Study introduces TeMoP model for better stock market predictions.
problem Decreasing prediction errors and robustness across datasets in machine learning models.
method Probabilistic multiple lag order model based on trend encoding.
result TeMoP model outperforms machine learning models in accuracy and stability across different stock indexes.
Hybrid Bayesian neural networks use function uncertainty for probabilistic inference.
problem Uncertainty in neural network weights is hard to specify and interpret.
method Integrates probabilistic layers with standard deterministic layers for function uncertainty.
result Improves probabilistic inference by encoding function uncertainty.
New method enforces encoder sparsity in HPF for more interpretable feature selection.
problem Lack of encoder sparsity in HPF leads to lack of column-clustering property.
method Enforces encoder sparsity using a generalized additive model (GAM).
result Gains ability to perform feature selection and relates each representation to original features.
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.
Paper introduces probabilistic SNNs for efficient learning.
problem Training SNNs with biological plausibility and energy efficiency.
method Discrete-time probabilistic models, variational inference.
result Derives supervised and unsupervised learning rules.
A deep probabilistic model analyzes DNA-encoded library data for efficient screening.
problem Complex data from DNA-encoded library experiments mask underlying signals.
method Compositional deep probabilistic model of DEL data, modeling latent reactions between synthons.
result DEL-Compose model demonstrates strong performance and valuable insights.
Wasserstein autoencoder improves sentence generation in NLP.
problem Difficulty in training variational autoencoders for text.
method Proposes a stochastic Wasserstein autoencoder (WAE) for probabilistic sentence generation.
result Wasserstein autoencoder achieves higher BLEU scores for sentence reconstruction.
AESMC uses auto-encoding for efficient model and proposal learning.
problem Inference in structured probabilistic models.
method Maximizing log marginal likelihood with SMC and deep neural networks.
result Improved model and proposal learning with new training procedure.
Paper introduces MLRH, a probabilistic model for multilabel classification.
problem Multilabel classification challenges in various domains.
method Introduces hidden variables to relax one-hot-encoding in logistic regression.
result Probabilistic model achieves competitive performance compared to other algorithms.
New method encodes function preferences into neural nets for better generalization.
problem Challenges in encoding explicit function preferences in neural network training.
method Function-space empirical Bayes (FSEB) regularization.
result FSEB leads to near-perfect semantic shift detection and improved generalization.
Exact solution for missing data in factor analysis using autoencoders.
problem Handling missing data in factor analysis models.
method Developed an exact solution for factor analysis with missing data using autoencoders.
result An exact latent posterior distribution for factor analysis with missing data.
This paper introduces probabilistic SNNs for efficient neural processing.
problem Training algorithms for SNNs lag behind hardware implementations.
method Discrete-time probabilistic models and variational inference.
result Derivation of learning rules for SNNs from first principles.
CGAE model predicts solar irradiance with high reliability and sharpness.
problem Probabilistic spatio-temporal solar irradiance forecasting.
method Convolutional Graph Auto-Encoder (CGAE) based on spectral graph convolutions and variational Bayesian inference.
result State-of-the-art performance in probabilistic solar irradiance prediction.
A new approach to generative modeling using optimal transport.
problem Improving unsupervised generative modeling techniques.
method Relaxing constrained optimization of probabilistic encoders to a penalized optimal transport objective.
result The POT objective for 2-Wasserstein distance matches AAEs, providing theoretical justification.
Develops a deep model for joint image-text learning.
problem Bidirectional joint image-text modeling.
method Variational hetero-encoder randomized GAN (VHE-GAN).
result Achieves state-of-the-art performance in image-text learning and generation.
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.
PE-SVI reduces SVI inference complexity by finding a suitable start point.
problem Complex posterior inference in graphical models leads to suboptimal learning.
method PE-SVI uses a pseudo-encoded start point to reduce gradient steps and step sizes.
result PE-SVI achieves the same ELBo objective as SVI with less than 1% of the required steps.
