Probabilistic deep learning uses neural networks and models to handle uncertainty.
problem Handling uncertainty in deep learning models.
method Two approaches: probabilistic neural networks and deep probabilistic models.
result TensorFlow Probability library supports both approaches.
Probabilistic models with deep neural networks now handle large data sets.
problem Historical constraints on probabilistic modeling.
method Variational inference, stochastic gradient descent, distributed computation.
result Probabilistic models can now handle large data sets and complex relationships.
InferPy simplifies probabilistic modeling with deep neural networks in Python.
problem Complex probabilistic models with deep neural networks.
method User-friendly API for defining, learning, and evaluating models.
result Compact and simple way to define general hierarchical probabilistic models.
Survey on probabilistic models and variational inference in deep RL.
problem Understanding and applying probabilistic models and variational inference in deep reinforcement learning.
method Detailed derivations and comparisons of recent advances in deep reinforcement learning.
result Comprehensive tutorial on probabilistic graphical models and variational inference in deep reinforcement learning.
ZhuSuan is a Python library for Bayesian deep learning.
problem Bayesian deep learning for probabilistic models.
method Bayesian inference, probabilistic programming, Tensorflow.
result Supports various probabilistic models including hierarchical and deep generative models.
D2PCCA integrates deep learning and probabilistic modeling for nonlinear dynamical systems.
problem Analyzing nonlinear dynamical systems with probabilistic understanding.
method Combines deep learning and probabilistic modeling, using KL annealing and normalizing flows.
result Captures latent dynamics in sequential datasets with improved convergence and flexibility.
Pyro enables scalable AI models using probabilistic programming.
problem Developing complex probabilistic models for large datasets.
method Stochastic variational inference, PyTorch, Poutine.
result Pyro supports scalable AI models with high-dimensional data.
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.
Proposes a deep probabilistic multi-view model for multi-view learning.
problem Learning from multiple related views with shared latent structure.
method Probabilistic Canonical Correlation Analysis (CCA) in latent space, deep generative networks, variational inference.
result Efficient variational inference approximates posterior distributions of latent multi-view layer.
Paper proposes using backpropagation for probabilistic program learning.
problem Difficult to learn probabilistic models from data.
method Learning parameters of a probabilistic program using backpropagation.
result Trains probabilistic models similar to neural networks.
CSPNs combine SPNs and neural networks for tractable probabilistic modeling.
problem Combining tractable SPNs with neural networks' expressiveness.
method Developed CSPNs by conditioning SPN parameters on inputs and learning structure from data.
result CSPNs outperform other models in multilabel image classification.
Deep models predict intraday electricity prices accurately.
problem Accurately forecasting intraday electricity prices.
method Two deep time series probabilistic models using ESNs with stochastic disturbances and copulas.
result Deep distributional models provide accurate short-term probabilistic price forecasts.
Stan models are compiled to generative languages and extended with new features.
problem Lack of direct support for variational inference and deep models in Stan.
method Comprehensive compilation scheme to convert Stan models to generative languages, and extension of Stan with new features.
result NumPyro backend yields a 2.3x speedup compared to Stan in geometric mean over 26 benchmarks.
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 novel deep probabilistic model for dynamic systems forecasting.
problem Probabilistic forecasting in dynamic systems.
method Combining deep generative models and state space models with recurrent neural networks and variational sequence models.
result Outperforms existing models in system identification benchmarks and real-world centrifugal compressor forecasting.
New method for efficient probabilistic deep state-space models.
problem Efficient inference for probabilistic deep state-space models.
method Deterministic inference algorithm for ProDSSM with neural network weights.
result Superior balance between predictive performance and computational budget.
This thesis improves deep sequence models by integrating probabilistic methods for uncertainty quantification.
problem Lack of uncertainty awareness in deep sequence models limits their deployment.
method Develops approximate Bayesian inference methods for Transformers and HiPPOs, leveraging inductive biases.
result Improves predictive and generative performance of deep sequence models by incorporating probabilistic structures.
Researchers propose better probabilistic models for deep learning.
problem Using cross-entropy loss for non-categorical data.
method Introducing continuous-categorical distribution and proposing probabilistic alternatives.
result Potential for outperformance in deep learning models with proper probabilistic treatment.
