Foundation models fail to preserve continuous geometry, identified as the Geometric Alignment Tax.
problem Continuous geometry is lost in foundation models due to discrete categorical bottlenecks.
method Controlled ablations on synthetic systems and evaluation of 14 biological models using rate-distortion theory and MINE.
result Replacing cross-entropy with a continuous head reduces geometric distortion by up to 8.5x.
Survey on geometric foundations of data reduction methods.
problem High-dimensional data with intrinsic nonlinear structure.
method Spectral manifold learning methods.
result Derivation and convergence analysis of spectral manifold learning.
Logifold improves ensemble machine learning by identifying fuzzy domains.
problem Improving ensemble machine learning accuracy.
method Formulating logifold structure and interpreting local charts of datasets.
result Logifold improves accuracy compared to averaging model outputs.
Geometric framework detects concept frustration between human concepts and machine representations.
problem Aligning human concepts with machine learning representations.
method Geometric framework and similarity measures for detecting concept frustration.
result Concept frustration affects machine learning model performance and reorganizes learned concept representations.
Develops theory of relatively geometric actions on CAT(0) cube complexes.
problem Understand actions of relatively hyperbolic groups on CAT(0) cube complexes.
method Introduces and studies relatively geometric actions, proving key results.
result Proves full relatively quasi-convex subgroups are convex compact.
Paper proposes a probabilistic alignment method for domain adaptation.
problem Latent distribution mismatch and miscalibrated uncertainty in adapting large-scale models.
method Bayesian latent transport framework with PAC-Bayesian regularization.
result Reduction in latent manifold discrepancy and improved uncertainty calibration.
Geometric cohomology model uses co-oriented maps to define a product structure.
problem Constructing a geometric model for cohomology of smooth manifolds.
method Develops a cochain complex model based on co-oriented smooth maps, focusing on their pull-back product structure.
result Geometric cochains with a partially defined product structure induce the cup product in cohomology.
ML reduces high-dimensional data to reveal its underlying structure.
problem Handling large, high-dimensional data sets.
method Non-linear dimension reduction techniques.
result Reveals the geometric shape of high-dimensional data.
Develops Riemannian geometry for optimization on manifolds with detailed derivations.
problem Abstract high-level optimization on nonlinear spaces like matrix manifolds.
method Systematic derivation of geometric structures and constructions in coordinates and matrix form.
result Unified treatment of Riemannian geometry for optimization on manifolds.
Foundations for free boundary Brakke flows established.
problem Analyzing free boundary flows through singularities
method Introducing unit-regular and cyclic free boundary flows, proving avoidance principle, and introducing inner and outer flows.
result General tools for analyzing free boundary flows through singularities.
New combinatorial framework for geometric realizations of subword complexes.
problem Proving or disproving geometric realizations of subword complexes of Coxeter groups.
method Algebraic combinatorics and discrete geometry framework, parameter matrices.
result Existence of parameter matrices equivalent to realizability of subword complexes as chirotopes.
By means of an analogy with Classical Mechanics and Geometrical Optics, we are able to reduce Lagrangians to a kinetic term only. This form enables us to examine the extended solution set of field theories by finding the geodesics of this kinetic term's metric. This new geometrical standpoint sheds light on some founda…
Survey of minimal generating sets for nonorientable mapping class groups.
problem Challenges in generating minimal sets for nonorientable surfaces.
method Detailed analysis of various generating sets, including torsions, involutions, and commutators.
result For large genus, both Mod(Ng) and Tg are generated by two elements. These are the proceedings of the workshop "Math in the Black Forest", which brought together researchers in shape analysis to discuss promising new directions. Shape analysis is an inter-disciplinary area of research with theoretical foundations in infinite-dimensional Riemannian geometry, geometric statistics, and geo…
The paper studies geometric constants under modified Ricci flows with variable parameters.
problem Understanding geometric constants under variable coupling parameters in Ricci flows.
method Introduced modified Ricci flows with variable coefficients, derived evolution formulas, and proved monotonicity conditions.
result Conditions for maintaining monotonicity of geometric constants under modified Ricci flows.
