Developed a half-space model for pseudo-hyperbolic space.
problem Modeling pseudo-hyperbolic space for any dimensions.
method Created an isometric embedding of pseudo-hyperbolic space into a half-space.
result Geodesics, totally geodesic submanifolds, horospheres, and isometry group are described in the half-space model.
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.
Empirical mode modeling improves state-space analysis of noisy data.
problem Analyzing nonlinear systems with noisy data.
method Combining empirical mode decomposition with empirical dynamic modeling.
result Empirical mode modeling enhances state-space representations in noisy data.
Localizes smooth spaces to study their homotopy properties.
problem Understanding the homotopy theory of smooth spaces.
method Model category localization, Quillen equivalences, fibrant replacement.
result Localisation of smooth spaces agrees with motivic-style R-localisation. We prove that the moduli space of the pseudo holomorphic curves in the A-model on a symplectic torus is homeomorphic to a moduli space of Feynman diagrams in the configuration space of the morphisms in the B-model on the corresponding elliptic curve. These moduli spaces determine the A∞ structure of the both …
Characterizes higher rank model geometries using antipodal sets.
problem Identifying higher rank model geometries among Hadamard spaces.
method Using antipodal sets at infinity to characterize model geometries.
result Characterizes Riemannian symmetric spaces, Euclidean buildings, and products as higher rank model geometries.
One of the key issues in the analysis of machine learning models is to identify the appropriate function space and norm for the model. This is the set of functions endowed with a quantity which can control the approximation and estimation errors by a particular machine learning model. In this paper, we address this iss…
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.
Generative models for function-valued data in infinite dimensions.
problem Lack of semantics relating discretized data to underlying functional forms.
method Generalized diffusion models to function space, using Gaussian measures on Hilbert spaces.
result Explicit specification of function space allows unconditional and conditional generation of function-valued data.
We analyze the possibility of defining infinite-dimensional manifolds as ringed spaces. More precisely, we consider three definitions of manifolds modeled on locally convex spaces: in terms of charts and atlases, in terms of ringed spaces, and in terms of functored spaces, as introduced by Douady in his thesis. It is s…
Develops methods to measure and set function-space learning rates in neural networks.
problem Measuring and optimizing changes in neural network output functions.
method Efficient methods to measure and set function-space learning rates, requiring minimal computational overhead.
result Demonstrates FLeRM (Function-space Learning Rate Matching) for hyperparameter transfer across model scales.
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.
Paper proposes a method to improve MCMC sampling for energy-based models.
problem MCMC sampling of energy-based models is often not mixing in high-dimensional data.
method Proposes using a flow-based model as a backbone to correct the energy-based model, enabling mixing in latent space.
result MCMC sampling of the corrected EBM in the latent space mixes well and traverses modes in the data space.
We analyze the information-theoretic limits for the recovery of node labels in several network models. This includes the Stochastic Block Model, the Exponential Random Graph Model, the Latent Space Model, the Directed Preferential Attachment Model, and the Directed Small-world Model. For the Stochastic Block Model, the…
We prove affirmatively the conjecture raised by J. Mostovoy; the space of short ropes is weakly homotopy equivalent to the classifying space of the topological monoid (or category) of long knots in R3. We make use of techniques developed by S. Galatius and O. Randal-Williams to construct a manifold space mo…
Paper analyzes latent space geometry in generative models using Fisher information.
problem Understanding the structure of latent spaces in generative models.
method Reconstructs Fisher information metric from generated samples and posterior distribution.
result Reveals fractal structure and abrupt changes in Fisher metric at phase boundaries.
Extends SGM to functional spaces for multimodal data.
problem Modeling densities in functional spaces.
method Represent data in spectral space, dissociate stochastic and space-time components, use SGM for sampling.
result Demonstrates effectiveness on multimodal datasets.
Pixel-space diffusion models outperform latent models on high-resolution image synthesis.
problem Efficiency and quality trade-off in high-resolution image synthesis.
method Sigmoid loss-weighting, simplified architecture, and resolution scaling.
result Achieved 1.5 FID on ImageNet512, new SOTA results on other datasets.
A new statistical model uses Orlicz-Sobolev spaces with Gaussian weight.
problem Statistical modeling of infinite-dimensional probability measures.
method Affine statistical bundle on Gaussian Orlicz-Sobolev space.
result Provides tools for solving infinite-dimensional evolution problems.
This paper is devoted to the problem of choosing the most suitable model of a geometrical system for describing the real crystallographic space. It has been shown that all 230 crystallographic groups used to describe the crystalline structures in a Euclidean space can be presented by elliptic motions in the closed spac…
The paper studies biharmonic functions and bi-eigenfunctions on spheres and model spaces.
problem Characterizing biharmonic functions and eigenfunctions on model spaces.
method Analyzes bi-Laplacian on spheres, derives integral formulas for biharmonic solutions, and classifies proper biharmonic functions.
result Proper biharmonic functions on model spaces can be constructed from eigenfunctions of the factor sphere.
Paper develops a consistent model selection framework for learning Hypotheses Space from data.
problem Avoiding overfitting in complex spaces with limited data.
method Develops a model selection framework based on Learning Spaces, selecting a Hypotheses Space from data.
result The method converges with probability one to a target Hypotheses Space, providing a consistent framework for model selection.
Predicts cryptocurrency prices with deep state-space model.
problem Predicting day-ahead crypto-currency prices.
method Proposes a deep state-space model combining state-space formulation and deep neural networks.
result The deep state-space model outperforms state-of-the-art and classical methods in accuracy.
