Paper addresses the disparity between sampled and mean representations in disentangled learning.
problem Disparity between sampled and mean representations in disentangled learning.
method Proposes a method to eliminate the disparity by proving and utilizing the relationship between total correlation of sampled and mean representations for multivariate normal distributions.
result Demonstrates that a factorized mean representation can have lower total correlation than the sampled representation.
Mean representations of VAEs are correlated but still useful for tasks.
problem Correlation between mean and sampled representations of VAEs.
method Selective posterior collapse to identify active and passive variables.
result Passive variables in mean representations are correlated but uncorrelated in sampled ones.
The paper finds formulas for special surface shapes in 3D space.
problem Creating formulas for constant mean curvature surfaces.
method Weierstrass representations for discrete surfaces in isotropic space.
result Constructs examples of surfaces with discrete parametrizations.
Spinor representation in isotropic space via Laguerre geometry.
problem Representing conformal and constant mean curvature surfaces in isotropic space.
method Developing Laguerre geometry of isotropic space, defining spin transformations, and constructing Weierstrass and Kenmotsu representations.
result Explicit constructions of zero mean curvature and constant mean curvature surfaces.
Study constant mean curvature surfaces with integrable boundary conditions.
problem Understanding surfaces with constant mean curvature under specific boundary conditions.
method Used generalized Weierstrass representation to determine potentials.
result Determined potentials for surfaces satisfying integrable boundary conditions.
Unified representation for minimal and constant mean curvature surfaces.
problem Representing minimal and constant mean curvature surfaces in Euclidean and hyperbolic spaces.
method Integral system methods applied to Weierstrass and Bryant representations.
result Unified representation and classification of various examples.
Classifies surfaces with zero mean curvature in a light cone.
problem Classifying surfaces with zero mean curvature in a light cone.
method Examined geodesics and screw motions, used Weierstrass representations.
result Complete classification of ruled zero mean curvature surfaces.
We study in this paper the problem of jointly clustering and learning representations. As several previous studies have shown, learning representations that are both faithful to the data to be clustered and adapted to the clustering algorithm can lead to better clustering performance, all the more so that the two tasks…
We focus on mean-variance hedging problem for models whose asset price follows an exponential additive process. Some representations of mean-variance hedging strategies for jump type models have already been suggested, but none is suited to develop numerical methods of the values of strategies for any given time up to …
We give a conformal representation in terms of meromorphic data for a certain class of spacelike surfaces in the Lorentz-Minkowski 4-space L^4 whose mean curvature vector is either lightlike or zero at each point. This representation extends simultaneously the Weierstrass representation for minimal surfaces in Euclidea…
EGAE improves graph clustering by utilizing GAE's representations in a way consistent with relaxed k-means theory.
problem Improving graph clustering performance using unsupervised methods.
method Designing an Embedding Graph Auto-Encoder (EGAE) that aligns with theoretical relaxed k-means to learn explainable representations.
result EGAE achieves superior graph clustering results compared to existing methods.
We present a global representation for surfaces in 3-dimensional hyperbolic space with constant mean curvature 1 (CMC-1 surfaces) in terms of holomorphic spinors. This is a modification of Bryant's representation. It is used to derive explicit formulas in hypergeometric functions for CMC-1 surfaces of genus 0 with thre…
Constructs constant mean curvature surfaces using geometric flow.
problem Creating surfaces with constant mean curvature in 3D spaces.
method Using a generalized Weierstrass representation and geometric flow on potentials.
result Describes construction of CMC surfaces with symmetries.
We derive a correspondence between (Lorentzian) harmonic maps into the pseudosphere S12, with appropriate regularity conditions, and certain connection 1-forms. To these harmonic maps, we associate a representation of type Weierstrass, and we apply it to construct timelike surfaces with constant mean curvature.
Temporal-difference and Q-learning learn feature representations that converge to optimal ones.
problem Understanding how feature representations evolve in temporal-difference and Q-learning with neural networks.
method Mean-field theory applied to overparameterized two-layer neural networks.
result The feature representation converges to the optimal one, generalizing previous results.
