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

78156234312 · Jun 202019922001200920182026
48 results for unsupervised regularization

The paper identifies saddlepoints in unsupervised auto-encoding neural nets.

problem The risk landscape of unsupervised least squares in auto-encoding neural nets.
method Established an equivalence between unsupervised least squares and principal manifolds, discussed regularization strategies for auto-encoders.
result All non-trivial critical points in auto-encoding are saddlepoints, which are degenerate in overcomplete auto-encoding.

The paper introduces a scalable unsupervised learning framework to improve deep neural networks.

problem Improving deep neural networks' performance and generalization in unsupervised settings.
method A scalable unsupervised regularization framework that constrains hypothesis space to non-trivial piecewise constant functions.
result The framework leads to a factually confident and smooth discriminative model, achieving state-of-the-art clustering results and generalization on both synthetic and real data.

Proposes RN for unsupervised attention in neural networks.

problem Limited, imbalanced, and non-stationary input distributions in various tasks.
method Inspired by neuronal adaptation, RN uses MDL principle and universal code length for incremental layer-wise computation.
result Outperforms existing normalization methods across diverse tasks.

Proposes a novel unsupervised clustering method using pseudo labels and graph-based regularization.

problem Clustering unlabeled data without explicit supervision.
method Randomly assigns pseudo labels, trains a neural network with ACOL, and uses GAR terms for propagation of latent information.
result Obtains state-of-the-art performance on MNIST, SVHN, and USPS datasets.

Proposes a regularization method for unsupervised domain adaptation that aligns predictions with target data's top singular vectors.

problem Domain adaptation challenges in high joint error scenarios.
method Regularizes classifier to align with unsupervised target data guided by label alignment property (LAP).
result The method improves performance in MNIST-USPS domain adaptation and cross-lingual sentiment analysis.

A new method for feature selection in high-dimensional data.

problem Dealing with noise and high-dimensional data in unsupervised feature selection.
method Sparse PCA via l2,pl_{2,p}-norm regularization, combined with an efficient optimization algorithm.
result The proposed method effectively selects features from real-world data sets.

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.

A novel unsupervised feature selection method using subspace clustering and self-expressive model.

problem Feature selection for large datasets with minimal labeling effort.
method Subspace clustering with adaptive representation learning and regularized regression.
result The method effectively captures sample similarities and discriminative information.

Graph convolutional networks fail to use eigenvectors beyond the first, unlike spectral embedding.

problem Understanding when graph convolutional networks fail compared to spectral embedding.
method Presented a simple generative model to illustrate failure.
result Graph convolutional networks fail to use eigenvectors beyond the first in certain graphs.

Unsupervised algorithm parses CSG images into CFG without pretraining.

problem Sparse reward problem in unsupervised program synthesis for images.
method Grammar-encoded tree LSTM, entropy regularization, sampling without replacement.
result Recover meaningful programs in large search spaces (up to 3.8imes10283.8 imes 10^{28}).

BRDAD uses bagging and regularization to improve anomaly detection without labeled data.

problem Anomaly detection in unlabeled data with sensitivity to kk-nearest neighbors.
method Bagged regularized kk-distances (BRDAD) for anomaly detection, converting to convex optimization.
result BRDAD addresses sensitivity to hyperparameter choice and improves performance on large datasets.

A new method uncovers intrinsic data structures for unsupervised domain adaptation.

problem Learning domain-aligned features can damage intrinsic target discrimination.
method Structurally Regularized Deep Clustering (H-SRDC) integrating structural source regularization.
result H-SRDC outperforms existing methods in image classification and semantic segmentation.

A new method for neural networks adapts to different domains without labeled data.

problem Adapting neural networks to new domains without labeled data.
method Metric-based regularization to maximize similarity of domain-specific activation distributions by aligning moments.
result The method achieves higher classification accuracies than existing approaches.

Unsupervised DA method using hyper-graph matching.

problem Discrepancy between source and target data distributions.
method Class-regularized hyper-graph matching with first-, second-, and third-order similarities.
result Improved performance on target domain compared to state-of-the-art methods.

The paper proposes a method to adapt models from source to target domains by calibrating their predictive uncertainties.

problem Inferring class labels for unlabeled target domain given a related labeled source dataset.
method The approach involves calibrating predictive uncertainties quantified as Renyi entropy, using variational Bayes learning and sample variance regularization.
result The proposed method effectively adapts models across three domain-adaptation tasks.

TAMD prevents degeneracy in finite mixtures, offering strong guarantees but modest practical improvements.

problem Degeneracy in maximum likelihood estimation of finite mixtures.
method Transcendental regularization with analytic barrier functions.
result Strong theoretical guarantees (identifiability, consistency, robustness) but modest practical improvements.

Generates synthetic data for benchmarking unsupervised outlier detection.

problem Difficulty in benchmarking unsupervised outlier detection due to rare and varied outliers in real data.
method Proposes a generic process to generate synthetic data with insightful characteristics.
result Demonstrates practicality of the generic process through a benchmark with state-of-the-art detection methods.

Autoencoders improve unsupervised and semi-supervised learning with new generalization bounds.

problem Lack of theoretical understanding of autoencoder generalization in unsupervised and semi-supervised learning.
method Utilized recent advances in deep learning theory and a novel reconstruction loss to provide generalization bounds.
result First theoretical generalization bounds for autoencoders in unsupervised and semi-supervised learning.

