Dropout improves GAN outputs by preserving input constraints.
problem Generating multiple outputs from one input.
method Using Dropout in GANs to maintain input constraints.
result Enhanced generation of diverse outputs from a single input.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “latent-space constraint”
BEGAN-CS prevents mode collapse in GANs by adding a latent-space constraint.
problem Mode collapse in BEGAN during training.
method Introducing a latent-space constraint in the loss function of BEGAN.
result BEGAN-CS improves training stability and suppresses mode collapse.
Method reformulates constrained optimization as latent space inference.
problem Optimizing black-box functions with hard constraints.
method Posterior inference in latent space using flow-based models and diffusion models.
result Method achieves superior performance across various tasks.
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.
Improves VAE latent space by balancing capacity and disentanglement.
problem Hard to achieve both high capacity and disentanglement in VAE latent space.
method Formulates soft-constrained optimization problem to address both properties.
result EC and weight-filter method improve latent space quality and performance.
Unsupervised machine learning helps design complex experiments more efficiently.
problem Designing experiments with many factors and constraints is challenging and costly.
method Applied a beta variational autoencoder (beta-VAE) to represent trials in a low-dimensional latent space.
result Generated pragmatic designs with fewer trials while maintaining objectives.
Deep generative neural networks have proven effective at both conditional and unconditional modeling of complex data distributions. Conditional generation enables interactive control, but creating new controls often requires expensive retraining. In this paper, we develop a method to condition generation without retrai…
COLD optimizes samples by projecting them into a latent space, ensuring they are distinct from training data.
problem Optimizing discrete data for specific characteristics using gradient-based methods often leads to dissimilar samples.
method Constrained Optimisation with Latent Distributions (COLD) to find optimal samples similar to but distinct from training data.
result COLD generates diverse, high-quality samples with similar properties to training data.
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 -ARM gradient estimator to dynamically adjust latent space dimensions.
result The latent space can be pruned effectively without violating reconstruction error constraints.
Paper introduces CageBO for optimizing complex public policy problems.
problem Complex decision-making and implicit constraints in public policy.
method CageBO framework using conditional variational autoencoder.
result CageBO outperforms baselines in optimizing large-scale police redistricting.
TLR learns better latent representations for unsupervised domain adaptation.
problem Learning models in a target domain using data from a source domain.
method Designing a simple linear autoencoder objective function to derive robust latent representations.
result TLR reduces domain shift and preserves common properties of both domains.
Proposes a framework to optimize complex data constraints effectively.
problem Challenges in optimizing high-dimensional, noisy data with constraints.
method Multi-stage Constrained Optimization Framework (MCOF) with EC-VAE, UT, and CPM.
result Validated on synthetic and real-world problems, achieving feasible solutions.
NE-VAE prevents posterior collapse in VAEs by embedding neighbors in latent space.
problem Posterior collapse in VAEs when strong decoders are used.
method Neighbor embedding in latent space to prevent collapse.
result NE-VAE produces qualitatively different latent representations with active latent dimensions.
Unified approach for learning state representations from streaming data.
problem Learning reusable state representations from high-dimensional, non-stationary data.
method Unified mathematical formulation for learning latent relations, enabling flexible and principled shaping of latent space.
result Improved understanding and evaluation of existing unsupervised learning approaches.
New method uses cycle consistency to enforce invariance in latent space.
problem Learning meaningful and independent factors of variation in datasets.
method Two separate latent subspaces, cycle consistency constraints, deep information bottleneck.
result Identifies more meaningful factors leading to sparser and interpretable models.
VELC model detects anomalies in time series data better than existing methods.
problem Anomaly detection in time series data.
method VELC model based on Variational AutoEncoder with re-Encoder and Latent Constraint network.
result VELC model outperforms state-of-the-art methods on benchmark datasets.
A new algorithm learns causal relationships from multimodal data.
problem Discovering causal relationships in exploratory settings without prior information.
method causalPIMA algorithm using multimodal data and physics constraints.
result Learned causal structure and key features in fully unsupervised settings.
