Proposes a method to learn representations of higher-dimensional simplicial complexes.
problem Lack of methods for representing entire simplicial complexes.
method Geometric message passing schemes for end-to-end learning of simplicial complex representations.
result First method for learning representations of entire simplicial complexes.
Paper studies complex Lagrangian surfaces and their relation to SL(3,C)-representations.
problem Minimal Lagrangian surfaces in bi-complex hyperbolic space and their representations.
method Introduces bi-complex Higgs bundles and parameterizes SL(3,C)-quasi-Fuchsian representations. result Parameterization of SL(3,C)-quasi-Fuchsian representations by an open set in Teichmüller space. Researchers describe unitary representations of mixed braid groups.
problem Understanding unitary representations of mixed braid groups.
method Explicitly describe unitary representations on cohomology of Abelian branched covers.
result Image of the representation is generated by complex reflections and related to the multivariate Burau representation.
Cube complexes allow hyperbolic groups to have Anosov representations.
problem Understanding representations of hyperbolic groups in higher dimensions.
method Analyzing representations of hyperbolic groups acting on CAT(0) cube complexes.
result Generic representations of certain groups are Anosov.
Researchers compute determinants and torsions of Rumin complex in specific Lie group representations.
problem Computing determinants and torsions of Rumin complex in specific Lie group representations.
method Analyzing Schrodinger and generic representations of the (2,3,5) nilpotent Lie group.
result Computed the spectrum and zeta regularized determinant of Rumin differentials in Schrodinger representations and evaluated their alternating product in generic representations.
A measure of neural complexity quantifies how hard it is to access information across neurons.
problem Understanding how mutual information is distributed among neurons in neural networks.
method Partial Information Decomposition (PID) to disentangle contributions of single neurons, multiple neurons, and synergistic effects.
result Representational Complexity measures the difficulty of accessing information across multiple neurons.
This paper explores the complexity of learning representations in contextual linear bandits.
problem Understanding the complexity of representation learning in contextual linear bandits.
method Systematic approach to representation learning in contextual linear bandits, focusing on instance-dependent perspective.
result Representation learning is fundamentally more complex than linear bandits, with some cases being arbitrarily harder.
Anosov representations of surface groups are complex manifolds.
problem Characterizing the geometry of Anosov representations of surface groups.
method Analyzing the character varieties of Anosov representations into $\SL(n , \C)$.
result Character varieties of Anosov representations are complex manifolds of specific dimension.
This study finds a special class of representations that dominate others in a complex hyperbolic group.
problem Domination of surface-group representations in complex hyperbolic groups.
method Analysis of T-bent representations and their domination by discrete and faithful representations. result A discrete and faithful representation exists that dominates a given T-bent representation in the Bergman translation length spectrum. This work explores representation complexity in RL paradigms, revealing model-based RL as the easiest task.
problem Investigating the representation complexity gap among model-based, policy-based, and value-based RL.
method Demonstrated through analysis of Markov decision processes (MDPs) and introduced new classes of MDPs.
result Representation complexity hierarchy: model-based RL > policy-based RL > value-based RL.
Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and optimal control make it possible to design control algorithms on these latent representations, but the field still lacks a large-scale standard …
Deroin and Tholozan's representations are mapped to complex projective space via action-angle coordinates.
problem Mapping representations of a punctured sphere into PSL(2,R) to a simpler geometric space. method Polygonal model and chains of triangles to extract action-angle coordinates.
result Action-angle coordinates give an explicit isomorphism and almost global Darboux coordinates.
We give criteria for real, complex and quaternionic representations to define s-representations, focusing on exceptional Lie algebras defined by spin representations. As applications, we obtain the classification of complex representations whose second exterior power is irreducible or has an irreducible summand of co-d…
Link between braid groups and q-deformed rationals solves a classification problem.
problem Classifying faithful complex specializations of the Burau representation of braid group B3.
method Established a link between Burau representation and q-deformed rational numbers.
result Proved faithfulness of Burau representation outside a specific annulus.
Neural networks benefit from intermediate representations, reducing sample complexity.
problem Understanding how neural networks leverage intermediate representations for hierarchical learning.
method Fixed, randomly initialized neural network as a representation function, compared with raw inputs and other trainable networks.
result Neural representations can achieve improved sample complexities compared to raw inputs, especially for low-rank polynomials.
