Improved robust latent variable estimation for neural dynamics.
problem Inconsistent results due to noise and nonlinearity in existing models.
method Probabilistic approach to latent variable estimation in decomposed models.
result More accurate latent variable inference in nonlinear systems with diverse noise conditions.
This work extends identifiability analysis to sequential latent variable models, focusing on Switching Dynamical Systems.
problem Identifying latent variables in sequential data models.
method Proved identifiability of Markov Switching Models and established conditions for Switching Dynamical Systems.
result Identifiability of latent variables and non-linear mappings in Switching Dynamical Systems up to affine transformations.
Study identifies latent variables and models from spacecraft data.
problem Learning reliable models from spacecraft data with complex relationships.
method Inductive bias inspired by controllable canonical forms for sparse, input-dependent latent variables.
result Identifies latent variables up to scaling and determines dynamic models up to transformations for linear and affine systems.
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.
Paper develops a new model for dynamic graph representation learning.
problem Learning over dynamic graphs with changing topology and node attributes.
method Hierarchical variational model with latent random variables and semi-implicit variational inference.
result SI-VGRNN and VGRNN outperform existing methods in dynamic link prediction.
New metric improves latent dynamics inference from neural data.
problem Limitations of co-smoothing in predicting latent dynamics.
method Few-shot co-smoothing to assess latent dynamics.
result High co-smoothing models often have extraneous dynamics, which few-shot co-smoothing detects.
Framework learns image dynamics between time steps using latent variables.
problem Challenges in capturing evolving image patterns and temporal information.
method Estimates intermediary image stages using a physical latent variable model.
result Demonstrates robustness and effectiveness in geoscientific imagery.
A new method for efficient variational inference in dynamic models.
problem Performing variational inference in dynamical latent variable models efficiently.
method Amortized variational filtering algorithm derived from the filtering setting.
result Improves performance across various deep dynamical latent variable models.
A new model captures variability in time series data.
problem Capturing high variability in time series data.
method Temporal latent variables and dynamic weight modifications.
result Demonstrated efficacy on various sequential data.
Model infers latent variables in sparse coding models using Langevin dynamics.
problem Sampling posterior distribution in sparse coding models.
method Langevin dynamics for inference and simultaneous learning of parameters.
result Langevin dynamics efficiently sample from 'L0 sparse' posterior distribution.
Paper proposes a fast method for learning deep latent variable models.
problem Learning deep generative models with hierarchical latent variables.
method Noise initialized short run MCMC with variational optimization of step size.
result The method outperforms VAE in reconstruction and synthesis quality.
New model captures state-dependent variability in partially observed systems.
problem Structured stochasticity not captured by constant-variance models.
method State-coupled stochastic volatility framework with particle expectation-maximization.
result Model consistently reduces recovery bias under partial observation.
Study improves Gaussian Process Latent Variable Model for noisy longitudinal data.
problem Noisy and incomplete longitudinal data makes learning representations difficult.
method Augment variational approximation with systematic samples of unseen observations.
result Demonstrates improved learning of Gaussian Process Dynamical Systems in noisy data.
Framework LiLY recovers latent causal variables from time-series data under distribution shifts.
problem Learning and correcting models under unknown distribution shifts in time-series data.
method LiLY framework that recovers latent causal variables and identifies their relations from temporal data under different distribution shifts.
result The framework reliably identifies time-delayed latent causal influences from observed variables under different distribution changes.
Dynamic network model forecasts interbank market link formation.
problem Forecasting interbank market link formation with time-varying topologies.
method Dynamic network model with past link existence and node-specific latent variables. Markov dynamics and EM algorithm for estimation.
result Forecasting future link presence and recognition of preferential lending.
Improves latent variable learning for complex data.
problem Expressive latent variables for model prediction on multi-component data.
method Dynamic Latent Separation method that distances data samples in the latent space.
result Enhances output diversity and provides interpretable representations.
Adapts to new environments in robotics using latent variable models.
problem Learning dynamics in robotic environments with subtle variations.
method Variational inference for latent representation, online Bayesian inference, neural network ensemble.
result Positive transfer during training and online adaptation on HalfCheetah task.