We introduce two constructions in geometric deep learning for 1) transporting orientation-dependent convolutional filters over a manifold in a continuous way and thereby defining a convolution operator that naturally incorporates the rotational effect of holonomy; and 2) allowing efficient evaluation of manifold convol…
Geometrically reformulates GENERIC stochastic dynamics.
problem Unified treatment of reversible and dissipative dynamics.
method Introduces degenerate Poisson structure, co-metric, and volume form.
result Preserves Boltzmann measure, conserves energy, reduces to deterministic limit.
Second-order superintegrable systems in dimensions two and three are essentially classified. With increasing dimension, however, the non-linear partial differential equations employed in current methods become unmanageable. Here we propose a new, algebraic-geometric approach to the classification problem - based on a p…
Prove asymptotics of geometric flows using algebro-geometric methods.
problem Prove asymptotics of geometric flows
method Algebro-geometric methods
result Prove a conjecture of Haiden-Katzarkov-Kontsevich-Pandit
We give completely combinatorial proofs of the main results of [3] using polygons. Namely, we prove that the mapping class group of a surface with boundary acts faithfully on a finitely-generated linear category. Along the way we prove some foundational results regarding the relevant objects from bordered Heegaard Floe…
Unified geometric framework for Brownian motion on various manifolds.
problem Modeling Brownian motion on complex Riemannian manifolds.
method Constructing stochastic differential equations with noise and drift terms aligned with Laplace-Beltrami operators.
result Geometrically transparent and mathematically consistent foundation for diffusion processes.
This paper organizes recent deep learning theory advances.
problem Lack of theoretical foundations in deep learning.
method Literature review and categorization into six groups.
result Organized recent advances in deep learning theory.
New framework for noncommutative Carrollian geometry using Lie-Rinehart pairs.
problem Developing a geometric framework for ultra-relativistic physics in noncommutative settings.
method Using ρ-Lie-Rinehart pairs to generalize Carrollian Lie algebroids to almost commutative geometry.
result Foundational principles of Carrollian geometry hold in almost commutative geometry.
Survey explores translation surfaces from geometric and topological perspectives.
problem Underutilized aspects of translation surfaces in dynamical viewpoint.
method Equivalent definitions, moduli spaces, period map, holonomy map.
result Highlights foundational, yet underrated, aspects of translation surfaces theory.
Geometrically convex return risk measures on AM-algebras
problem Quantifying risk in time series analysis
method Extending return risk measures to general ordered vector spaces
result Establishing results on finiteness, continuity, separability, and dual and aggregation-based representations
Develops geometric foundations for sublinear Morse boundaries in mapping class groups and Teichmüller spaces.
problem Capturing generic directions in mapping class groups and Teichmüller spaces.
method Develops tools for modeling hulls of median rays in hierarchically hyperbolic spaces via CAT(0) cube complexes.
result Sublinear Morse boundaries are visibility spaces and admit continuous equivariant injections into the boundary of the curve graph.
This paper contains the technical foundations from stochastic differential geometry for the construction of geometrically intrinsic nonlinear recursive filters. A diffusion X on a manifold N is run for a time interval T, with a random initial condition. There is a single observation consisting of a nonlinear function o…
We introduce an invariant linked to some foundational questions in geometric measure theory and provide bounds on this invariant by decomposing an arbitrary cycle into uniformly rectifiable pieces. Our invariant measures the difficulty of cutting a nonorientable closed manifold or mod-2 cycle in Rn into ori…
New framework explains neural network behavior through geometric postulates.
problem Understanding neural network mechanisms and making them more transparent.
method Introducing the Pursuit of Subspaces (PoS) hypothesis as an axiomatic framework.
result Unified geometric perspective on neural network representation, computation, and generalization.
The paper characterizes stable cohomotopy groups in codimensions two and three, linking algebraic and geometric perspectives.
problem Characterizing stable cohomotopy groups in specific codimensions.
method Algebraic and geometric approaches, including CW complexes and bordism theory.
result Complete characterizations of stable cohomotopy in codimension two and partial results in codimension three.
This paper presents geometrical foundation for a systematic treatment of three main (elliptic, parabolic and hyperbolic) types of analytic function theories based on the representation theory of SL(2,R) group. We describe here geometries of corresponding domains. The principal role is played by Clifford algebras of mat…
Motivated by numerical integration on manifolds, we relate the algebraic properties of invariant connections to their geometric properties. Using this perspective, we generalize some classical results of Cartan and Nomizu to invariant connections on algebroids. This has fundamental consequences for the theory of numeri…
Advances M-polyfolds for complex geometry applications.
problem Complex geometry challenges in differential geometry.
method Introduces and proves geometric structures within M-polyfolds.
result Establishes M-polyfolds as useful differential geometric objects.
