GAAVI offers anytime-valid tests for CMF global null and contrasts.
problem Inference on the conditional mean function for high confidence decisions.
method Asymptotic anytime-valid tests for CMF global null and contrasts.
result Achieves asymptotic type-I error guarantees, power one, and optimal sample complexity.
CD algorithm achieves near-optimal convergence rate for unnormalized models.
problem Training unnormalized models with high efficiency.
method Non-asymptotic analysis of contrastive divergence algorithm.
result CD can achieve O(n−1/2) convergence rate under regularity assumptions. A new method for online VI in SSMs using asymptotic contrast.
problem Lack of functionality for streaming data in standard VI methods for SSMs.
method Propose maximising an IWAE-type variational lower bound on the asymptotic contrast function using stochastic approximation.
result OSIWAE allows for online learning of model parameters and latent states.
There are many models, often called unnormalized models, whose normalizing constants are not calculated in closed form. Maximum likelihood estimation is not directly applicable to unnormalized models. Score matching, contrastive divergence method, pseudo-likelihood, Monte Carlo maximum likelihood, and noise contrastive…
We show that many hyperbolic monopoles can be distinguished from each other via their asymptotic values in contrast to the case of Euclidean monopoles.
We study the asymptotics of a family of link invariants on the orbits of a smooth volume-preserving ergodic vector field on a compact domain of the 3-space. These invariants, called linear saddle invariants, include many concordance invariants and generate an infinite-dimensional vector space of link invariants. In con…
New theory explains contrastive learning via overlapping augmented views.
problem Lack of theoretical understanding of contrastive learning.
method Augmentation overlap perspective to improve downstream performance.
result Asymptotically closed bounds for downstream performance under weaker assumptions.
We study a new parametric approach for particular hidden stochastic models such as the Stochastic Volatility model. This method is based on contrast minimization and deconvolution. After proving consistency and asymptotic normality of the estimation leading to asymptotic confidence intervals, we provide a thorough nume…
New findings show optimal noise in contrastive learning is not the same as data distribution.
problem The optimal noise distribution in contrastive learning is not the same as the data distribution.
method Empirical and theoretical analysis of contrastive learning methods.
result Deviation from the assumption of equal noise and data distribution leads to better statistical estimators.
This paper addresses measurement errors in high-dimensional compositional data using a log-contrast model calibration approach.
problem Measurement errors in high-dimensional regression models involving compositional covariates.
method Calibration approach for the linear log-contrast model under lenient sparsity conditions.
result Established asymptotic normality of the estimator for inference.
We construct a solution to inverse mean curvature flow on an asymptotically hyperbolic 3-manifold which does not have the convergence properties needed in order to prove a Penrose--type inequality. This contrasts sharply with the asymptotically flat case. The main idea consists in combining inverse mean curvature flow …
This work optimizes alignment and uniformity of features on a hypersphere for better downstream performance.
problem Improving the performance of contrastive representation learning.
method Identifying and optimizing alignment and uniformity of features on a hypersphere.
result Directly optimizing alignment and uniformity leads to comparable or better performance than contrastive learning.
We examine the local super trace asymptotics for the de Rham complex defined by an arbitrary super connection on the exterior algebra. We show, in contrast to the situation in which the connection in question is the Levi-Civita connection, that these invariants are generically non-zero in positive degree and that the c…
Sharp criterion for Chern-Gauss-Bonnet integral using Q curvature.
problem Quantifying the Chern-Gauss-Bonnet integral using Q curvature.
method New approach involving singular integral estimation.
result Derivation of asymptotic formula for Q curvature equation.
The paper compares theoretical and empirical performance of imputation methods for missing data.
problem Missing data in real-world datasets.
method Contrast of theoretical and empirical imputation methods for prediction.
result Mean-imputation is asymptotically optimal for prediction, while mode-imputation is sub-optimal.