Deep state space model forecasts time series with uncertainty.
problem Probabilistic forecasting for risk management.
method Parameterized deep networks for non-linear models, recurrent neural nets for dependency, ARD network for exogenous variables.
result Accurate and sharp probabilistic forecasts with realistic uncertainty growth.
Deep models forecast epidemics with uncertainty quantification.
problem Accurate probabilistic forecasting of epidemics is challenging due to nonlinear temporal dependencies and spatial interactions.
method Deep spatiotemporal engression methods with geometric ergodicity and asymptotic stationarity.
result Proposed methods outperform benchmarks in point and probabilistic forecasting.
Deep neural operators learn complex probabilistic models efficiently.
problem Learning complex probabilistic models with global Lipschitz conditions.
method Deep neural-operator framework under global Lipschitz conditions.
result Explicit network-size bounds for universal approximation of probabilistic models.
A new probabilistic approach improves deep metric learning by considering image uncertainties and class-specific variances.
problem Proxy-based deep metric learning struggles with image uncertainties and class-specific structures.
method Introduces non-isotropic probabilistic proxy-based deep metric learning using directional von Mises-Fisher distributions.
result Improves generalization performance and competitive on standard benchmarks.
A generative model is developed for deep (multi-layered) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding efficient bottom-up (pretraining) and top-down (refinement) probabilistic learning. Experimental results demonstrate powerful capabilities of th…
CDEFs reduce model complexity and uncover time correlations.
problem Model complexity and data efficiency in probabilistic modeling.
method Builds on deep exponential families, ties weights for reduced parameters.
result CDEFs uncover time correlations with fewer parameters.
Improved deep probabilistic time series forecasting by learning error autocorrelation.
problem Simplification of time-independent error process and lack of serial correlation in existing models.
method Proposes a training method that incorporates error autocorrelation to enhance probabilistic forecasting accuracy.
result Improves predictive accuracy and uncertainty quantification across multiple datasets.
New probabilistic deep learning models using random SPNs are robust and interpretable.
problem Inference limitations in probabilistic deep learning models.
method Random Sum-Product Networks (RAT-SPNs) trained with deep learning techniques.
result RAT-SPNs yield comparable predictions to deep neural networks with interpretability and robustness.
A method for constraining dynamics in deep probabilistic models.
problem Tackling the challenge of parameter inference and monotonic regression.
method Flexible methodological framework with stochastic variational inference for posterior distribution.
result Accurate and scalable uncertainty quantification on predictions and parameters.
Proposes a deep learning model for probabilistic forecasting that is also interpretable.
problem Inability to explain predictions of neural network-based time series forecasting methods.
method Deep Autoregressive Networks (DANLIP) for locally interpretable probabilistic forecasting.
result DANLIP provides interpretable predictions with comparable performance to state-of-the-art methods.
DGC-SPNs improve SPNs for image data by combining CNNs and SPNs.
problem SPNs struggle with complex spatial relationships in images.
method Integrates CNNs with SPNs, using novel parameterization for dilations and strides.
result Significantly improved feature coverage and resolution compared to existing SPN architectures.
Bayesian Neural Network improves calibration of deep probabilistic models.
problem Uncalibrated probabilities from deep neural networks limit their use in critical scenarios.
method Decoupled Bayesian Neural Network to map uncalibrated probabilities to calibrated ones.
result Our approach consistently improves calibration and provides more reliable probabilistic models.
Bayesian approach models neurodegenerative diseases without clinical labels.
problem Personalized, predictive modeling of neurodegenerative diseases.
method Probabilistic programmed deep kernel learning combining Gaussian processes and neural networks.
result Surpasses deep learning in accuracy and timeliness of predicting neurodegeneration.
DPEs use KL divergence to approximate BNNs, improving uncertainty estimates for active learning.
problem Improving uncertainty estimates in active learning for visual classification.
method Regularized ensemble approach with KL divergence penalty for variational inference.
result DPEs steadily improve active learning performance with increased annotation budgets.
An unregularized score improves anomaly detection in images with varying complexity.
problem Inaccurate anomaly detection in images with complex shapes and small anomalies.
method Proposed an unregularized score for deep generative models to overcome the issue of lower likelihoods for complex objects.
result The unregularized score is robust to the complexity of samples and improves anomaly detection.