Geometric approach to quantum thermodynamics models state spaces and processes.
problem Quantum thermodynamics in the regime of non-equilibrium states.
method Contact geometry and principal fiber bundles to model quantum state spaces and processes.
result Geometric formulation reveals the fundamental thermodynamic relations and unattainability of the third law.
TDL uses topological features for deep learning models, promising new insights and solutions.
problem Lack of comprehensive theoretical foundations and practical benefits in TDL.
method Discussing open problems and potential solutions in TDL.
result TDL can complement existing graph and geometric learning methods.
Expands Bredon's trick for applications in geometry and topology.
problem Local-to-global extension principles in geometric and topological contexts.
method Novel applications and frameworks for stratified pseudomanifolds, Ricci flow, and persistent homology.
result Establishes Bredon's trick as a unifying framework.
First-order jet bundles can be put at the foundations of the modern geometric approach to nonlinear PDEs, since higher-order jet bundles can be seen as constrained iterated jet bundles. The definition of first-order jet bundles can be given in many equivalent ways - for instance, by means of Grassmann bundles. In this …
Paper formalizes multi-dimensional FSD using geometric methods.
problem Complex measure theory and calculus barriers to formalization in proof assistants.
method Geometric framework for first-order stochastic dominance in N dimensions.
result Geometric approach bypasses complex integration theory for direct comparison of survival probabilities.
Survey of analytic and geometric results on fibred cusp spaces.
problem Analyzing a class of non-compact Riemannian manifolds with cusp singularities.
method Careful microlocal analysis of the resolvent and heat kernel.
result Main theorems on spectral geometry, including analytic torsion and index theory.
We develop the foundation of the complex symplectic geometry of Lagrangian subvarieties in a hyperkahler manifold. We establish a characterization, a Chern number inequality, topological and geometrical properties of Lagrangian submanifolds. We discuss a category of Lagrangian subvarieties and its relationship with the…
Although consistency is a minimum requirement of any estimator, little is known about consistency of the mean partition approach in consensus clustering. This contribution studies the asymptotic behavior of mean partitions. We show that under normal assumptions, the mean partition approach is consistent and asymptotic …
Mathematical framework to understand neural network vulnerability.
problem Understanding and quantifying adversarial vulnerability in neural networks.
method Develops a geometric framework using Ricci curvature to measure decision boundaries and adversarial perturbations.
result Establishes a new theory linking adversarial attacks to Ricci curvature of decision boundaries.
Geometric stability predicts steerability and detects drift in language models.
problem Predicting steerability and detecting drift in language models.
method Supervised and unsupervised geometric stability measures.
result Supervised geometric stability predicts steerability with high accuracy and detects drift earlier.
We give a generalized curvature-dimension inequality connecting the geometry of sub-Riemannian manifolds with the properties of its sub-Laplacian. This inequality is valid on a large class of sub-Riemannian manifolds obtained from Riemannian foliations. We give a geometric interpretation of the invariants involved in t…
Mathematical foundation for phylogenetic tree uncertainty quantification.
problem Uncertainty in evolutionary relationships between species.
method Introducing the Wald space as a subset of symmetric positive definite matrices, studying its topology and structure, and proposing a new numerical method for geodesics and curvature.
result Wald space has a topology of disjoint open cubes, is contractible, and is a Whitney stratified space of type (A).
A framework for precontact geometry using pairs of differential forms.
problem Extending contact geometry with weakened conditions.
method Study of pairs of 1-form and 2-form under mild conditions.
result Characterization and analysis of precontact structures.
This paper analyzes Barlow Twins' representation efficiency using information-geometric methods.
problem Understanding and comparing the efficiency of self-supervised learning methods.
method Introduces an information-geometric framework to quantify representation efficiency and applies it to Barlow Twins.
result Proves that Barlow Twins achieves optimal representation efficiency (η=1).
This paper reviews discrete curvature models for geometric data analysis.
problem Capturing intrinsic geometric structure in diverse data representations.
method Comprehensive review of discrete curvature models from Riemannian and metric geometry perspectives.
result Systematic pipeline for curvature-driven data analysis and learning.