MAVEN improves multi-agent exploration by hybridizing value and policy-based methods.
problem Exploration and suboptimality in complex multi-agent environments.
method MAVEN combines value and policy-based approaches with a latent space for hierarchical control.
result MAVEN achieves significant performance improvements on challenging multi-agent tasks.
Regularization preserves topological data structure in autoencoders.
problem Ensuring topological data structure preservation in autoencoders.
method Regularization using Legendre nodes to preserve manifold embedding.
result Regularized autoencoders ensure one-to-one embedding of data manifolds.
Proposes a new framework for image generation using classification latent space representations.
problem Combining discriminative and dense representations for image generation and reconstruction.
method Discriminative modeling framework using manipulated supervised latent representations.
result Higher classification accuracy and visually realistic image generation compared to existing models.
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.
δ-CLUE generates diverse explanations for model uncertainty.
problem Lack of constraints in generating explanations for uncertainty estimates.
method Augmenting CLUE approach to provide a set of plausible explanations.
result Returns a set of diverse inputs that yield confident predictions.
Generative Topological Networks (GTNs) simplify latent space generation.
problem Complex latent space generation in generative models.
method GTNs use topology theory for a simple, supervised learning approach.
result GTNs improve upon VAEs and converge quickly, generating realistic samples.
In recent years, neural network approaches have been widely adopted for machine learning tasks, with applications in computer vision. More recently, unsupervised generative models based on neural networks have been successfully applied to model data distributions via low-dimensional latent spaces. In this paper, we use…
Structured and sparse partial least squares coherence for multivariate cortico-muscular analysisstat.AP
New algorithm extracts shared latent space for cortico-muscular interactions.
problem Challenges of high dimensionality and limited sample sizes in multivariate cortico-muscular analysis.
method Structured and sparse partial least squares coherence (ssPLSC) algorithm.
result ssPLSC achieves competitive or better performance in scenarios with limited sample sizes and high noise levels.
Proposes a method to generate realistic counterfactuals by learning relationships.
problem Counterfactual explanations often ignore intrinsic relationships between data attributes.
method Uses a variational auto-encoder to learn relationships and perturb the latent space.
result The model preserves relationships and generates realistic counterfactuals.
X-VAE uses data-adaptive Gaussian priors to improve latent space modeling.
problem Limitations of standard Gaussian priors in complex datasets.
method Data-adaptive Gaussian prior derived from pretrained autoencoder latent codes.
result Improved latent space modeling and generation quality.
Physics-Constrained Predictive Molecular Latent Space Discovery with Graph Scattering Variational Autoencoderphysics.chem-ph
Model predicts stable molecules with AI and physics constraints.
problem Designing stable molecules with limited data.
method Graph Scattering Variational Autoencoder with physical constraints.
result Model generates stable molecules with desired properties.
Efficient tensor completion method using rank minimization on TR latent space.
problem High model sensitivity and exponential model possibilities in TR decomposition.
method Nuclear norm regularization on latent TR factors, ADMM scheme.
result Superior performance and efficiency compared to state-of-the-art algorithms.
BOSS optimizes string inputs using string kernels and genetic algorithms.
problem Optimizing string inputs with constraints.
method Bayesian optimization over string kernels and genetic algorithms.
result Significantly improved optimization across various string constraints.
This paper uses deep neural networks for one-class classification by splitting normal data into typical and atypical subsets.
problem Training deep neural networks with only one class of data for one-class classification.
method Intra-class splitting to create typical and atypical subsets, using binary loss and auxiliary subnetworks.
result The method outperformed seven baselines and had comparable performance to state-of-the-art methods on image datasets.
Simple Deep LDA models achieve accuracy competitive with softmax baselines.
problem Training Deep LDA models by maximum likelihood estimation leads to overlapping or collapsed class clusters.
method Proposed a constrained Deep LDA formulation with geometric constraints to fix class means and covariance.
result MLE becomes stable under geometric constraints, yielding well-separated class clusters.
Disentangling Speech and Non-Speech Components for Building Robust Acoustic Models from Found Dataeess.AS
This work disentangles speech and non-speech components from found data.
problem Building robust acoustic models from found data with non-standard variations.
method Latent Stochastic Models and Multinode Latent Space Variational Autoencoders (VAE).
result Speech and music can be separated in the latent space of a VAE, independent of the language.