Study improves seasonal forecasts using deep learning.
problem Challenges in generating large forecast ensembles and limited observations for verification.
method Developed a probabilistic deep neural network model.
result Demonstrated favorable skill compared to state-of-the-art dynamical forecast systems.
Layered graphical models improve discriminative learning efficiency.
problem Improving discriminative learning efficiency in graphical models.
method Designing layered graphical models (LGMs) in analogy to neural networks, using tensorized truncated variational inference and backpropagation.
result LGMs achieve competitive results in image classification, comparable to neural networks.
Transforms ensemble predictions to maintain interpretability.
problem Loss of interpretability in deep ensembles.
method Proposes transformation ensembles that aggregate predictions while preserving interpretability.
result Transformation ensembles yield better predictions than individual models and maintain interpretability.
Proposes DGCN with trajectory sampling for data-efficient policy search in MBRL.
problem Improving data efficiency in model-based reinforcement learning.
method Combines trajectory sampling and DGCN for uncertainty propagation in probabilistic world models.
result Improves sample-efficiency over other uncertainty propagation methods and probabilistic models.
Proposes VSGD optimizer combining probabilistic and gradient-based methods.
problem Uncertainty modeling in deep neural networks.
method Combines probabilistic and gradient-based approaches using SVI.
result VSGD outperforms Adam and SGD on image classification tasks.
Develops deep probabilistic graphical modeling for better flexibility and interpretability.
problem Lack of flexibility in probabilistic graphical models and interpretability in deep learning.
method Combines deep learning and probabilistic graphical modeling to create flexible models with interpretable latent structures.
result Solves problems in probabilistic topic models and introduces new learning algorithms.
Edward is a flexible probabilistic programming language that integrates with TensorFlow.
problem Probabilistic programming challenges in flexibility and efficiency.
method Compositional representations of random variables and inference, flexible inference methods, integration with TensorFlow.
result Edward achieves significant speedups in probabilistic modeling and inference.
Method uses neural networks to speed up probabilistic model inference.
problem Efficient inference in probabilistic models.
method Compiles probabilistic programs into neural networks for approximate inference.
result Significant speedups in inference efficiency demonstrated on various models.
Study shows how deep generative models can memorize data.
problem Understanding and preventing memorization in deep generative models.
method Adapted a memorization measure for unsupervised density estimation and demonstrated its effectiveness.
result Memorization in deep generative models differs from mode collapse and overfitting.
Proposes a model for multi-horizon probabilistic forecasting of time series influenced by asynchronous events.
problem Forecasting time series influenced by asynchronous events is challenging.
method Introduces Variational Synergetic Multi-Horizon Network (VSMHN), a deep conditional generative model combining deep point processes and variational recurrent neural networks.
result Produces accurate, sharp, and realistic probabilistic forecasts.
End-to-end deep model for coherent probabilistic forecasts in hierarchical time series.
problem Hierarchical probabilistic forecasting for coherent predictions.
method Dirichlet proportions model for learning root and child distributions.
result Significant improvements over state-of-the-art baselines (up to 26%).
Develops methods to verify probabilistic models ensuring they meet specified properties.
problem Ensuring deep probabilistic models meet desired properties like semantic equivalence and monotonicity.
method Proposes a novel verification framework for deep probabilistic models that requires high probability of constraints being satisfied over latent variable sampling and conditioning inputs.
result Efficient algorithms can be used to verify properties like monotonicity and convexity in functional spaces.
Deep model learns graph structure with context diffusion.
problem Processing structured graph data efficiently.
method Constructive deep architecture with probabilistic models.
result Generative approach improves graph structure classification.
New model predicts entire distribution of time series data.
problem Probabilistic forecasting of multivariate time series.
method Deep generative quantile-copula models with latent uniform distribution.
result Single neural network parameterizes joint predictive distribution.
Introduces a probabilistic view of deep learning for better understanding and explaining neural networks.
problem Explaining the behavior and properties of deep neural networks.
method Introduces a probabilistic representation of deep learning, linking neurons, hidden layers, and the whole architecture to Gibbs distributions and Bayesian neural networks.
result Demonstrates the hierarchy and generalization properties of deep learning through a probabilistic lens.