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.
Generic Hitchin representations generate dense subgroups.
problem Understanding dense subgroups in SL_n(R) representations.
method Using a theorem by Rapinchuk, Benyash-Krivetz, and Chernousov.
result Generic Hitchin representations are strongly dense.
A new beta-VAE based regression model accelerates oilfield optimization studies.
problem Computational expense of full-physics reservoir simulations.
method beta-VAE for interpretable latent space representation, probabilistic dense layers for uncertainty quantification.
result Interpretable latent representation and quantified uncertainty for optimization decisions.
New representations of hyperbolic 3-manifold groups into larger groups.
problem Finding representations of hyperbolic 3-manifold groups into larger matrix groups.
method Holonomy representations from projective deformations of hyperbolic structures.
result First examples of strongly dense representations into SL(4,R) and SU(3,1). GANs can improve image reconstruction by using intermediate layers.
problem Improving the quality of image reconstruction using GANs.
method Exploiting the representation in intermediate layers of the generator.
result Intermediate layers in GANs can represent natural images with high visual fidelity.
The paper finds dense subgroups in certain Lie groups.
problem Finding dense subgroups in Lie groups.
method Constructing dense surface subgroups in specific Lie groups.
result Uniform lattices contain infinitely many dense Hitchin representations.
For text analysis, one often resorts to a lossy representation that either completely ignores word order or embeds each word as a low-dimensional dense feature vector. In this paper, we propose convolutional Poisson factor analysis (CPFA) that directly operates on a lossless representation that processes the words in e…
Maximal representations in symplectic lattices proven for most cases.
problem Understanding maximal representations in symplectic lattices.
method Analyzing mapping class group orbits and continuous deformations of maximal diagonal representations.
result Proof of maximal representations in most lattices of Sp(2n,R).
Deforms surface groups to be Zariski dense in SL(n,R)
problem Finding Zariski dense surface groups in SL(n,R)
method Deforming K-integral representations of surface groups result Generalizes Long and Thistlethwaite's method to SL(n,R)
NetSMF efficiently embeds large networks by sparse matrix factorization.
problem Learning latent representations for large-scale networks efficiently.
method NetSMF leverages spectral sparsification to efficiently sparsify and factorize a dense matrix.
result NetSMF achieves high efficiency and effectiveness on large-scale networks.
Graph neural network constructs a sparse latent point cloud from dense point clouds.
problem Efficiently reconstructing and simulating point clouds with fine details.
method Irregular graph convolutional neural network with non-isotropic operations.
result The model can reconstruct dense point clouds from a sparse latent representation.
We show that the bounded Borel class of any dense representation $ρ: G\to \PSL_n\bC$ is non-zero in degree three bounded cohomology and has maximal semi-norm, for any discrete group G. When n=2, the Borel class is equal to the 3-dimensional hyperbolic volume class. Using tools from the theory of Kleinian groups, …
ProbE model improves relational implication detection to 0.8143.
problem Improving inference of relational data to extract more useful information.
method Formal probabilistic model of relational implication using estimators based on empirical distribution.
result ProbE model outperforms existing approaches, achieving 0.8143 AUC on evaluation dataset.
DenseHMM improves HMMs by learning dense representations that enable gradient-based optimization.
problem Learning dense representations for hidden states and observables in HMMs.
method DenseHMM uses kernelized transition probabilities and two optimization schemes.
result DenseHMM achieves superior performance and expressiveness compared to standard HMMs.
Cataclysm deformations study Anosov representations and their convergence.
problem Understanding convergence of Anosov representations under deformation.
method Cataclysm deformation of Anosov representations using twisted transverse cocycles.
result Uniform convergence of cataclysm deformations on compact sets.
Cataclysm deformations study Anosov representations, leading to new formulas and non-open sets.
problem Understanding Anosov representations and their deformations.
method Cataclysm deformations based on twisted transverse cocycles.
result Uniform convergence of cataclysm deformations on compact sets.