Develops a new representation for constant mean curvature surfaces in hyperbolic 3-space.
problem Finding conformal immersions of constant mean curvature in hyperbolic 3-space.
method Uses a Weierstrass-Kenmotsu type representation based on the Hermitian model, balanced spectral deformation, and Iwasawa splitting of $\SL$.
result Establishes an explicit correspondence with Aiyama and Akutagawa's representation and interprets the construction in terms of Kokubu's adjusted normal Gauss map.
We sharpen the construction of representation space in the paper "Principal Series Representations of Infinite Dimensional Lie Groups II: Construction of Induced Representations". We show that the principal series representation spaces constructed there, are completions of spaces of sections of Hilbert bundles rather t…
We obtain the explicit representation of Legendre surfaces in the unit 5-sphere with harmonic mean curvature vector field, under the condition that the mean curvature function is constant along a certain special direction.
New analysis of annealing paths in sampling and estimation.
problem Sampling from complex distributions and estimating normalization constants.
method Extending known results on Bregman divergence to quasi-arithmetic means under monotonic embedding.
result Analogous result for quasi-arithmetic means, highlighting the interplay between means, parametric families, and divergence functionals.
MMD-B-Fair learns fair representations by minimizing MMD test power.
problem Learning fair representations of data while preserving target attributes.
method Kernel two-sample testing and block testing schemes.
result Minimizing MMD test power allows hiding sensitive attribute information.
We present a theorem on the unitarizability of loop group valued monodromy representations and apply this to show the existence of new families of constant mean curvature surfaces homeomorphic to a thrice-punctured sphere in the simply-connected 3-dimensional space forms R3, $\bbS^3 $ and $\bbH^3$. Additionally, we…
New integrable systems for marginally trapped surfaces in 4D Lorentz-Minkowski space.
problem Constructing new representations for marginally trapped surfaces in L4. method Developed new Weierstrass-type representations to solve a linear PDE.
result Explicit examples of marginally trapped surfaces with non-vanishing mean curvature.
In the paper, a mean-square minimization problem under terminal wealth constraint with partial observations is studied. The problem is naturally connected to the mean-variance hedging problem under incomplete information. A new approach to solving this problem is proposed. The paper provides a solution when the underly…
Motivated by the study of the interrelation between functorial and algebraic quantum field theory, we point out that on any locally trivial bundle of compact groups, representations up to homotopy are enough to separate points by means of the associated representations in cohomol- ogy. Furthermore, we observe that the …
We study surfaces with constant anisotropic mean curvature which are invariant under a helicoidal motion. For functionals with axially symmetric Wulff shapes, we generalize the recently developed twizzler representation of Perdomo to the anisotropic case and show how all helicoidal constant anisotropic mean curvature s…
There is some theoretical evidence that deep neural networks with multiple hidden layers have a potential for more efficient representation of multidimensional mappings than shallow networks with a single hidden layer. The question is whether it is possible to exploit this theoretical advantage for finding such represe…
In hyperbolic 3-space H3 surfaces of constant mean curvature H come in three types, corresponding to the cases 0≤H<1, H=1, H>1. Via the Lawson correspondence the latter two cases correspond to constant mean curvature surfaces in Euclidean 3-space E3 with H=0 and H=0, re…
This work analyzes how neural networks learn representations in actor-critic algorithms.
problem Theoretical support for neural AC algorithms is limited to linear function approximations.
method Mean-field analysis of a two-timescale learning AC algorithm with overparameterized networks.
result Neural AC finds the globally optimal policy at a sublinear rate in the continuous-time and infinite-width limiting regime.
A mean field variational Bayes approach to support vector machines (SVMs) using the latent variable representation on Polson & Scott (2012) is presented. This representation allows circumvention of many of the shortcomings associated with classical SVMs including automatic penalty parameter selection, the ability to ha…
Paper proves k-means clustering works on persistence diagrams.
problem Complex geometry of persistence diagram space.
method Proves convergence of k-means on persistence diagram space. result Performance of k-means on persistence diagrams and measures is superior. The paper connects knot representations and spherical quandle colorings.
problem Defining the Casson-Lin invariant for knots.
method One-to-one correspondence between SU(2)-representations and spherical quandle colorings. result Geometric interpretation of the trace-free condition for the Casson-Lin invariant.
