FMI uses matching to mimic interventions for causal feature learning.
problem Challenges in causal discovery from observational data.
method Feature Matching Intervention (FMI) using matching to emulate perfect interventions.
result FMI outperforms in identifying causal features from observational data.
Generative model for realistic text generation using feature matching.
problem Applying GAN to text generation due to convergence issues and difficulties with discrete data.
method Employing a long short-term memory network as generator and a convolutional network as discriminator. Matching latent feature distributions via a kernelized discrepancy metric.
result Superior performance in generating realistic-looking sentences compared to standard GAN.
This work makes latent features from relational learning more interpretable.
problem Interpreting latent features from relational learning.
method Clustering instances and their relations to learn interpretable latent features.
result Latent features from clustering are interpretable and capture data properties.
Decentralized learning for matching markets with time-varying preferences.
problem Matching between competing agents and supply arms with time-varying preferences.
method Linear contextual bandit framework, learning algorithms to identify latent environment and stable matchings.
result Achieve instance-dependent logarithmic regret, applicable for large markets.
First place solution for cross-device user matching in online advertising.
problem Identifying same users across multiple devices from browsing logs.
method Pairwise classification using unsupervised neural feature ensemble and supervised classifiers.
result Improved accuracy in cross-device user matching compared to traditional methods.
New methods improve matching in high-dimensional data.
problem Matching in high-dimensional data is challenging due to the curse of dimensionality.
method Pseudo-metric learning approach using MLPs or siamese neural networks.
result Neural-net-based methods outperform traditional matching methods in simulations and real data.
A new method resolves permutation issues in shuffled linear regression for large-scale applications.
problem Estimating latent features through linear transformation with unknown permutations.
method Spectral matching method to align spectral components of measurement and feature covariances.
result Achieves accurate estimates in shuffled LS and LASSO settings with sufficient samples.
SDE Matching eliminates simulation for training Latent SDEs, achieving similar performance.
problem Training Latent SDEs with adjoint sensitivity methods is computationally expensive and limited.
method SDE Matching, inspired by Score- and Flow Matching, eliminates simulation for training Latent SDEs.
result SDE Matching achieves performance comparable to adjoint sensitivity methods while reducing computational complexity.
Improves deep learning training by matching mini-batch distributions.
problem Overfitting and noise in mini-batch training.
method ITDM, which matches the moments of mini-batch distributions to reduce overfitting.
result ITDM reduces overfitting and improves DNN training.
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.
Generative model improves latent space convexity through adversarial training on interpolations.
problem Improving latent space convexity in generative models.
method Adversarial training on latent space interpolations within an AE-GAN architecture.
result Convex latent distribution of generated images, preserving realistic resemblances.
New method generates data across domains using latent variables.
problem Understanding and adapting to distribution changes across domains.
method Causal Generative Domain Adaptation Network (CG-DAN) with latent variable decomposition.
result CG-DAN improves learning efficiency and data generation across domains.
Improved text matching model using deconvolutional networks.
problem Text sequence matching challenges.
method Jointly optimizing generative and discriminative objectives with deconvolutional networks.
result Significantly outperforms sentence-encoding baselines, especially in semi-supervised settings.
Unified framework for self-supervised learning via latent distribution matching.
problem Lack of a unifying theoretical framework for diverse SSL methods.
method Casting SSL as latent distribution matching (LDM): maximizing alignment and uniformity.
result Derives a Bayesian filtering model and proves identifiable latent representations.
Proposes a VAE with a discrete bottleneck for better text generation.
problem VAEs struggle with latent variable auto-regressive decoding in text generation.
method Introduces a discretized bottleneck to enforce latent feature matching in a compact space.
result Demonstrates improved text generation capabilities across various tasks.
LSDM uses unpaired data to match latent space distributions for generative modeling.
problem Generating high-quality images with limited paired data.
method Two-stage approach: latent space learning from paired and unpaired data, followed by joint distribution matching.
result LSDM enhances geometric fidelity in generated outputs and provides theoretical insights into LDMs.
A new method generates implied volatility surfaces without arbitrage issues.
problem Generating volatility surfaces without financial arbitrage constraints.
method Variational autoencoder with flow-matching for latent space learning.
result Model closely reproduces empirical distribution and satisfies no-arbitrage conditions.