Contrastive learning recovers latent distributions for ambiguous inputs, including aleatoric uncertainty.
problem Real-world observations often have inherent ambiguities, making the true posterior probabilistic with heteroscedastic uncertainty.
method Extended InfoNCE objective and encoders to predict latent distributions, proving they recover the correct posteriors, including aleatoric uncertainty.
result Contrastive learning encoders can recover the correct posteriors of data-generating processes, including aleatoric uncertainty, up to a rotation of the latent space.
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.
A deep learning method speeds up probabilistic optimal power flow calculations.
problem Efficiently solving large-scale nonlinear and nonconvex optimization problems in power systems.
method Developed a SDAE-based OPF using stacked denoising auto encoders to extract system correlations and calculate OPF solutions.
result The trained SDAE network can quickly compute OPF solutions for random system states without optimization.
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.
Efficiently combines autoregressive and set-based models for joint distributions.
problem Joint distributions over multiple predictions from set-based models.
method Causal autoregressive buffer that caches context and captures dependencies.
result Up to 20x faster joint sampling and density evaluation, up to 7x lower memory usage.
A simple approach speeds up probabilistic programming models.
problem Efficiently implementing probabilistic programming in deep learning.
method Embedding probabilistic programming into TensorFlow with a single random variable abstraction.
result Optimal linear speedup from 1 to 256 TPUv2 chips, and 100x speedup on GPUs.
BinConv improves time series forecasting by preserving ordinal information in a classification framework.
problem Lack of ordinal information in existing classification-based time series forecasting methods.
method Cumulative Binary Encoding (CBE) and BinConv architecture.
result BinConv achieves superior performance in time series forecasting compared to existing methods.
BLISS detects and separates astronomical sources quickly and accurately.
problem Detecting and separating overlapping astronomical sources in large images.
method Bayesian Light Source Separator (BLISS) using deep generative models and variational inference.
result BLISS can process megapixel images in seconds and produce highly accurate catalogs.
PPC detects anomalies in high-dimensional data efficiently.
problem Scalability issues and reduced performance with high-dimensional data.
method Probabilistic Predictive Coding (PPC) learns latent representations and predicts uncertainties.
result PPC achieves linear time complexity and high adaptability.
Paper shows domain recursion is more powerful than previously thought, enabling faster inference.
problem Intractable probabilistic inference in relational models.
method Study of domain recursion rule and its impact on lifted inference.
result Domain recursion extends the range of models for which lifted inference is polynomial-time.
CMRFs extend PGMs for topological data, capturing both conditional and marginal dependencies.
problem Limited expressiveness of PGMs for topological data.
method Introducing Colored Markov Random Fields (CMRFs) that model Gaussian edge variables on topological spaces.
result CMRFs improve distributed estimation over physical networks compared to baselines.
The paper proposes a probabilistic autoencoder for discovering causal directions between variables.
problem Finding the causal direction between two associated variables.
method Building an autoencoder of the joint distribution and maximizing its estimation capacity relative to marginal distributions.
result The higher estimation capacity is consistent with the unconstrained choice of a distribution representing the cause, while the lower capacity reflects the constraints imposed by the mechanism on the distribution of the effect.
Faster diffusion-based models generate data with fewer steps.
problem Slow and costly diffusion-based generative models.
method Truncate diffusion process to generate data more efficiently.
result Truncated models provide consistent improvements in performance.
Algorithm determines if missing data makes probabilistic queries estimable.
problem Determining estimability of probabilistic queries from missing data.
method Algorithm based on Bayesian networks and missingness mechanisms.
result Advances existing work by systematically determining estimability.
New framework uses cohomology to analyze probabilistic distortions and arbitrage.
problem Analyzing probabilistic distortions and arbitrage in categorical filtrations.
method Transport cohomological framework, simplicial structure, loop effects, holonomy.
result Nontrivial probabilistic distortions and obstructions generated by loops.
DeRegiME forecasts with regime structure, improving probabilistic predictions across various time series.
problem Probabilistic forecasting discards residual uncertainty, and distribution shifts are hard to capture.
method DeRegiME uses a sparse variational Gaussian process with a nonstationary regime-mixing kernel to separate latent uncertainty regimes.
result DeRegiME improves NLPD by 20.3% on average across benchmarks, with gains on CRPS and MSE.