A VB-groupoid is a Lie groupoid equipped with a compatible linear structure. In this paper, we describe a correspondence, up to isomorphism, between VB-groupoids and 2-term representations up to homotopy of Lie groupoids. Under this correspondence, the tangent bundle of a Lie groupoid G corresponds to the "adjoint repr…
New CR representations are found and shown to be redundant.
problem Identifying and classifying CR representations of 3-manifolds.
method Experimental computation of limit sets and exact computations of triangle groups.
result Many CR representations are redundant and conjugate.
New statistical guarantees for transfer learning with diverse tasks.
problem Statistical guarantees for transfer learning across different tasks.
method Formal analysis of t+1 tasks with shared representation. result Sample complexity reduction for new tasks using shared representation.
New algorithm reduces sample complexity for multi-task bandits.
problem Optimizing representation and predictor pairs for multi-task bandits.
method OSRL-SC algorithm with sample complexity H(Glog(1/δG)+Xlog(1/δH)). result OSRL-SC algorithm approaches sample complexity lower bounds.
Uniformizes compact complex manifolds via Anosov representations.
problem Uniformization of compact complex manifolds.
method Anosov homomorphisms with small limit sets.
result Local homeomorphism of character variety to Teichmüller space.
Researchers extend geometric quantization to complex Abelian Lie supergroups.
problem Quantization of super Kähler structures on complex Abelian Lie supergroups.
method Extended geometric quantization scheme to super Kähler setting, constructed unitary representation.
result Irreducible subrepresentations of the constructed representation are determined by the moment map.
Defines complexity measure for neural networks and feature representations, revealing scaling patterns.
problem Understanding the nonlinearity and dimensionality of neural network computations and feature representations.
method Introduces complexity and effective dimension measures, investigates their dynamics during training, and analyzes their scaling properties.
result Power law scaling of complexity and effective dimension during training, revealing hidden structure of datasets.
Novel algorithm learns sparse signal representations over topological spaces.
problem Sparse representation of signals over combinatorial topological spaces.
method Leveraging Hodge theory, the paper embeds topology into a dictionary structure via concatenated sub-dictionaries, each as a polynomial of Hodge Laplacians, and optimizes the dictionary coefficients and sparse signal representation via iterative alternating algorithms.
result Efficiently learned sparse representations and underlying relational structure of topological signals.
New methods evaluate data representations by complexity of low-loss predictor learning.
problem Evaluating quality of data representations for downstream tasks.
method Surplus Description Length (SDL) and ε Sample Complexity (εSC) methods.
result Methods measure the information needed to approximate optimal predictor up to specified tolerance.
The paper studies geometric representations of submanifolds using complex-valued functions.
problem Exploring the geometry of codimension-2 submanifolds.
method Implicitly representing submanifolds by complex-valued functions and showing a prequantum bundle structure.
result The space of implicit representations admits a prequantum bundle structure over the space of submanifolds.
Researchers define new quantum representations for a Lorentz algebra and study their Clebsch-Gordan decomposition.
problem Quantum representations of a Lorentz algebra and their Clebsch-Gordan decomposition.
method Defined new infinite-dimensional irreducible representations using quantum torus algebra and quantized Chern-Simons theory.
result The Clebsch-Gordan decomposition of tensor product representations reduces to problems in Fenchel-Nielson length operators in quantized Chern-Simons theory.
When two boundary-parabolic representations of knot groups are given, we introduce the connected sum of these representations and show several natural properties including the unique factorization property. Furthermore, the complex volume of the connected sum is the sum of each complex volumes modulo iπ2 and the twi…
New algorithms extract low-dimensional representations from sequential data, revealing insights into complex processes.
problem Challenges in extracting low-dimensional representations from sequential, high-dimensional, sparse, and noisy data.
method Developed new clustering algorithms based on Block Markov Chains theory, validated on real-world data.
result These algorithms can successfully extract low-dimensional representations from real-world sequential data, revealing insights into complex processes.
IsUMap improves data visualization of complex geometries.
problem Accurately representing complex, locally distorted metric spaces.
method Integrates UMAP and Isomap with Vietoris-Rips filtrations.
result Significant improvements in data representation quality.
We prove a Milnor-Wood inequality for representations of the fundamental group of a compact complex hyperbolic manifold in the group of isometries of quaternionic hyperbolic space. Of special interest is the case of equality, and its application to rigidity. We show that equality can only be achieved for totally geodes…
Representations of Dirac-Hestenes and Dirac spinor fields via coordinates of surfaces conformally immersed into 4-dimensional complex space are proposed. A relation between time evolution of spinor fields and integrable deformations of surfaces is discussed.