A new method assesses similarity in bipartite data using reflexive regular equivalence.

problem Challenges in clustering bipartite data, especially in validating co-similarity assumptions.
method Uses spectral properties of a bipartite adjacency matrix and reflexive regular equivalence to estimate similarity.
result The method outperforms other measures in correctly classifying genes in real-world data.

Improves unsupervised clustering using deep generative models with a Gaussian mixture prior.

problem Cluster degeneracy in variational autoencoders (VAEs).
method Applying a heuristic called minimum information constraint to mitigate over-regularization in a VAE with a Gaussian mixture prior.
result Demonstrates improved performance in unsupervised clustering on synthetic and real datasets.

Unified analysis of self-training for deep networks on unlabeled data.

problem Theoretical understanding of self-training for deep networks on unlabeled data.
method Unified theoretical analysis using expansion assumption and input-consistency regularization.
result Proves high accuracy of minimizers of population objectives based on self-training and input-consistency regularization.

DMRL improves UDA by mixing source and target samples and enriching latent space structures.

problem Lack of class-aware information and insufficient samples for domain-invariant feature extraction.
method Dual Mixup Regularized Learning (DMRL) that conducts category and domain mixup regularizations.
result DMRL achieves state-of-the-art performance on domain adaptation benchmarks.

MONet learns to decompose scenes into meaningful components without supervision.

problem Learning meaningful scene decompositions without labeled data.
method MONet combines a VAE and recurrent attention network to learn decompositions of 3D scenes.
result MONet can learn to represent 3D scenes into meaningful components like objects and background.

Improves unsupervised domain adaptation methods by aligning class conditional distributions.

problem Domain shift between source and target domains makes supervised learning models fail to generalize.
method Co-regularized domain alignment, creating multiple feature spaces and aligning them individually while encouraging agreement across class predictions.
result Significant performance improvements on domain adaptation benchmarks.

Unified taxonomy for graph representation learning.

problem Lack of unified understanding and integration of graph representation learning methods.
method Proposes a Graph Encoder Decoder Model (GRAPHEDM) to unify graph neural networks, network embedding, and graph regularization.
result Unified taxonomy and Graph Encoder Decoder Model (GRAPHEDM) for graph representation learning.

Improves deep learning with less labeled data using unsupervised projection.

problem Lack of labeled data for deep learning models.
method Modified unsupervised discriminant projection as a regularization term for semi-supervised learning.
result Proposes an algorithm that enhances classification performance with minimal labeled data.

Proposes TFDF to learn transferable and discriminative features for unsupervised domain adaptation.

problem Difficult to induce supervised classifier without labeled data in unsupervised domain adaptation.
method TFDF optimizes transferability and discriminability by aligning distributions and minimizing class confusion.
result TFDF achieves better performance on real-world datasets compared to existing methods.

New method clusters multi-view data by squeezing hybrid knowledge.

problem Removal of redundant information and fusion of multi-view features.
method Low-rank subspace multi-view clustering with adaptive graph regularization.
result Our method outperforms state-of-the-art algorithms on multi-view benchmarks.

Improved unsupervised word translation using adversarial autoencoder with cycle consistency and input reconstruction.

problem Challenging language pairs and lack of parallel data for unsupervised word translation.
method Adversarial autoencoder with cycle consistency and input reconstruction regularization.
result More stable and better performance than recent approaches.

Unsupervised model learns word and context embeddings from character sequences.

problem Learning meaningful word and context embeddings from unlabeled data.
method Character-aware neural architecture that jointly learns word and context embeddings.
result Compact encoders achieve high performance in downstream tasks.

A novel unsupervised feature learning architecture using multi-clustering integration and MIRBM.

problem Feature learning without labeled data.
method Multi-clustering integration module with MIRBM, using K-means, affinity propagation, and spectral clustering.
result The proposed architecture outperforms state-of-the-art methods in clustering tasks.

A new method learns meaningful distances between samples using optimal transport.

problem Learning meaningful distances between samples in datasets without labeled data.
method Computes OT distances between samples and features using singular vectors of a function mapping ground metrics to OT distances.
result Wasserstein Singular Vectors provide a scalable solution for unsupervised ground metric learning.

Optimizes PnL using linear signals in quantitative finance.

problem Maximizing profit and loss in financial trading.
method Unsupervised machine learning approach that maximizes Sharpe Ratio through linear relationships and parameter optimization.
result Empirical validation and effectiveness of the model on U.S. Treasury ETF.

Paper proposes unsupervised knowledge graph alignment with adversarial learning.

problem Aligning knowledge graphs from different sources or languages without large amounts of aligned triplets.
method Adversarial learning framework to align entity and relation embeddings, with mutual information regularization.
result Framework effectively aligns knowledge graphs in unsupervised and weakly-supervised settings.

A new method improves graph-based learning for high-dimensional data.

problem Inconsistent high-dimensional learning efficiency of semi-supervised graph regularization.
method Introducing a novel regularization approach involving centering operation.
result Empirical results show improved performance over spectral clustering.

Improves unsupervised domain adaptation by mixing source and target domains.

problem Improves unsupervised domain adaptation by mixing source and target domains.
method Enforces training constraints across domains using mixup formulation and feature-level consistency regularizer.
result Significantly improves state-of-the-art performance on image classification and human activity recognition tasks.