Big mapping class groups of infinite type surfaces have infinite asymptotic dimension.
problem Understanding asymptotic dimension of big mapping class groups of infinite type surfaces.
method Analyzing big mapping class groups with coarsely bounded generating sets and essential shifts.
result Big mapping class groups of infinite type surfaces have infinite asymptotic dimension.
We consider the evolution of the asymptotically hyperbolic mass under the curvature-normalized Ricci flow of asymptotically hyperbolic, conformally compactifiable manifolds. In contrast to asymptotically flat manifolds, for which ADM mass is constant during Ricci flow, we show that the mass of an asymptotically hyperbo…
PCA++ improves robustness to background noise in contrastive learning.
problem Recovering shared signal subspaces from positive pairs in high-dimensional data with structured background noise.
method PCA++ uses hard uniformity-constrained contrastive learning to enforce identity covariance on projected features.
result PCA++ outperforms standard PCA and alignment-only PCA+ in simulations and real-world datasets.
This paper classifies instantons with closed reductions and provides examples of non-closed reductions.
problem Understanding the geometry of toric Kähler instantons with and without closed reductions.
method Sharp geometric criteria and examples of instantons with different reduction types.
result Established geometric criteria for closed reductions and classified asymptotic geometries.
This paper establishes that optimistic algorithms attain gap-dependent and non-asymptotic logarithmic regret for episodic MDPs. In contrast to prior work, our bounds do not suffer a dependence on diameter-like quantities or ergodicity, and smoothly interpolate between the gap dependent logarithmic-regret, and the $\wid…
The paper studies the free elastic flow of closed curves and finds their asymptotic shape converges to a circle.
problem Challenges in studying the asymptotic behavior of the free elastic flow for closed curves.
method Analysis of the free elastic flow as an L2-gradient flow for Euler's elastic energy. result An appropriate rescaling of initial curves geometrically close to circles converges to a unique round circle.
The paper studies heat behavior on curved spaces without radiality assumption.
problem Analyzing heat behavior on curved spaces.
method Examining heat equation solutions on specific Riemannian manifolds.
result Long-time convergence results hold on more general manifolds.
The paper analyzes the InfoNCE loss under different temperature schedules using Langevin dynamics.
problem Understanding the dynamics of InfoNCE loss under fixed versus annealed temperature schedules.
method Modeling embedding evolution under Langevin dynamics on a compact Riemannian manifold, with theoretical guarantees for convergence.
result Slow logarithmic inverse-temperature schedules ensure convergence to globally optimal representations, while faster schedules risk suboptimal minima.
Unified definition of mass aspect function for weakly regular hyperbolic manifolds.
problem Ambiguity in mass definition for asymptotically hyperbolic manifolds.
method Introduced an ADM-style mass aspect function for broad asymptotics and low regularity.
result Unified mass aspect function exhibits favorable covariance properties.
No semistability found for Calabi-Yau metrics near cones.
problem Understanding the stability of Calabi-Yau metrics near cones.
method Developed a 2-step degeneration theory to eliminate intermediate K-semistable cones.
result No intermediate K-semistable cone possible for Calabi-Yau metrics near cones.
New insights into contrastive learning reveal how projectors affect downstream performance.
problem Understanding how projectors in contrastive learning impact downstream linear classification accuracy.
method Identified and modeled two effects: expansion and shrinkage induced by contrastive loss.
result Linear projectors operating in the shrinkage regime hinder downstream classification accuracy.
Rigidity theorem shows massless hyperboloidal data embeds into Minkowski space.
problem Characterizing massless initial data sets in General Relativity.
method Precise decay estimates for spinors on harmonic level sets.
result Asymptotically hyperboloidal IDS with zero mass embed isometrically into Minkowski space.
ACERL embeds networks into a low-dimensional space preserving structural and semantic properties.
problem Challenges in brain connectivity data analysis with subject-specific, high-dimensional, and sparse networks.
method Contrastive learning of augmented network pairs with adaptive random masking.
result Achieves minimax optimal convergence rate for edge representation learning.
