Moment Pooling reduces latent space dimensions in machine learning models.
problem High-dimensional latent spaces in machine learning models are hard to interpret.
method Moment Pooling extends Deep Sets networks to arbitrary multivariate moments.
result Latent dimensions as small as 1 can achieve similar performance to higher dimensions.
Adaptive framework for learning latent space dimensions in GANs.
problem Inadequate latent space dimensions lead to poor generative models for complex data.
method Proposes a novel framework (LWGAN) that adaptively learns latent dimensions of data manifolds.
result Proves that the estimated intrinsic dimension is a consistent estimate of the true data manifold dimension.
Bayesian non-parametric model selects latent dimensions automatically.
problem Non-linear, sparse latent variable selection.
method Indian buffet process prior, random Fourier approximation, MCMC sampling.
result Superior performance on synthetic, biological, and text datasets.
SAE improves VAE's latent space precision in high dimensions.
problem High-dimensional latent codes vs probabilistic inference in VAEs.
method Spherical Auto-Encoder (SAE) with spherical normalization on latent space.
result SAE improves latent code inference precision in high dimensions.
Develops a new method for nonlinear dimension reduction using random features.
problem Statistical challenges in generalizing Gaussian process-based latent variable models to non-Gaussian data.
method Random feature latent variable models (RFLVMs) that approximate nonlinear relationships with linear functions of random features.
result RFLVMs produce comparable results to state-of-the-art methods on various data types.
Bayesian model estimates latent dimension and communities in graphs.
problem Automatic selection of latent dimension and number of communities in spectral embeddings.
method Bayesian model for simultaneous selection of latent dimension and number of communities.
result Promising performance in recovering latent community structure on simulated and real-world data.
An efficient algorithm selects the correct number of latent dimensions in multidimensional probit models.
problem Determining the correct number of latent dimensions in multidimensional probit graded response models.
method Adaptive Bayesian dimension selection framework using cumulative ordered spike-and-slab (COSS) prior and Albert--Chib latent response augmentation.
result The proposed method accurately recovers latent structures and avoids repeated model fitting.
Early stopping improves sample quality in latent diffusion models.
problem Latent diffusion models degrade sample quality with conventional early stopping.
method Analyzed the interaction between latent dimension and stopping time under Gaussian framework.
result Lower-dimensional representations benefit from earlier termination, higher-dimensional spaces require later stopping.
Model complexity is an important factor to consider when selecting among graphical models. When all variables are observed, the complexity of a model can be measured by its standard dimension, i.e. the number of independent parameters. When hidden variables are present, however, standard dimension might no longer be ap…
Estimates latent dimensionality for prediction tasks using mutual information.
problem Estimating the latent dimensionality needed for accurate prediction.
method Formulates the problem as an Information Bottleneck question and uses neural mutual information estimators with a hybrid critic to preserve latent geometry.
result The hybrid critic method provides a more accurate estimation of task-relevant dimensionality.
This paper proposes a new method for inferring the latent dimension of linear dynamical systems.
problem Manual specification of latent dimension is impractical and leads to model limitations.
method The paper introduces a minimum description length criterion to infer latent dimension.
result The proposed method effectively infers latent dimension and improves model performance.
StrEBM learns distinct latent components for better source separation.
problem Blind source separation with identifiable and decoupled latent components.
method Structured latent energy-based model with learnable structural biases.
result The model effectively recovers source components from mixed signals.
Modeling latent dynamics in high-dimensional event sequences without prior knowledge.
problem Modeling latent dynamics in high-dimensional event sequences with unknown marker relations.
method Adversarial imitation learning framework decomposed into latent structural intensity model, efficient random walk model, and seq2seq discriminator.
result Effective detection of hidden network among markers and decent prediction for future events.
PGA maps data and target distributions to a latent space for better generative model training.
problem Training generative models is difficult due to mismatch between data and target distributions.
method Train generator to match target distribution in latent space using autoencoder.
result PGA achieves state-of-the-art FID scores on CIFAR-10 and CelebA.
This research tackles ordering latent variables in normalizing flows.
problem Learning low-dimensional, meaningful representations in latent space.
method Nested dropout normalizing flows with ordered latent variables.
result A trade-off exists between flow likelihood and ordering quality.
Develops efficient MCMC for Bayesian inverse problems, robust to high dimensions.
problem Efficient exploration of posterior distributions in high-dimensional latent states.
method Non-centred parameterizations and dimension-robust samplers for latent Gaussian processes.
result Framework is dimension-robust, maintaining efficiency as dimension increases.