GLAD improves latent graph generation by quantizing discrete latent space.
problem Latent space graph generative models lack performance and make unnatural assumptions.
method Adapting diffusion bridges to a discrete latent space, avoiding data space decompositions.
result GLAD achieves competitive performance on graph benchmark datasets.
ClusterGAN clusters latent space in GANs, preserving latent space interpolation across categories.
problem Clustering in GAN latent space is not retained.
method Proposes ClusterGAN, using mixture of one-hot and continuous latent variables, and an inverse network trained jointly with a clustering loss.
result Demonstrates superior clustering performance on synthetic and real datasets.
A new method to learn EBM in latent space for better data modeling.
problem Efficiently modeling data with complex structures.
method Joint learning of latent space EBM and top-down network using maximum likelihood and MCMC sampling.
result Simple EBM in latent space captures data regularities effectively and performs well in generation and anomaly detection.
New method uses Diffusion Maps for latent space modeling of dynamical systems.
problem Building reduced dynamical models from time series data.
method Two rounds of Diffusion Maps on latent coordinates, with lifting back to ambient space.
result Approximation of full state functions in reduced coordinates.
This research examines the geometry of latent spaces in push-forward generative models.
problem Tendency of deep generative models to output samples outside target distribution support.
method Geometric measure theory and truncation method to enforce simplicial cluster structure.
result Proves sufficient condition for optimality in latent space geometry.
New metrics and transformations improve understanding of generative models' latent spaces.
problem Understanding the structure of latent spaces in generative models.
method Developed new metrics and transformations to study latent space geometries.
result Improved meaningful distances and data visualizations in latent spaces.
A new method learns manifold-valued latents without an encoder.
problem Distorting data with intrinsic non-Euclidean structure.
method Riemannian generative decoder that learns latents directly.
result Learned representations respect the prescribed geometry and capture intrinsic non-Euclidean structure.
EXoN creates an explainable latent space for semi-supervised learning.
problem Creating an explainable latent space for semi-supervised learning.
method EXoN combines VAE with SCI (Soft-label Consistency Interpolation) to create an explainable latent space.
result EXoN reduces the cost of investigating representation patterns on the latent space.
Researchers analyze and improve latent space in NAR models.
problem Latent space resolution and range issues in NAR models.
method Detailed analysis of GNN latent space structure, proposing and testing solutions.
result Improvements in majority of algorithms on CLRS-30 benchmark.
LOL-BO improves latent space Bayesian optimization over structured inputs.
problem Optimizing complex functions over high-dimensional, structured search spaces.
method Adapting trust regions from high-dimensional to structured settings, using a DAE to map inputs into a latent space.
result Achieves up to 20x improvement over state-of-the-art methods.
We extend GAN latent space projection for Gaussian priors.
problem Non-trivial latent space projection for GANs with Gaussian priors.
method Extend previous techniques to Gaussian priors.
result Demonstrated effectiveness of extended technique.
Investigates latent variable models for useful generative concept representations.
problem Creating latent representations that support various concepts and attributes.
method Latent variable modeling, including latent variable models, latent representations, and latent spaces.
result Hierarchical latent representations and latent space vectors and geometry are effective for generative concept representations.
Estimates latent positions in 1D torus from noisy pairwise affinities.
problem Estimating latent positions in a 1D torus from noisy pairwise affinities.
method Introduced an estimation procedure with provable localization error of .
result The estimation procedure provably localizes latent positions with a maximum error of .
TALBO optimizes latent spaces for evolving design objectives.
problem Temporal drift in design objectives.
method GP-prior variational autoencoder for time-varying latent space.
result Consistently outperforms LSBO baselines across varying drift speeds and objectives.
The work investigates deep generative models, which allow us to use training data from one domain to build a model for another domain. We propose the Variational Bi-domain Triplet Autoencoder (VBTA) that learns a joint distribution of objects from different domains. We extend the VBTAs objective function by the relativ…