cases it is often useful to analyze a network which has already been trained for its specific purpose. In this work, we develop a method to produce explanation masks for pre-trained networks. The mask localiz…

2019-11-15abs ↗pdf ↗

Improved sentiment analysis in Korean finance using masked PLMs.

problem Fine-grained sentiment analysis in non-English finance literature is lacking due to limited annotated data.
method Developed KorFinASC dataset and applied TGT-Masking to PLMs to remove non-stationary knowledge.
result Improved classification accuracy by 22.63% on KorFinASC.

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.

We present an unsupervised training approach for a neural network-based mask estimator in an acoustic beamforming application. The network is trained to maximize a likelihood criterion derived from a spatial mixture model of the observations. It is trained from scratch without requiring any parallel data consisting of …

2019-04-02abs ↗pdf ↗

DOS improves language model generation by considering inter-token dependencies.

problem Lack of sequence-level information and inter-token dependencies in existing decoding strategies.
method Dependency-Oriented Sampler (DOS) that uses attention matrices to approximate inter-token dependencies.
result DOS consistently achieves superior performance on code generation and mathematical reasoning tasks.

New analysis shows diverse classes in pre-training boost NLP performance.

problem Improving sample efficiency in downstream NLP tasks.
method Proved that diverse classes in pre-training lead to better performance, using a large last linear layer singular value.
result Transfer learning excess risk improves with large ildeν ildeν and $O\left(\frac{1}{ ildeν \sqrt{n}} ight)$ rate.

Unsupervised pre-training improves model generalization, but lacks theoretical understanding.

problem Lack of theoretical understanding of unsupervised pre-training's impact on model generalization.
method Introduces a novel theoretical framework to analyze and enhance generalization.
result Enhances understanding of unsupervised pre-training and fine-tuning, proposing a new regularization method.

Novel bio-inspired masking for robust speech emotion recognition.

problem Noise degradation in speech emotion recognition.
method Cochlear cepstrogram-based contrastive learning with temporal and frequency masking.
result Improved speech emotion recognition performance on K-EmoCon benchmark.

This paper improves anomaly detection in lane rendering images for safer navigation.

problem Anomalies in lane rendering images can mislead drivers, posing safety risks.
method Proposes a four-phase pipeline using Transformer models, self-supervised pre-training, and fine-tuning.
result The pipeline enhances detection accuracy and reduces training time.

New findings show BERT subnetworks can train independently and transfer to various tasks.

problem Finding smaller subnetworks that can train independently and transfer to other tasks.
method Examined pre-trained BERT models for subnetworks that can train independently and transfer to various downstream tasks.
result Found subnetworks at 40% to 90% sparsity that can train independently and transfer to various tasks.

RGI improves robustness of GAN-inversion for image restoration and anomaly detection.

problem Robustness of GAN-inversion to unknown gross corruptions.
method Proposes RGI and R-RGI methods with provable robustness guarantees.
result Restored images and corrupted region masks converge to ground truth under mild assumptions.

We Microsoft Research Asia made submissions to 11 language directions in the WMT19 news translation tasks. We won the first place for 8 of the 11 directions and the second place for the other three. Our basic systems are built on Transformer, back translation and knowledge distillation. We integrate several of our rece…

2019-11-07abs ↗pdf ↗

Paper proposes a unified time series forecasting model with adaptive transfer.

problem General forecasting models for diverse time series data.
method Unified representations through Decomposed Frequency Learning and adaptive domain-specific features via Time Series Register.
result State-of-the-art forecasting performance on seven real-world benchmarks.

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.

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.

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.

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…

2020-01-23abs ↗pdf ↗

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…

2016-06-15abs ↗pdf ↗

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.

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.

Masking diffusion outperforms other discrete diffusion models by incorporating jump times into the model.

problem Improving the performance of discrete diffusion models.
method Conditioning on the jump schedule of discrete Markov processes.
result Schedule-conditioned discrete diffusion (SCUD) models outperform classical and masking diffusion models.

The ConditionaL Neural Networks (CLNN) and the Masked ConditionaL Neural Networks (MCLNN) exploit the nature of multi-dimensional temporal signals. The CLNN captures the conditional temporal influence between the frames in a window and the mask in the MCLNN enforces a systematic sparseness that follows a filterbank-lik…

2018-02-18abs ↗pdf ↗

Unified framework for ICL in causal and masked models.

problem Understanding ICL in masked language models and comparing it to causal models.
method Developed a statistical learning framework representing context by empirical measure and predicting using context and query.
result Upper bounds for masked and autoregressive objectives under Wasserstein-type regularity conditions.

VLSI mask optimization is one of the most critical stages in manufacturability aware design, which is costly due to the complicated mask optimization and lithography simulation. Recent researches have shown prominent advantages of machine learning techniques dealing with complicated and big data problems, which bring p…

2019-12-16abs ↗pdf ↗