DPA preserves data distribution in reduced dimensions.
problem Loss of data distribution in dimension reduction.
method DPA combines encoder and decoder to match data distribution.
result DPA successfully reconstructs data distribution.
A new method maps high-dimensional Bayesian inverse problems to lower dimensions.
problem High-dimensional Bayesian inverse problems with complex prior information.
method Data-driven VAE prior and KRnet map for posterior approximation in latent space.
result Efficiently reduces computational cost and approximates posterior distributions.
A new method for disentangled latent spaces in VAEs that can manipulate attributes.
problem Disentangled representation of attributes in latent spaces of VAEs.
method Attribute-based regularization loss to enforce monotonic relationships between attributes and latent codes.
result Manipulation of attributes in latent spaces post-training.
Bayesian model learns optimal number of latent dimensions for Boolean data.
problem Optimal number of latent dimensions in Boolean data models.
method Indian Buffet Process prior over factor matrices for non-parametric Boolean factorisation.
result Posterior inference is efficient and the number of latent dimensions is transparently inferred.
New model handles mixed data types better.
problem Handling data with different types of attributes.
method Mixed likelihood Gaussian process latent variable model with separate likelihoods for each dimension.
result Better predictive performance for real-world data with mixed attributes.
PDGMM-VAE uses adaptive priors for better ICA recovery.
problem Nonlinear ICA recovery of latent source signals.
method Adaptive per-dimension Gaussian mixture model priors in a variational autoencoder.
result PDGMM-VAE effectively recovers source-specific non-Gaussian marginals.
The Gaussian process latent variable model (GP-LVM) is a popular approach to non-linear probabilistic dimensionality reduction. One design choice for the model is the number of latent variables. We present a spike and slab prior for the GP-LVM and propose an efficient variational inference procedure that gives a lower …
New findings limit the dimensionality of latent space for set functions.
problem Limiting dimensionality of latent space for set functions.
method Used continuous mappings to prove practical constraints on latent space dimensionality.
result Latent space dimensionality must match maximum number of input elements for universal function representation.
New algorithm tackles big data Bayesian problems with latent variables.
problem Bayesian computing for large-scale problems with missing data and dimension jumping.
method Extended stochastic gradient MCMC with latent variables.
result Highly scalable and more efficient than traditional MCMC algorithms.
Paper shows graphs can be embedded in lower dimensions than expected.
problem Choosing the right embedding dimension for graph analysis.
method Utilizes hidden manifold structure to predict lower-dimensional embedding.
result Graphs can be embedded in much lower dimensions than previously thought.
The paper develops a method to dynamically adjust VAE latent space dimensions during training.
problem Under- or overprovisioning of latent space dimensions in VAEs.
method GECO optimizer with L0-ARM gradient estimator to dynamically adjust latent space dimensions. result The latent space can be pruned effectively without violating reconstruction error constraints.
Latent DiTs improve data distribution recovery and inference efficiency under low-dimensional latent space.
problem Improving data distribution recovery and inference efficiency in latent DiTs.
method Investigates statistical and computational limits of latent DiTs under low-dimensional latent space assumption, deriving approximation error bounds, sample complexity, and efficient inference and training algorithms.
result Latent DiTs can bypass high dimensionality challenges and achieve almost-linear time inference and training.
SAHMM-VAE separates sources adaptively using hidden Markov priors.
problem Unsupervised blind source separation.
method Source-wise adaptive Hidden Markov prior variational autoencoder.
result Different latent dimensions align with different source-specific temporal organizations.
Efficient RL in large POMDPs with latent determinism and embeddings.
problem Efficient reinforcement learning in large-scale POMDPs with latent states and observations.
method Conditional Hilbert space embeddings, linear optimal Q-function, deterministic latent transitions, gap assumption. result Computationally and statistically efficient algorithm for exact optimal policy.
tvGP-VAE models tensor-valued latent variables with Gaussian processes for better data structure representation.
problem Agnostic latent variables in VAEs ignore data structure correlations.
method Proposes tensor-variate Gaussian process prior for variational autoencoder.
result Explicitly modeling correlation structures improves model performance in reconstruction.
New tests for identifying the number of latent factors in short panels with small time dimensions.
problem Determining the number of latent factors in short panels with small time dimensions.
method Eigenvalue tests based on variance-covariance matrices of asset returns, with assumptions on spherical errors or instrumental variables for factor betas.
result Established asymptotic distributional results and proposed a novel statistical test for weak factors.
