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.

169,291 papers · 148 categories

Trend · papers per month

4018011,2021,602 · Jun 202019922001200920182026
48 results for Deep Rendering Mixture Model

Unified framework for semi-supervised learning using DRMM.

problem Efficiently using both labeled and unlabeled data in semi-supervised learning.
method Developed an EM algorithm for DRMM to learn from labeled and unlabeled data.
result Reported state-of-the-art performance on MNIST and SVHN.

A new probabilistic framework improves deep learning performance.

problem Improving deep learning models and understanding their limitations.
method Developed a probabilistic framework based on DRMM, a generative model capturing latent variables.
result DRMM outperforms DCNs in classification tasks, achieving state-of-the-art results.

A new model combines normalizing flows with mixture components for better density estimation.

problem Lack of explicit probability density functions in deep generative models.
method Variational mixture of normalizing flows, using variational inference and neural network parameters.
result The model can perform density estimation, semi-supervised learning, and clustering.

Paper addresses causal inference and clustering for mixtures of ANMs.

problem Causal inference from heterogeneous sources with multiple ANMs.
method Generalized ANM to a mixture model, GPPOM with independence enforcement.
result Effective causal inference and clustering for mixtures of ANMs.

The paper optimizes hyperplanes for binary classification in high-dimensional data with latent Gaussian mixtures.

problem Binary classification in high-dimensional data with latent Gaussian mixtures.
method Generalized least squares estimator for estimating the direction of the optimal separating hyperplane. Simple correction for intercept estimation.
result The procedure is minimax optimal in many scenarios and can retain the interpolation property.

A new metric for detecting out-of-distribution samples using neural rendering models.

problem Difficulty in detecting out-of-distribution samples with existing deep generative models.
method Derive metrics for out-of-distribution detection using a neural rendering model.
result Lower likelihood of latent variables is assigned to out-of-distribution samples.

Improves synthetic data for deep model training and adaptation.

problem Evaluating and improving synthetic data for deep learning models.
method Proposes a novel learned synthesis technique using generative models for shading and rendering, and uses an ensemble of models to generate datasets.
result Improves classifier performance on real data compared to state-of-the-art methods.

AR-GANs learn depth and DoF from unlabeled images using aperture rendering and focus cues.

problem Learning depth and DoF from unlabeled natural images with diverse viewpoints and shapes.
method Aperture rendering and focus cues to learn depth and DoF from unlabeled images.
result AR-GANs effectively learn depth and DoF from various datasets, including flower, bird, and face images.

Percival uses deep learning to block ads in real-time, minimizing performance impact.

problem Real-time ad blocking in browsers with minimal performance overhead.
method Deep learning for image classification integrated into browser's rendering pipeline.
result Percival achieves 96.76% accuracy in blocking ads, comparable to block lists.

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.

Efficiently marginalizes over Gaussian Process kernels for better model flexibility and uncertainty.

problem Inefficient marginalization over Gaussian Process kernels for large datasets.
method Bayesian Quadrature scheme with maximum mean discrepancies and invariances between Spectral Mixture kernels.
result Achieves more accurate predictions and better calibrated uncertainty than state-of-the-art baselines.

VMoER improves uncertainty quantification in MoE layers for scalable foundation models.

problem Uncertainty quantification in large-scale models like MoE layers.
method Structured Bayesian approach with amortized variational inference over routing logits and temperature parameter inference.
result Improves routing stability, reduces calibration error, and increases AUROC by 12%.

Proposes a new prior for deep generative models to capture latent properties.

problem Complex non-linear relationships between data and latent properties.
method Factorial mixture prior with Gaussian mixture models for quantization.
result Empirically evaluated method for learning discrete properties in unsupervised or semi-supervised settings.

Deep neural networks converge to Gaussian mixtures as layer width increases.

problem Understanding the distribution of outputs from deep neural networks.
method Proof and experiments with a simple model showing the convergence of neural network outputs to Gaussian mixtures.
result Neural networks converge to Gaussian mixtures as the width of the last hidden layer increases.