In this paper we study a model of random knots obtained by fixing a space curve in n-dimensional Euclidean space with n>3, and orthogonally projecting the space curve on to random 3 dimensional subspaces. By varying the space curve we obtain different models of random parametrized knots, and we will study how the…
Divides state space into regions with identical term structure shapes.
problem Classifying term structure shapes in the two-factor Vasicek model.
method Using envelopes and winding numbers to divide and classify the state space.
result Nearly complete classification of parameter space regarding term structure shapes.
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 …
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.
Introduces a new phase space for 2D supersymmetric sigma models.
problem Developing a new Hamiltonian formulation for 2D supersymmetric sigma models.
method Introduces a phase space with spinorial momenta and derives a covariant Hamiltonian formulation.
result Shows the existence of additional supersymmetries in the new formulation.
New smooth models for string groups defined in ∞-categories.
problem Defining string group models in smooth spaces.
method Homotopy-theoretic definition using singular complex functor.
result New smooth models for the string group.
We consider sub-Riemannian spaces admitting an isometry group that is maximal in the sense that any linear isometry between the horizontal tangent spaces is realized by a global isometry. We will show that these spaces have a canonical choice of partial connection on their horizontal bundle, which is determined by isom…
A new model predicts network events with improved accuracy and interpretability.
problem Predicting and understanding complex dynamic relational data in networks.
method Mutually Exciting Latent Space Hawkes (LSH) model for continuous-time networks.
result The LSH model outperforms existing models in prediction accuracy and interpretability.
Proposes CLSM for better subsequence generation in music sequences.
problem Editing subsequences in music sequences without losing context.
method Context-informed prior and decoder for generative model, context position-informed encoder for inference.
result Contextual latent space is smoother in interpolation and generates higher quality samples.
The paper proposes a Gaussian mixture model for Hilbert-space-valued data.
problem Challenges in characterizing probability measures for infinite-dimensional random objects.
method Gaussian mixture framework based on kernel mean embeddings.
result The proposed algorithm yields a dense class of approximations in infinite-dimensional spaces.
Defines coarse cohomology of space complements, proving new duality results.
problem Defining and studying coarse cohomology of space complements.
method Introducing a model space, new approach to PD spaces, homological criterion.
result Proves new versions of coarse Poincaré duality and Alexander duality.
We give the complete classification of all sub-Riemannian model spaces with both step and rank three. They will be divided into three families based on their nilpotentization. Each family will depend on a different number of parameters, making the result crucially different from the known case of step two model spaces.…
Generative models learn manifold structure; new approach uses atlas and geodesic interpolation.
problem Challenges in representing manifolds with topology different from Euclidean space.
method Atlas Generative Models (AGMs) with hybrid latent spaces and geodesic interpolation.
result Geodesic interpolation can be extended to AGMs, improving manifold representation.
Model criticism is usually carried out by assessing if replicated data generated under the fitted model looks similar to the observed data, see e.g. Gelman, Carlin, Stern, and Rubin [2004, p. 165]. This paper presents a method for latent variable models by pulling back the data into the space of latent variables, and c…
Combines deep state space models with diffusion models for better forecasting and capturing latent dynamics
problem Forecasting and capturing latent dynamics in time series
method DDSSM: Diffusion-driven state space model
result Empirically outperforms state-of-the-art deep SSM
Bayesian deep learning uses function-space priors to improve model uncertainty and robustness.
problem Bayesian deep learning struggles with model-specific weight-space priors that are hard to interpret and specify.
method Apply a Dirichlet prior in predictive space and perform approximate function-space variational inference.
result The approach improves uncertainty quantification, scalability, and adversarial robustness in large-scale image classification.
Space mapping speeds up shape optimization for PDEs.
problem Efficiently solving shape optimization problems constrained by PDEs.
method Combines fine and coarse model optimizations using Riemannian metrics.
result Space mapping methods are highly efficient for complex shape optimization problems.
Sliced Inverse Regression reduces parameter space for estimating complex financial models.
problem High-dimensional parameter space in stochastic differential equations.
method Sliced Inverse Regression for dimension reduction.
result Reduced computational costs in estimating parameters.
Random feature models approximate functions in Banach spaces efficiently.
problem Approximating functions in Banach spaces efficiently.
method Randomly initialized feature maps and linear readout training.
result Universal approximation in Bochner spaces for Banach space-valued models.
FFM generates functions between Gaussian and data distributions.
problem Generating functions between Gaussian and data distributions.
method Define a path of measures, learn a vector field to generate this path.
result FFM outperforms other function-space generative models.
In this paper we investigate a link between state- space models and Gaussian Processes (GP) for time series modeling and forecasting. In particular, several widely used state- space models are transformed into continuous time form and corresponding Gaussian Process kernels are derived. Experimen- tal results demonstrat…
Study on signal detection in sparse additive models with nonasymptotic minimax rates.
problem Signal detection in sparse additive models.
method Nonasymptotic minimax analysis of signal detection in sparse additive models.
result Established minimax separation rate for signal detection.
Many mathematical models of physical phenomena that have been proposed in recent years require more general spaces than manifolds. When taking into account the symmetry group of the model, we get a reduced model on the (singular) orbit space of the symmetry group action. We investigate quantization of singular spaces o…
Generative models use Riemannian manifolds to improve latent space interpretation.
problem Generative models often bias latent space interpretations.
method Use Riemannian manifolds to define latent space paths that respect ambient geometry.
result Improves interpretability of learned representations for both stochastic and deterministic generators.
Latent diffusion improves robustness in missing data imputation.
problem Missing data imputation under MCAR corruption.
method Two-stage framework: VAE for latent feature learning, diffusion model in latent space.
result Latent diffusion maintains high quality and stability up to 50% missingness.