PPT optimizes transformer behavior by steering its latent posterior using prior samples.
problem Eliciting desired behavior from transformers without backpropagation.
method Posterior Prefix Tuning (PPT) uses predictive Monte Carlo (PMC) samples and importance sampling to optimize the latent posterior.
result PPT optimizes transformer behavior without backpropagation, achieving high utility across different utility functions.
Paper introduces a new generative learning model using Schrödinger bridge diffusion in latent space.
problem Learning distributions from divergent data distributions.
method Pre-training with large-scale models, Schrödinger bridge diffusion model in latent space.
result Effective control of second-order Wasserstein distance between generated and target distributions.
Tiered latent representations and latent spaces for molecular graphs provide a simple but effective way to explicitly represent and utilize groups (e.g., functional groups), which consist of the atom (node) tier, the group tier and the molecule (graph) tier. They can be learned using the tiered graph autoencoder archit…
Synthetic tabular data synthesis models balance utility and risk.
problem Generating synthetic tabular data for regulated domains.
method Latent flow models with various learning targets, paths, and sampling methods.
result Velocity and posterior matching objectives yield higher utility, while score and noise matching achieve lower risk.
The paper optimizes portfolios using MACD signals derived from price history.
problem Optimizing risky asset portfolios with latent mean-reverting and momentum factors.
method Derives optimal strategies based on MACD signals from EMA processes.
result Establishes admissibility and verification of optimal strategies.
Data-driven anomaly detection methods suffer from the drawback of detecting all instances that are statistically rare, irrespective of whether the detected instances have real-world significance or not. In this paper, we are interested in the problem of specifically detecting anomalous instances that are known to have …
Improves matrix completion by exploiting biased observation patterns.
problem Matrix completion with biased observation patterns.
method Mask Nearest Neighbor (MNN) algorithm: two-stage process.
result MNN achieves competitive performance with 28x smaller mean squared error.
Paper presents a novel approach for global feature aggregation in Graph Neural Networks.
problem Graphs lack a straightforward way to perform non-local feature aggregation like images and texts.
method Utilizes Latent Fixed Data Structure (LFDS) to aggregate feature vectors from local extraction.
result Proposed methods achieve competitive or better results with linear computational complexity.
cMCA uses contrastive learning to identify latent subgroups in political party data.
problem Identifying latent subgroups within political party data.
method Contrastive learning applied to multiple correspondence analysis (MCA).
result cMCA identifies latent subgroups not seen by traditional methods.
Improves causal graph learning on dependent binary data.
problem Challenges in learning causal graphical models from dependent binary data.
method Decorrelation-based approach using latent utility model and EM-like algorithm.
result Significant improvement in accuracy of causal graph learning.
Distributed devices such as mobile phones can produce and store large amounts of data that can enhance machine learning models; however, this data may contain private information specific to the data owner that prevents the release of the data. We wish to reduce the correlation between user-specific private information…
Multi-criteria recommender systems have been increasingly valuable for helping consumers identify the most relevant items based on different dimensions of user experiences. However, previously proposed multi-criteria models did not take into account latent embeddings generated from user reviews, which capture latent se…
Neural Decomposition breaks down VAE latent structure for better interpretability.
problem Limited interpretability of VAE latent representations.
method Adapted functional ANOVA to VAEs, applying constraints for identifiability.
result Decomposes data variation into latent and fixed input effects.
GCAE uses density estimation to achieve reliable disentanglement in latent space.
problem Disentangled learning representations suffer from reliability issues.
method GCAE uses Gaussian Channel Autoencoder with Dual Total Correlation (DTC) to avoid the curse of dimensionality.
result GCAE achieves highly competitive and reliable disentanglement scores.
Paper proposes a new method to identify causal graphs with latent variables using higher-order cumulants.
problem Estimating causal directed acyclic graphs with latent confounders.
method Uses higher-order cumulants to identify causal structures among observed and latent variables.
result Validates the proposed algorithm through simulations and real-world data.