Secure communication system detects deletions and eavesdropping.
problem Reliable communication over deletion channels with eavesdropping.
method Probabilistic finite-state automata for encoding and decoding.
result Scheme ensures small error probability in decoding and tamper detection.
New bounds enable training of probabilistic models for deep networks.
problem Training scalable latent variable models for deep networks.
method Introducing new variational bounds for specific output layers of neural networks.
result Analytical bounds for certain output layers allow training without re-parameterization or Monte Carlo approximations.
A new model for efficient sequential pattern mining without specific encoding schemes.
problem Mining relevant sequential patterns efficiently and effectively.
method Subsequence interleaving model based on probabilistic sequence database.
result Efficient inference through submodular optimization, resulting in low spuriousness and redundancy.
Probabilistic grammars improve equation discovery from data.
problem Discovering scientific laws from data using equations.
method Proposed probabilistic context-free grammars to encode soft constraints and a Monte-Carlo algorithm.
result Probabilistic grammars lead to more efficient equation discovery.
MIM learns joint distributions with mutual information and low divergence.
problem Learning joint distributions over observations and latent variables.
method Probabilistic auto-encoder with three design principles: low divergence, high mutual information, and low marginal entropy.
result MIM learns representations with high mutual information, consistent encoding and decoding distributions, effective latent clustering, and comparable data log likelihood to VAE.
Capsule models enforce object pose relationships for robustness, explored with probabilistic generative and variational methods.
problem Enforcing object pose relationships for robustness to viewpoint changes.
method Probabilistic generative model with variational bound, exploring capsule assumptions and inference mechanisms.
result Unified objective and test time optimisation demonstrated for capsule models.
Proposes using knowledge graphs to improve probabilistic model estimation.
problem Lack of direct utilization of domain knowledge in regularization methods.
method Knowledge-based distant regularization framework using knowledge graph embeddings.
result Improvement in generalization capability of probabilistic models.
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.
Bayesian approach for policy search in stochastic domains.
problem Policy search in stochastic domains.
method Nested probabilistic programs, Lightweight Metropolis-Hastings (LMH) adaptation.
result Similar quality policies learned with simpler algorithm.
Proposes Likelihood Regret for VAEs to improve OOD detection.
problem VAEs can assign high likelihoods to OOD samples, making traditional likelihood thresholds unreliable.
method Introduces Likelihood Regret, a new OOD score for VAEs.
result Empirical results show Likelihood Regret outperforms existing methods for VAEs.
Develops a neural framework for probabilistic forecasting of dynamical systems.
problem Uncertainty quantification in dynamical systems using trajectory-oriented approaches.
method D2D neural probabilistic forecasting framework using kernel mean embeddings and mixture density networks.
result The D2D model captures distributional evolution in chaotic systems and produces skillful probabilistic forecasts.
New method for invariant neural networks using probabilistic symmetries.
problem Improving neural network performance in data-scarce, non-i.i.d., or unsupervised settings.
method Characterizing neural network structures invariant under compact group actions using probabilistic symmetry.
result Established a link between functional and probabilistic symmetry, yielding generative representations of invariant distributions.
Unified probabilistic models improve audio signal processing efficiency and interpretability.
problem High computational cost and difficulty in interpreting probabilistic models in time-frequency analysis.
method Equivalence to Spectral Mixture Gaussian processes, state space representation, Kalman smoothing, efficient parameter learning.
result Unified models make it easier to interpret and modify model assumptions.
A new model improves analysis of neural activity from calcium imaging.
problem Statistical modeling of deconvolved calcium signals for neural activity interpretation.
method Proposed a zero-inflated gamma (ZIG) model to characterize calcium responses as a mixture of a gamma distribution and a point mass.
result The ZIG model outperforms simpler models in neural encoding and decoding problems.
New insights into encoder-decoder structures using information measures.
problem Understanding the role of encoder-decoder design in machine learning.
method Using information sufficiency and mutual information loss concepts.
result Characterizes the expressiveness loss in encoder-decoder designs.