Unsupervised matching method for relational data without alignment info.
problem Matching objects in different relational datasets without correspondence info.
method Model latent vectors, estimate by likelihood, project onto shared space.
result Preserves structural information in latent vectors across datasets.
Dualities in physics help in machine learning tasks.
problem Applying dualities to improve machine learning performance.
method Enforcing dual representations in neural networks and using additional loss terms.
result Computers can find dualities, linking physics and machine learning.
This paper introduces Gumbel-Sinkhorn networks for learning latent matchings.
problem Learning in latent variable models with permutations is difficult due to combinatorial intractability.
method Approximates maximum-weight matching using the Sinkhorn operator, extending Gumbel-Softmax.
result Demonstrates effectiveness on sorting, jigsaw puzzles, and neural signal identification tasks.
Polynomial-time algorithm matches correlated random graphs with non-vanishing correlation.
problem Matching correlated random graphs with non-vanishing edge correlation.
method Iterative algorithm for polynomial-time recovery of latent matching.
result Algorithm succeeds in recovering latent matching as long as edge correlation is non-vanishing.
Generative model disentangles 3D shapes into independent factors.
problem Learning rich representations of deformable 3D shapes.
method Supervised 3D mesh-convolutional Variational AutoEncoder with latent feature disentanglement.
result Explicit disentanglement of latent factors improves shape generation and downstream tasks.
Researchers analyze neural process architectures and their representational capacities.
problem Understanding what functions can be represented by different neural process architectures.
method Analyzing four types of neural process architectures: CNPs, ANPs, TNPs, and their latent variants.
result Prove these architectures form a strict hierarchy and characterize their representational capabilities.
A hierarchical model shows how scaling laws emerge from sequential feature recovery.
problem Emergence of scaling laws from feature learning in multi-layer networks.
method Layer-wise spectral algorithm adapted to compositional structure, sequential feature detection.
result Sequential detection of latent features, leading to explicit power-law decay of prediction error.
Enhances learning of structured distributions using nonlinear denoising score matching.
problem Learning structured distributions from noisy data.
method Latent Nonlinear Denoising Score Matching (LNDSM) integrating nonlinear dynamics with VAE-based latent score matching.
result LNDSM achieves superior sample quality and variability compared to structure-agnostic methods.
Study sharpens threshold for matching correlated graphs without labels.
problem Matching latent vertex correspondences in correlated random graphs.
method Analyzes information-theoretic limits for correct vertex matching in sub-sampled graphs.
result Establishes a sharp information-theoretic threshold for vertex matching recovery.
VAELLS learns latent manifold structure to improve VAE model accuracy.
problem VAEs struggle with mismatched latent structure and global structure.
method Integrates learnable manifold model into latent space of VAE.
result Improves model accuracy by matching prior to data manifold structure.
Diversifies reply suggestions for IM systems using M-CVAE.
problem Improving diversity of automated reply suggestions in instant messaging systems.
method Formulated a generative latent variable model with Conditional Variational Auto-Encoder (M-CVAE) to diversify responses.
result Increased diversity by ~30-40% without significant impact on relevance.
Advances deep latent variable models for more flexible text generation.
problem Limited representation power of VAEs due to Gaussian assumptions and posterior collapse.
method Develops sample-based variational distributions and an LVM to directly match aggregated posterior to prior.
result Demonstrates improved text generation in various scenarios.
Framework generates causal probabilities from observational data.
problem Generating causal probabilities from observational data.
method Moment-matching graph-networks for causal inference.
result Automated sampling of latent space conditional probability distributions.
The paper provides convergence guarantees for ODE-based generative models using transformers.
problem Theoretical guarantees for ODE-based generative models.
method A pre-trained autoencoder maps inputs to a latent space, and a transformer predicts the velocity field.
result The distribution of samples generated via estimated ODE flow converges to the target distribution in Wasserstein-2 distance.