The paper uses differentiable rendering to generate semantic counterexamples for improving neural network robustness.

problem Neural networks' brittleness to semantic transformations.
method Differentiable rendering for generating realistic images that model semantic changes, combined with adversarial machine learning attacks.
result Semantic counterexamples improve generalization, robustness, and transferability of neural networks.

New adversarial training enhances malware detectors against various attacks.

problem Vulnerability of malware detectors to evasion attacks.
method Proposes a mixture of attacks and adversarial training to improve deep neural networks.
result Significantly enhances robustness of deep neural networks against a wide range of attacks.

Deep learning representations of GAN data are like Gaussian mixtures, according to this study.

problem Understanding the statistical nature of deep learning representations of GAN-generated data.
method Using Random Matrix Theory, the study shows that DL representations of GAN data are concentrated random vectors that behave like Gaussian mixtures.
result Deep learning representations of GAN data can be fully described by their first two statistical moments.

The paper introduces a new method for multivariate density estimation using deep neural mixture models.

problem Multivariate density estimation is a fundamental but underexplored task in machine learning.
method The paper extends Neural Mixture Densities (NMMs) to multivariate Deep Neural Mixture Models (DNMMs) using maximum-likelihood algorithm.
result The DNMMs can model any probability density function to any degree of precision and outperform traditional statistical estimation techniques.

New deep Cox mixture model improves survival analysis performance.

problem Challenges in survival analysis due to censoring and healthcare applications.
method Learning mixtures of Cox regressions with deep neural networks for hazard ratios and non-parametric baseline hazard.
result Our approach outperforms classical and modern survival analysis methods, especially in minority demographics.

A new model DKMPP integrates covariates and uses an integration-free method for spatio-temporal point processes.

problem Training intractable deep spatio-temporal point processes with multimodal covariates.
method DKMPP uses a deep kernel to model complex relationships and an integration-free score matching method.
result DKMPP and score-based estimators outperform baseline models in spatio-temporal point processes.

Paper uses a mix of deep and kernel learning to personalize sepsis treatment.

problem Managing sepsis in ICU patients due to individual variability.
method A mixture-of-experts framework combining kernel-based and deep reinforcement learning.
result The mixture-based approach outperforms individual methods on a large sepsis patient cohort.

Deep learning predicts semitransparent pigment mixtures for novice painters.

problem Support novice painters in learning color mixing.
method Built a watercolor dataset with transmittance and reflectance data. Used a deep neural network to train a model for predicting pigment mixtures.
result Trained model accurately predicts semitransparent pigment mixtures.

ECM algorithm estimates graphical models efficiently in high dimensions.

problem Bayesian graphical models in high-dimensional settings are computationally infeasible.
method ECM algorithm using mixture priors for posterior exploration.
result ECM approach enables fast posterior exploration and incorporates multiple sources of information.

Proposes deep mixture models for probabilistic price movement forecasting in high-frequency trading.

problem Probabilistic forecasting of price movements in high-frequency trading.
method Deep recurrent neural networks with probabilistic mixture models.
result Outperforms benchmark models in both metric-based and simulated trading scenarios.

SPIRAL uses reinforcement learning to generate programs for images.

problem Weak inductive biases in deep learning models lead to inefficiencies.
method Adversarial training with reinforcement learning to generate programs.
result Using the discriminator's output as a reward signal is key to progress.

Paper presents a reparameterized DP-DLGMM for clustering.

problem Non-parametric DP priors in DLGMM are hard to couple with variational inference.
method Closed-form updates for DP-DLGMM's variational posterior.
result Model generates realistic samples and performs competitively in semi-supervised settings.

Deep neural networks classify unbounded Gaussian mixture data without dimensionality issues.

problem Binary classification of unbounded Gaussian mixture data.
method Deep ReLU neural networks with non-asymptotic upper bounds and convergence rates.
result Deep ReLU networks can classify unbounded Gaussian mixture data without dimensionality constraints.

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.

Efficiently synthesizes atmospheric cloud images using neural networks and Monte Carlo integration.

problem Rendering atmospheric clouds, especially their characteristic silverlining and whiteness, is challenging.
method Pre-learning the radiant flux distribution from cloud exemplars and using a deep neural network to predict radiance.
result The method synthesizes clouds nearly indistinguishable from reference solutions in seconds.