The paper studies conjugating complex representations into real ones.
problem Understanding representations of surface groups into complex Lie groups.
method Analyzes representations of finitely generated groups into PGL(k,C) and determines conjugacy conditions. result Identifies representations in the larger variety that are conjugate in PGL(k,C) to a representation in PGL(k,R). Complex numbers have long been favoured for digital signal processing, yet complex representations rarely appear in deep learning architectures. RNNs, widely used to process time series and sequence information, could greatly benefit from complex representations. We present a novel complex gated recurrent cell, which i…
Let ρ be a maximal representation of a uniform lattice Γ⊂SU(n,1), n≥2, in a classical Lie group of Hermitian type H. We prove that necessarily H=SU(p,q) with p≥qn and there exists a holomorphic or antiholomorphic ρ-equivariant map from complex hyperbolic space to the symmetric sp…
Deep neural networks (DNNs) transform stimuli across multiple processing stages to produce representations that can be used to solve complex tasks, such as object recognition in images. However, a full understanding of how they achieve this remains elusive. The complexity of biological neural networks substantially exc…
The paper defines and calculates Reidemeister torsion for a specific class of representations.
problem Defining and calculating Reidemeister torsion for G-Anosov representations.
method Symplectic chain complex method to establish a novel formula for R-torsion.
result Reidemeister torsion is well-defined and calculated for G-Anosov representations.
We complete the classification of maximal representations of uniform complex hyperbolic lattices in Hermitian Lie groups by dealing with the exceptional groups E6 and E7. We prove that if ρ is a maximal representation of a uniform complex hyperbolic lattice Γ⊂SU(1,n), n>1, in an exce…
We consider a set of probabilistic functions of some input variables as a representation of the inputs. We present bounds on how informative a representation is about input data. We extend these bounds to hierarchical representations so that we can quantify the contribution of each layer towards capturing the informati…
We examine the influence of input data representations on learning complexity. For learning, we posit that each model implicitly uses a candidate model distribution for unexplained variations in the data, its noise model. If the model distribution is not well aligned to the true distribution, then even relevant variati…
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.
This thesis investigates unsupervised time series representation learning for sequence prediction problems, i.e. generating nice-looking input samples given a previous history, for high dimensional input sequences by decoupling the static input representation from the recurrent sequence representation. We introduce thr…
Study parabolic representations of knots using quandles and polynomials.
problem Classify parabolic representations of knot groups.
method Utilize parabolic and symplectic quandles, generalized Riley polynomials, and u-polynomials. result Complete classification of parabolic representations up to 12 crossings.
New method computes optimal fairness-performance trade-off without complex models.
problem Intrinsic trade-off between fairness and classifier performance.
method Computes optimal Pareto front without training complex models.
result Optimal fair representations have useful structural properties enabling efficient computation.
The first time that the connection between isometric immersion of surfaces and solutions of the Dirac equation appeared in the literature was in the seminal paper of Thomas Friedrich in 1998. In consequence of that, several authors contributed to this topic hereafter, by obtaining the spinorial representation of Spin m…
We use the Cartan representations of SO(3) and SU(3), and an irreducible 14-dimensional representation of Sp(3) to construct certain totally geodesic submanifolds in "skew" position in the complex quadrics, the complex 2-Grassmannians and the quaternionic 2-Grassmannians.
Geometric methods for surface group representations in higher rank SL(2m+1,R).
problem Representations of surface groups in higher rank SL(2m+1,R).
method Para-complex and pseudo-Riemannian geometric techniques.
result One-to-one correspondence between Higgs bundles and isotropic P-alternating surfaces.
Paper improves sample complexity for reward-free RL in low-rank MDPs.
problem Reward-free RL in low-rank MDPs with unknown representation and weights.
method Proposes a novel model-based algorithm RAFFLE with improved sample complexity.
result RAFFLE achieves ε-optimal policy and accurate system identification with significantly fewer samples. Classifies real trivectors in 9D, following complex classification methods.
problem Classifying real trivectors in 9D space.
method Used Galois cohomology to divide trivectors into nilpotent, semisimple, and mixed groups.
result Classification of real trivectors in 9D space follows the same pattern as complex classification.