In many statistical problems, a more coarse-grained model may be suitable for population-level behaviour, whereas a more detailed model is appropriate for accurate modelling of individual behaviour. This raises the question of how to integrate both types of models. Methods such as posterior regularization follow the id…
New framework tackles stochastic latent subgroup heterogeneity in online decision-making.
problem Stochastic latent heterogeneity in online decision-making where individual responses vary with unobserved subgroups.
method Latent heterogeneous bandit framework using EM-greedy algorithm to learn subgroup probabilities and reward parameters.
result Achieves optimal estimation and classification guarantees, revealing a fundamental stochastic barrier in online decision-making.
McGAN uses feature matching IPMs to train GANs more stably.
problem Training stable GANs.
method Feature matching IPMs for mean and covariance.
result McGAN minimizes meaningful loss between distributions.
ICIL learns policies invariant to multiple environments, improving generalization.
problem Learning policies from multiple environments leads to spurious correlations.
method ICIL learns invariant feature representations and a matching imitation policy.
result ICIL policies generalize better to unseen environments.
PFM generates novel samples on data manifolds using pullback geometry.
problem Generating novel samples on complex data manifolds.
method Pullback Flow Matching framework leveraging pullback geometry and isometric learning.
result PFM achieves improved manifold learning and generative performance.
Method evaluates disentanglement in DLVMs, including those not aligned with latent axes.
problem Evaluate disentanglement in DLVMs, especially those not aligned with latent axes.
method Proposes a statistical method to discover generative factors of a dataset.
result Empirically demonstrates the advantage of the method on two datasets.
Proposes a method to learn sparse and low-rank interactions in Ising models with latent variables.
problem Learning sparse interactions in Ising models with latent variables.
method Sparse + low-rank decomposition of Ising model parameters using convex regularized likelihood problem.
result Consistency properties in high-dimensional settings with growing number of variables and samples.
DMAE learns shared latent space from unpaired data.
problem Learning shared latent space from unpaired multi-modal data.
method Formulates cross-domain representation learning and object matching problem, optimizes autoencoders and pairing.
result Promising results in image captioning and unsupervised classifier learning.
A new method for generative modeling of discrete data using geometric latent subspaces.
problem Learning generative models for discrete data with statistical dependencies.
method Geometric latent-subspace framework in exponential parameter space of product manifolds of categorical distributions.
result Low-dimensional latent space encodes statistical dependencies and accurately models high-dimensional discrete data.
Algorithm generates diverse images of the same subject while maintaining specific aspects.
problem Training GANs to generate realistic, identity-matched images.
method Pairwise training scheme with Siamese discriminators.
result Algorithm produces convincing, identity-matched photographs.
Generalizes latent feature models for mixed data types.
problem Lack of models for heterogeneous datasets with mixed data types.
method Bayesian nonparametric latent feature model for mixed data.
result Model automatically infers feature complexity and binary latent features.
The paper explores methods for inference in multiplicative latent force models.
problem Inference in hybrid models combining mechanistic and flexible components.
method Two methods of approximate inference: gradient matching and mixtures of local approximations.
result Comparison of methods on simulated and motion capture data.
LOL method simplifies forming linear combinations of latent variables.
problem Lack of general-purpose methods for manipulating latent variables.
method Latent Optimal Linear combinations (LOL) method.
result LOL simplifies creation of expressive low-dimensional representations.
GRAMPA algorithm recovers latent vertex correspondence in correlated graphs with high probability.
problem Recovering latent vertex correspondence between unlabeled, edge-correlated weighted graphs.
method Spectral graph matching algorithm, GRAMPA, with exact recovery guarantees for Erdős-Rényi graphs.
result GRAMPA exactly recovers latent vertex correspondence with high probability for Erdős-Rényi graphs with edge correlation coefficient 1−σ2 and average degree at least polylog(n) when σ≲1/polylog(n). 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.
Extends IBP for non-diagonal latent covariance structures, improving feature recovery and denoising.
problem Modeling latent features with smoothness characteristics.
method Extend Indian Buffet Process to include non-diagonal latent covariance structures.
result Smoothness prior improves feature recovery and denoising under appropriate conditions.
Paper introduces Latent-CLIP for efficient text-image comparison in latent space.
problem Efficiently compare text and images in latent space without costly decoding.
method Trains CLIP model in latent space, uses Latent-CLIP rewards for noise optimization, and guides generation away from harmful content.
result Latent-CLIP matches CLIP performance on text-image classification and harmful content detection.