Context-aware recommender systems (CARS) have gained increasing attention due to their ability to utilize contextual information. Compared to traditional recommender systems, CARS are, in general, able to generate more accurate recommendations. Latent factors approach accounts for a large proportion of CARS. Recently, …
Improved DSSMs for easier interpretable latent variables.
problem Complex and hard-to-interpret latent variables in DSSMs.
method Simplified predictive decoder and shrinkage priors.
result Interpretable latent variables improve forecasting performance.
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.
We extend the framework of variational autoencoders to represent transformations explicitly in the latent space. In the family of hierarchical graphical models that emerges, the latent space is populated by higher order objects that are inferred jointly with the latent representations they act on. To explicitly demonst…
New findings show invariance alone isn't enough to identify latent causal variables.
problem Lack of theoretical insights for identifying latent causal variables when variables are latent.
method Assessed the connection between invariance and causal representation learning using impossibility results.
result Invariance alone is insufficient to identify latent causal variables.
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.
Improved vector quantization using Gaussian mixtures for better codebook utilization.
problem Training instability and information loss in discrete vector quantization.
method Generalized vector quantization with Gaussian mixture model and aggregated categorical posterior evidence lower bound.
result GM-VQ improves codebook utilization and reduces information loss without heuristics.
A neural network method determines the latent dimensionality of NMF.
problem Determining the correct number of hidden features (latent dimensionality) in NMF.
method Combining NMFk with an MLP classifier trained on a dataset of matrices with known latent features.
result The MLP classifier in conjunction with NMFk achieves a greater than 95% success rate in determining the correct number of latent features.
Improved deep hierarchical VAE with diffusion-based VampPrior.
problem Latent variable generative modeling challenges.
method Hierarchical VAE with amortized diffusion-based VampPrior.
result Better performance with fewer parameters and improved stability.
LaCIM avoids spurious correlation by modeling latent causal factors.
problem Avoiding spurious correlation in supervised learning.
method Introducing latent variables for causal prediction and optimizing over latent space.
result Improved interpretability, robustness, and prediction power on OOD scenarios.
Generative model learns investment strategies without explicit utility specification.
problem Challenges in modeling complex, multi-objective fund optimization.
method Generative adversarial network (GAN) framework that learns latent strategy representations.
result Framework captures diverse investment styles and realizations of optimization parameters.
GMVAE improves open-set classification by clustering latent representations.
problem Improving open-set classification accuracy and robustness.
method Cooperative learning of reconstruction and clustering in the latent space of a GMVAE.
result Achieved an average F1 improvement of 29.5% in open-set classification.
Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of unsupervised learning of features correlated to specific labels in a dataset. We propose a …
LUQ-Learning adapts Q-learning for healthcare decisions considering patient preferences.
problem Optimizing treatment decisions for multivariate outcomes based on individual preferences.
method Latent Utility Q-Learning (LUQ-Learning) framework that adapts Q-learning for composite outcomes.
result LUQ-Learning achieves highly competitive performance compared to alternative methods in simulations.
LaT-PFN model predicts time series with zero-shot capability.
problem Zero-shot time series forecasting.
method In-context latent space learning with JEPA and PFN integration.
result Superior zero-shot predictions compared to baselines.
Paper improves variational inference for complex models.
problem Improving statistical accuracy of variational inference in high-dimensional models.
method Developed a general framework for MFVI and proposed a partially grouped VI algorithm.
result Proposed algorithm works and outperforms vanilla MFVI in mixed membership stochastic blockmodel.
High-risk domains require reliable confidence estimates from predictive models. Deep latent variable models provide these, but suffer from the rigid variational distributions used for tractable inference, which err on the side of overconfidence. We propose Stochastic Quantized Activation Distributions (SQUAD), which im…
New measures quantify diversity of latent representations using metric space magnitude.
problem Evaluating the diversity of latent representations in machine learning models.
method Developed magnitude-based measures for latent representations, stable under data perturbations.
result Demonstrated superior performance across various domains and tasks.