Langevin autoencoders improve deep latent variable models with efficient posterior sampling.
problem Efficient posterior sampling in deep latent variable models using MCMC.
method Amortized Langevin dynamics (ALD) replaces datapoint-wise sampling with encoder updates.
result ALD is valid as an MCMC algorithm with the target posterior as a stationary distribution.
The paper presents a method to assess latent variable models by pulling data into latent space.
problem Assessing latent variable models for model criticism.
method Pulling data back into the latent space to perform model criticism.
result A more direct assessment of model assumptions in prior and likelihood.
Study analyzes Bayesian inference algorithms using dynamical functional approach.
problem Analysis of approximate inference algorithms for large Gaussian latent variable models.
method Dynamical functional approach to model nontrivial dependencies and obtain exact effective stochastic process.
result Closed-form expressions for the rate of convergence are derived and validated.
Optimally explores dynamical systems with varying properties using context inference.
problem Learning dynamics models for systems with varying properties.
method Formulates dynamics models as stochastic processes conditioned on a latent context variable inferred from system transitions. Uses probabilistic formulation to compute optimal action sequences for exploration.
result Demonstrates effectiveness of the method on non-linear toy-problems and reinforcement learning environments.
Latent variable models improve RL by facilitating efficient learning and exploration.
problem Improving sample efficiency in reinforcement learning.
method Representation view of latent variable models for state-action value functions, incorporating kernel embeddings and UCB exploration.
result Established sample complexity of the proposed approach in online and offline settings, demonstrated superior performance in benchmarks.
Proposes PredVAR model for reduced-dimensional dynamics from noisy data.
problem Extracting low-dimensional dynamics from high-dimensional noisy data.
method Probabilistic reduced-dimensional vector autoregressive model with oblique projection.
result Iterative algorithm yields dynamic latent variables with rank-ordered predictability.
Novel dynamic predictive strategy improves financial and macroeconomic forecasting.
problem Improving predictive models in data-rich environments.
method Decouple-recouple dynamic predictive strategy, latent states, time-varying latent factor model.
result Our framework generates significant out-of-sample benefits and outperforms other methods.
We propose a probabilistic model to infer supervised latent variables in the Hamming space from observed data. Our model allows simultaneous inference of the number of binary latent variables, and their values. The latent variables preserve neighbourhood structure of the data in a sense that objects in the same semanti…
Bayesian model captures spatial correlations in data.
problem Modeling spatial correlations in high-dimensional data.
method Structured Bayesian Gaussian process latent variable model with parameterized spatial kernel and structure-exploiting algebra.
result Inference is tractable with computational complexity similar to traditional Bayesian GP-LVM.
PRGDS models count tensors with sparsity and burstiness.
problem Modeling sequential count data with sparsity and burstiness.
method Poisson-randomized gamma dynamical system with alternating Poisson and gamma latent states.
result Sparse PRGDS often outperforms other models in predicting count data.
Paper introduces TSSDMN for modeling dynamic multilayer networks.
problem Capturing temporal and cross-layer dynamics in multilayer networks.
method Tensor State Space Model (TSSDMN) using symmetric Tucker decomposition.
result TSSDMN uniquely captures temporal dynamics within and across layers.
New method improves uncertainty quantification in latent variable models.
problem Uncertainty quantification in latent variable models with SGLD-Gibbs.
method Statistical scaling limit theory for SGLD-Gibbs, proposing hyperparameter tuning.
result Explicit guidance on hyperparameter tuning for SGLD-Gibbs ensures meaningful uncertainty quantification.
New method infers network couplings from spin trajectories in continuous time.
problem Inferring network couplings from observed spin trajectories in continuous time.
method Introducing latent variables to linearize and make likelihood quadratic, deriving EM and variational algorithms.
result Demonstrated performance on simulated data and biologically plausible network.
Method learns model for unknown stochastic system from data.
problem Modeling unknown stochastic dynamical systems.
method Autoencoder approach using deep neural networks (DNNs).
result Decoder serves as a predictive model for unknown stochastic systems.
New method for LVEBMs using saddle-point optimization and Langevin updates.
problem Expressive generative modeling of latent variables with hidden structure.
method Reformulate LVEBM training as a saddle problem, using Langevin updates and gradient flows.
result Proves existence and convergence of the algorithm under standard assumptions, with improved ELBO bounds.