New clustering technique estimates pointwise dimensionality of data.
problem Clustering complex datasets with varying dimensions.
method Estimates pointwise dimension using nearest neighbor distances.
result Dimensional clustering works effectively on various datasets.
Bayesian network models with latent variables are widely used in statistics and machine learning. In this paper we provide a complete algebraic characterization of Bayesian network models with latent variables when the observed variables are discrete and no assumption is made about the state-space of the latent variabl…
Improved recommendations using latent embeddings from user reviews.
problem Lack of consideration for latent embeddings in multi-criteria recommender systems.
method Utilized variational autoencoders to map user reviews into latent embeddings, which are then compressed into discrete vectors for multi-criteria recommendation.
result The proposed method significantly outperforms baselines across various datasets and evaluation measures.
Paper uses non-linear dimension reduction for better economic forecasting.
problem Analyzing economic effects of shocks in large datasets.
method Non-linear dimension reduction in factor-augmented vector autoregressions.
result Non-linear dimension reduction techniques improve forecasting, especially in volatile data.
New method handles missing data for tensor decomposition.
problem Learning latent variables from partial data.
method Weighted tensor decomposition approach for incomplete data.
result Weighted approach outperforms non-weighted methods.
SKR-VAE improves VAEs for ICA with reduced computational cost.
problem Efficiently performing ICA in VAEs with large datasets.
method Structured kernel functions to avoid costly GP kernel matrix inversion.
result SKR-VAE achieves greater computational efficiency and reduced resource consumption.
New algorithms use offline data to improve online decision-making with latent states.
problem Accelerating online sequential decision-making with latent states in offline data.
method Design end-to-end latent bandit algorithms for linear latent contextual bandits, learning latent subspace offline and using it online.
result Proves minimax optimal regret guarantees for online algorithms and practical efficiency.
A new model captures dependencies and unique characteristics in multi-dimensional sequences.
problem Modeling high-dimensional sequential data with dependencies and unique characteristics.
method Collaborative multi-output Gaussian process dynamical system (CGPDS) with shared and private latent processes, using inducing points and stochastic variational inference.
result Captures dependencies and unique characteristics in multi-dimensional sequences.
We present a max-margin nonparametric latent feature model, which unites the ideas of max-margin learning and Bayesian nonparametrics to discover discriminative latent features for link prediction and automatically infer the unknown latent social dimension. By minimizing a hinge-loss using the linear expectation operat…
Paper explores tradeoffs in classification using tensor subspaces.
problem Supervised classification with sample, computation, and storage complexities.
method Use of tensor subspaces, particularly hierarchical Kronecker structured subspaces.
result Hierarchical Kronecker structured subspaces improve classification tradeoffs.
Bayesian NMF model improves predictions and avoids overfitting.
problem Predicting missing values and finding hidden patterns in nonnegative data.
method Flexible and hierarchical prior for Bayesian NMF with Gibbs sampling.
result The proposed model leads to better predictions and avoids overfitting.
New methods forecast time series using high predictors via latent factors.
problem Forecasting with many predictors and nonlinear relationships.
method Factor analysis, sufficient dimension reduction, directional regression, inverse third-moment method.
result Captures non-monotone effects of latent factors on response.
Paper introduces a new deep-learning method for quantum mechanics.
problem Simulating time-evolving Schrödinger equations efficiently.
method Generative diffusion models and stochastic mechanics.
result Significantly lower computational complexity compared to existing methods.
Proposes LDIDPs for efficient sequential data generation from latent dynamical models.
problem Challenges in generating high-fidelity sequential samples from latent dynamical models.
method Utilizes implicit diffusion processes to sample from latent dynamical processes.
result Demonstrates accurate learning of dynamics and efficient generation of high-quality sequential data.
A new method bypasses regularization for disentangled latent variables without tuning.
problem Learning disentangled latent variables in unsupervised settings.
method Projection strategy to modify Gaussian encoder, ensuring zero cross-correlation among latent sub-coordinates.
result The method achieves maximal disentanglement theoretically and without loss in expressiveness.
Paper proposes a new model for speech synthesis with better interpretability.
problem Improving interpretability in speech synthesis models.
method Hierarchical, fine-grained latent variable model with conditional variational auto-encoder (VAE).
result The new model allows better interpretability without degrading performance.