Motion analysis is used in computer vision to understand the behaviour of moving objects in sequences of images. Optimising the interpretation of dynamic biological systems requires accurate and precise motion tracking as well as efficient representations of high-dimensional motion trajectories so that these can be use…
ViCE uses superpixels to enhance self-supervised learning for better dense visual embeddings.
problem Lack of high-resolution feature maps from self-supervised models.
method Superpixels for dense representation learning, contrasting over regions.
result Improves unsupervised semantic segmentation on benchmarks like Cityscapes and COCO.
Most artificial networks today rely on dense representations, whereas biological networks rely on sparse representations. In this paper we show how sparse representations can be more robust to noise and interference, as long as the underlying dimensionality is sufficiently high. A key intuition that we develop is that …
New domains of discontinuity found for Anosov representations.
problem Understanding Anosov representations acting on homogeneous spaces.
method Constructing open domains of discontinuity for Anosov representations acting on specific homogeneous spaces.
result Describes the largest possible open domains of discontinuity for Zariski dense Anosov representations.
Odd-dimensional SL(n,Q) contains dense surface subgroups.
problem Finding dense subgroups in SL(n,Q) for odd n.
method Constructing a continuous path of representations.
result Existence of dense surface subgroups in SL(n,Q) for odd n.
Latent representations are the essence of deep generative models and determine their usefulness and power. For latent representations to be useful as generative concept representations, their latent space must support latent space interpolation, attribute vectors and concept vectors, among other things. We investigate …
Develops a novel method to estimate non-Gaussian hydraulic conductivities efficiently.
problem Estimation of non-Gaussian hydraulic conductivity fields in subsurface flow models.
method Integrates adversarial autoencoders with residual dense convolutional networks for parameterization and surrogate modeling.
result Significantly reduces computation time for accurate inversion results.
Generic Hitchin representations avoid hyperplanes in Lie algebras.
problem Properties of Hitchin representations in Lie algebras.
method Defined J(ρ) and used hyperplanes in Lie algebras to show J(ρ)∩H=∅. result Generic G-Hitchin representations avoid hyperplanes in the Lie algebra of G. Detection of dense cycles in graphs reveals a gap between easy detection and hard recovery.
problem Detecting and recovering dense cycles in Erdős-Rényi graphs.
method Characterization of computational thresholds for detection and recovery using low-degree polynomial algorithms.
result A gap exists between the detection and recovery thresholds for certain parameter regimes.
The paper explores mapping class group quotients by Dehn twists and their representations.
problem Finite quotients and representations of mapping class groups by powers of Dehn twists.
method Construction of finite quotients using representations with Zariski dense images into semisimple Lie groups, and Long and Moody's method.
result The Fibonacci TQFT representation is a specialization of the Jones representation in genus 2.
We prove that a dense subgroup of Homeo+(I) is not elementary amenable. We also show that the topological group Homeo+(I) does not satisfy the Stability of the Generators Property, moreover, any finitely generated subgroup of Homeo+(I) admits a faithful discrete representation …
Study shows how to detect representation extendability using conformal measures.
problem Detecting extendability of representations using conformal measures.
method Using higher rank conformal measures and self-joinings of groups.
result Affirmative answer to detect extendability of representations.
Bayesian networks are typically faithful, with implications for causal inference.
problem Determining the typicality of faithfulness in Bayesian networks.
method Analysis of Bayesian networks over a given DAG, parametrized by conditional exponential families, and nonparametric conditional densities.
result The faithful Bayesian networks are dense and open with respect to the total variation metric, extending existing results for specific classes of Bayesian networks.
We define a Toledo number for actions of surface groups and complex hyperbolic lattices on infinite dimensional Hermitian symmetric spaces, which allows us to define maximal representations. When the target is not of tube type we show that there cannot be Zariski-dense maximal representations, and whenever the existenc…
Improved autoencoders guide latent sentence representations for better text generation and manipulation.
problem Current autoencoders struggle to maintain coherent latent spaces for meaningful text manipulations.
method Adversarial autoencoders with a denoising objective (DAAE) to guide latent space geometry.
result DAAE provides the best trade-off between generation quality and reconstruction capacity.
Improves NF for complex data distributions with multiple modes.
problem Difficulty in handling data distributions with multiple isolated modes.
method Proposes a new framework using variational latent representation to improve NF.
result Significantly more powerful for generating data distributions with multiple modes.