Generative model for SSc disease trajectories using deep learning.
problem Modeling complex disease trajectories in Systemic Sclerosis.
method Semi-supervised deep generative model with latent temporal processes.
result Learned latent processes enable personalized monitoring and prediction.
Context-aware recommender systems (CARSs) apply sensing and analysis of user context in order to provide personalized services. Adding context to a recommendation model is challenging, since the addition of context may increases both the dimensionality and sparsity of the model. Recent research has shown that modeling …
Model uses Preisach hysteresis to predict gig worker acceptance, reducing costs and improving fill rates.
problem Predicting and optimizing gig worker acceptance in labor markets.
method Preisach hysteresis model applied to neural network and XGBoost classifier for binary transaction outcomes.
result Model reduces total wage bill by 21.3% and increases expected fill rate by 9.7 pp.
New method for fitting graphical models with latent variables using regularized conditional likelihood.
problem Graphical modeling with latent variables and confounding dependencies.
method Regularized conditional likelihood for exponential family graphical models.
result Framework applicable to broader settings without knowing latent variables' distribution.
New method disentangles latent variables in nonstationary data.
problem Disentangling latent variables in nonstationary sequential data.
method NCTRL framework exploiting Markov assumption and temporal structure.
result Independent latent components can be recovered from nonlinear mixture without auxiliary variables.
Method learns latent dynamics of complex systems from noisy data.
problem Challenging to construct ROMs from noisy high-dimensional data.
method Recurrent stochastic variational deep kernel learning (SVDKL).
result Framework accurately predicts system evolution in low-dimensional latent spaces.
This paper tackles high-dimensional uncertainty quantification with semi-supervised learning.
problem High-dimensional uncertainty quantification due to the curse of dimensionality.
method Autoencoder for dimension reduction, DFN for mapping and reconstruction, GP for surrogate modeling, semi-supervised learning for accuracy.
result The framework effectively reduces uncertainty quantification and reliability analysis for high-dimensional problems.
ED-VAE improves VAEs by explicitly including entropy components in ELBO.
problem Limitations of traditional VAEs with ELBO in generating high-quality samples and interpreting latent spaces.
method Introduces ED-VAE, a re-formulation of ELBO that includes entropy and cross-entropy components.
result Significantly enhances model flexibility and improves interpretability and generative performance.
PABBO optimizes user utility learning from preferential feedback, significantly faster than traditional methods.
problem Computational inefficiency in Preferential Bayesian Optimization (PBO) methods.
method Amortized Bayesian Optimization (PABBO) using transformer neural processes and reinforcement learning.
result Significantly faster performance compared to traditional Gaussian process-based methods.
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.
This paper proposes Dirichlet Variational Autoencoder (DirVAE) using a Dirichlet prior for a continuous latent variable that exhibits the characteristic of the categorical probabilities. To infer the parameters of DirVAE, we utilize the stochastic gradient method by approximating the Gamma distribution, which is a comp…
spex-LVM infers interpretable latent factors from biomedical data.
problem Inability to learn sparse and interpretable hidden states.
method Factorial latent variable model with sparse priors and domain-relevant annotations.
result Robustly identifies relevant structure in RNA-seq datasets.
Improved DMs with DP-SGD for generating private images.
problem Low privacy of DMs and lack of good privacy-utility tradeoff.
method Adopt LDMs with DP-SGD on attention modules of LDMs.
result Generates high-quality DP images with reduced parameters.
New algorithms improve MPBART for HIV patient data.
problem Improving inference for multinomial outcomes in HIV patient data.
method Introduced two new algorithms for fitting MPBART.
result Better performance in MCMC convergence and predictive accuracy.
This study analyzes data science vocabulary changes over 13 years.
problem Understanding evolution of data science terms over time.
method Exploratory Data Analysis, Latent Semantic Analysis, Latent Dirichlet Analysis, N-grams Analysis.
result Identified new vocabulary and its incorporation into scientific literature.