Introduces alternators for modeling sequences, outperforming baselines.
problem Modeling complex sequential data with stability and efficiency.
method Two neural networks (OTN and FTN) alternate between outputting samples in observation and feature spaces, learned via cross-entropy criterion.
result Alternators outperform strong baselines in various domains (Lorenz equations, Neuroscience, Climate Science).
In nonlinear latent variable models or dynamic models, if we consider the latent variables as confounders (common causes), the noise dependencies imply further relations between the observed variables. Such models are then closely related to causal discovery in the presence of nonlinear confounders, which is a challeng…
VIND infers smooth nonlinear dynamics from electrophysiology data.
problem Analyzing smooth, nonlinear time series data from neuroscience experiments.
method Variational Inference for Nonlinear Dynamics (VIND) with structured approximate posterior and fixed-point iteration.
result VIND reconstructs 5D latent space variables similar to Hodgkin-Huxley models, and excels in predicting future neural activity.
Unified approach to training stochastic RNNs with latent variables.
problem Training generative latent variable models with autoregressive decoders.
method Amortized variational inference with backward RNN conditioning and auxiliary reconstruction cost.
result Improved performance on speech and sequential MNIST benchmarks.
Bayesian neural networks decompose uncertainty into epistemic and aleatoric components.
problem Uncertainty in Bayesian neural networks with latent variables.
method Information theoretic approach and risk-sensitive objective for safe reinforcement learning.
result Natural decomposition of predictive uncertainty in Bayesian active learning and safe RL.
New model learns continuous disease progression from RNA-seq data.
problem Continuous disease progression not captured by discrete categories.
method Covariate latent variable models for learning a low-dimensional data representation.
result Identifies genes stratifying patients on an immune-response trajectory.
New grammar model learns sentence structure with latent variables.
problem Grammar induction for sentences with complex dependencies.
method Compound probabilistic context-free grammar with latent variables, variational inference.
result Effective unsupervised parsing compared to state-of-the-art methods.
Generative models learn latent process to match target distributions.
problem Training flow-matching models with auxiliary stochastic dynamics.
method Introduces latent process generator matching, treating generative state as a deterministic image of a Markov process.
result Learn generator of a stochastic process with same marginal distributions.
New method learns latent energy models using particle algorithms.
problem Learning latent variable models with energy priors.
method Continuous-time SDEs for MMLE, particle-based discretization.
result Practical algorithm converges to solve MMLE problem.
Fast algorithm for analyzing huge social networks.
problem Analyzing dynamic social networks with large numbers of actors.
method Hierarchical strategy for latent space inference with spline processes and machine learning optimization.
result Can fit millions of nodes in a few minutes.
Recurrent-DBN models dynamic relational data with interpretable latent structures.
problem Interpreting dynamic relational data with hidden structures.
method Recurrent Dirichlet Belief Network framework with hierarchical latent structures and efficient inference strategy.
result Recurrent-DBN discovers interpretable latent structures and improves link prediction.
LSS learns molecular trajectories from MD data.
problem Limited integration time steps in MD simulations.
method Three deep learning networks for slow collective variables, dynamics, and configuration reconstruction.
result Generates ultra-long synthetic folding trajectories.
Predicts multiple vehicle trajectories efficiently.
problem Predicting uncertain future motions of agents in dynamic scenes.
method Probabilistic framework learning latent variables for multi-step future modeling.
result State-of-the-art predictions on vehicle trajectory datasets.
Model captures system input variations in latent space for actionable dynamics.
problem Learning dynamical systems from data without prescribing a mathematical model.
method Structured latent ODE model with stochastic factors of variation for each input.
result Improves generation of time-series data and inference of system inputs over baselines.
New methods improve sampling from complex dynamical models.
problem Sampling from high-dimensional, non-linear latent dynamical models is computationally challenging.
method Introduce auxiliary MCMC and Particle Gibbs samplers with improved performance and parallelisation.
result Enhanced samplers maintain performance in high-dimensional latent spaces and support parallelisation.
This work explains how linear representations in large language models arise from training objectives and gradient descent.
problem Understanding the origins of linear representations in large language models.
method A latent variable model to abstract and formalize concept dynamics, combined with analysis of the softmax cross-entropy objective and gradient descent.
result Linear representations emerge when learning from data matching the latent variable model, and this simple structure suffices to yield linear representations.