Current meta-learning approaches focus on learning functional representations of relationships between variables, i.e. on estimating conditional expectations in regression. In many applications, however, we are faced with conditional distributions which cannot be meaningfully summarized using expectation only (due to e…
Transformer learns representations from time series data for money laundering detection.
problem Detecting money laundering using structured time series data.
method Contrastive learning for representation learning, followed by scoring and thresholding.
result Transformer outperforms rule-based and LSTM methods in detecting money laundering with controlled false positives.
The abstract explains how word and relation representations capture semantic meaning.
problem Understanding how word and relation representations capture semantic meaning.
method Theoretical justification and extension of geometric relationships between word embeddings and knowledge graph representations.
result The geometric relationships between word embeddings correspond to semantic relations between words and entities in knowledge graphs.
UNTIE learns representations of coupled categorical data.
problem Challenges in learning from unlabeled categorical data with complex couplings.
method UNTIE approach for unsupervised representation learning of heterogeneous couplings.
result UNTIE significantly improves categorical data representations on 25 diverse datasets.
A new method for distribution regression using sliced Wasserstein distance.
problem Learning functions over spaces of probabilities.
method Proposes an OT-based estimator using the Sliced Wasserstein distance.
result Proves universal consistency and excess risk bounds for the proposed estimator.
We prove that, for a hyperbolic two bridge knot, infinitely many Dehn fillings are rigid in SO0(4,1). Here rigidity means that any discrete and faithful representation in SO0(4,1) is conjugate to the holonomy representation in SO0(3,1). We also show local rigidity for almost all Dehn fillings.
Recently, deep reinforcement learning (RL) methods have been applied successfully to multi-agent scenarios. Typically, these methods rely on a concatenation of agent states to represent the information content required for decentralized decision making. However, concatenation scales poorly to swarm systems with a large…
Advances in mobile computing technologies have made it possible to monitor and apply data-driven interventions across complex systems in real time. Markov decision processes (MDPs) are the primary model for sequential decision problems with a large or indefinite time horizon. Choosing a representation of the underlying…
We use Bryant Representation to construct constant mean curvature one surfaces in hyperbolic space that desingularize a horosphere packing.
The ability of the Generative Adversarial Networks (GANs) framework to learn generative models mapping from simple latent distributions to arbitrarily complex data distributions has been demonstrated empirically, with compelling results showing that the latent space of such generators captures semantic variation in the…
We give an infinite dimensional generalized Weierstrass representation for spacelike constant mean curvature (CMC) surfaces in Minkowski 3-space ℜ2,1. The formulation is analogous to that given by Dorfmeister, Pedit and Wu for CMC surfaces in Euclidean space, replacing the group SU2 with SU1,1. The non…
Extends adjoint representation concept to higher Lie groupoids.
problem Defining adjoint representation for higher Lie groupoids.
method Generalizes standard construction to higher Lie groupoids using simplicial vector bundles.
result Adjoint representation up to homotopy is well-defined and unique.
Transform learning improves K-means clustering for document analysis.
problem Improving K-means clustering for document analysis.
method Embedding K-means clustering loss into transform learning framework and solving jointly using ADMM.
result Improves over state-of-the-art in document clustering.
The generalized Weierstrass representation is used to analyze the asymptotic behavior of a constant mean curvature surface that arises locally from an ordinary differential equation with a regular singularity. We prove that a holomorphic perturbation of an ODE that represents a Delaunay surface generates a constant mea…
Earth observation embeddings can convert discrete biome maps into continuous representations that better capture ecological variation.
problem Biome maps impose categorical boundaries that compress continuous variation in biotic communities.
method Fit a linear classifier on Earth observation embeddings to predict biome labels.
result Continuous biome representation outperforms discrete biome labels for predicting species occurrence.
This study improves sentence embeddings from BERT models.
problem Capturing the underlying meaning of sentences using BERT models.
method Comprehensive review and testing of various sentence embedding extraction and refinement methods.
result Representation-shaping techniques significantly improve sentence embeddings from BERT-based and simple baseline models.
We address the problem of simultaneously learning a k-means clustering and deep feature representation from unlabelled data, which is of interest due to the potential of deep k-means to outperform traditional two-step feature extraction and shallow-clustering strategies. We achieve this by developing a gradient-estimat…