Proposes LMSSC for multi-view semi-supervised classification.
problem Leveraging multiple complementary views for improved classification.
method Semi-supervised classification with latent multi-view representation learning.
result Unified framework for latent representation learning, graph construction, and label propagation.
Interventional data helps identify latent factors without distributional assumptions.
problem Identifying latent factors from interventional data without distributional assumptions.
method Leveraging geometric signatures of latent factors' support from interventional data.
result Latent causal factors can be identified up to permutation and scaling given data from perfect do-interventions.
PRESTO maps latent representations across diverse ML models.
problem Understanding variability in latent representations across different ML models.
method Uses persistent homology to characterize latent spaces and measure their pairwise similarity.
result Preserves desirable properties and enables sensitivity analysis of latent representations.
Unified framework for learning function representations using INRs and Transformers.
problem Scalability and efficiency limitations in existing generative models.
method Integrates INRs and Transformer-based hypernetworks into latent variable models.
result Improved scalability, expressiveness, and generalization over existing models.
This work studies how contrastive learning extracts features from unlabeled data.
problem How neural networks trained by contrastive learning can extract features from unlabeled data.
method Formal analysis of contrastive learning's feature learning process, considering two types of features: sparse and dense.
result Contrastive learning using ReLU networks can learn sparse features if proper augmentations are adopted.
LCIT tests conditional independence using latent representations.
problem Detecting conditional independencies in statistical and machine learning tasks.
method Generative framework for learning latent representations of target variables X and Y, then testing for remaining dependencies.
result LCIT outperforms state-of-the-art baselines consistently under different metrics and settings.
Unified framework for disentangled representations using mechanistic independence.
problem Identifiability of disentangled latent factors under statistical dependencies.
method Introduces mechanistic independence to characterize latent factors by their actions on observed variables, proposing various independence criteria.
result Establishes conditions for identifiability of latent subspaces without statistical assumptions.
PLIs improve classifier performance by fine-tuning latent representations.
problem Difficult interpretation of high-dimensional latent representations in neural networks.
method Back-propagation of manual changes to low-dimensional embeddings using t-distributed stochastic neighbourhood embeddings.
result Manual separation of class clusters in latent space enhances classifier performance.
A new method, REC, compresses images by encoding their latent representations efficiently.
problem Efficiently compressing single images with latent representations.
method Relative Entropy Coding (REC) that directly encodes latent representations with codelength close to relative entropy.
result REC is more efficient for single image compression compared to previous methods and is competitive for lossy compression.
Paper proposes a new method for learning latent representations for control problems.
problem Learning representations for control algorithms in high-dimensional observation spaces.
method Formulated a loss function (PCC) consisting of prediction, consistency, and curvature terms, derived an amortized variational bound.
result The new variational-PCC learning algorithm leads to superior control performance and more stable training.
We show the set of faithful representations of a closed orientable hyperbolic surface group is dense in both irreducible components of the PSL(2,K) representation variety, where K is the field of real or complex numbers, answering a question of W. Goldman. We also prove the existence of faithful representations into PU…
We identify action representations from video data, proving their statistical benefits.
problem Identifying latent action policies from video data.
method Entropy-regularized LAPO objective, formalizing desiderata for action representations.
result Entropy-regularized LAPO identifies action representations satisfying desiderata under suitable conditions.
Recent success in deep reinforcement learning for continuous control has been dominated by model-free approaches which, unlike model-based approaches, do not suffer from representational limitations in making assumptions about the world dynamics and model errors inevitable in complex domains. However, they require a lo…
Latent factor models are the canonical statistical tool for exploratory analyses of low-dimensional linear structure for an observation matrix with p features across n samples. We develop a structured Bayesian group factor analysis model that extends the factor model to multiple coupled observation matrices; in the cas…
Learning data representations that reflect the customers' creditworthiness can improve marketing campaigns, customer relationship management, data and process management or the credit risk assessment in retail banks. In this research, we adopt the Variational Autoencoder (VAE), which has the ability to learn latent rep…
New architecture improves decision-making in dense traffic.
problem Designing accurate and compact learning architectures for autonomous vehicles in crowded conditions.
method Attention-based architecture that accounts for interactions between vehicles.
result Significant performance gains and interpretable interaction patterns.