We show the existence of isoperimetric regions of sufficiently large volumes in general asymptotically hyperbolic three manifolds. Furthermore, we show that large coordinate spheres in compact perturbations of Schwarzschild-anti-deSitter are uniquely isoperimetric. This is relevant in the context of the asymptotically …
For a surface S with n marked points and fixed genus g≥2, we prove that the logarithm of the minimal dilatation of a pseudo-Anosov homeomorphism of S is on the order of (logn)/n. This is in contrast with the cases of genus zero or one where the order is 1/n.
Growth rate of Dehn twist lattice points in Teichmüller space is slower than mapping class group lattice points.
problem Analyzing the growth rate of Dehn twist lattice points in Teichmüller space.
method Comparing growth rates of Dehn twist, mapping class group, and multi-twist lattice points.
result The growth rate of Dehn twist lattice points is coarsely asymptotic to $e^{ rac{h}{2}R}$, slower than the mapping class group.
We study the asymptotic behaviour of simply connected, Riemannian manifolds X of strictly negative curvature admitting a non-uniform lattice Γ. If the quotient manifold Xˉ=Γ\X is asymptotically 1/4-pinched, we prove that Γ is divergent and UXˉ has finite Bowen-Margulis measure (which is t…
The goal of this paper is to prove a result conjectured in Föllmer and Schachermayer [FS07], even in slightly more general form. Suppose that S is a continuous semimartingale and satisfies a large deviations estimate; this is a particular growth condition on the mean-variance tradeoff process of S. We show that S then …
New insights into manifold properties using Seiberg-Witten and L2 harmonic theories.
problem Characterizing properties of 4-manifolds with specific geometric conditions.
method Combining Seiberg-Witten theory on compact manifolds and L2 harmonic theory on non-compact manifolds, with a new argument for asymptotic properties. result Found a pair of homeomorphic 4-manifolds with distinct geometric properties under Riemannian metrics.
The paper examines Adaptive Lasso and Transfer Lasso, highlighting their differences and proposing a new method.
problem Comparing and contrasting Adaptive Lasso and Transfer Lasso.
method Theoretical analysis of asymptotic properties and introduction of a new method.
result The Transfer Lasso method reduces non-asymptotic estimation errors compared to Adaptive Lasso.
Data balancing reduces variance in machine learning models.
problem Reduction of variance in machine learning models.
method Non-asymptotic statistical bound and eigenvalue decay of Markov operators.
result Data balancing across modalities and sources reduces variance.
The theme of this paper is that algebraic complexity implies dynamical complexity for pseudo-Anosov homeomorphisms of a closed surface S_g of genus g. Penner proved that the logarithm of the minimal dilatation for a pseudo-Anosov homeomorphism of S_g tends to zero at the rate 1/g. We consider here the smallest dilatati…
UCB-V algorithm improves on UCB for MAB problems with variance estimates.
problem Optimizing arm selection in MAB problems with variance information.
method Asymptotic and high probability analysis of UCB-V algorithm.
result UCB-V can exhibit instability in arm-pulling rates but achieves refined regret bounds.
The paper explores isometric models and Busemann functions for Funk and Hilbert discs.
problem Exploring isometric models and Busemann functions for Funk and Hilbert discs.
method Finding and describing isometric models and computing Busemann functions.
result Proving asymptotic harmonicity of the Funk disc and showing its dependence on measure.
Model identifies causal structure from paired observational and interventional data with unknown soft interventions.
problem Identifying causal structure from observational and interventional data with unknown soft interventions.
method Proposes a scalable causal discovery model that aggregates subset-level PDAGs and applies contrastive cross-regime orientation rules.
result The model asymptotically recovers the identifiable PDAG and can orient additional edges compared to non-contrastive subset-restricted methods.
We prove that there is a true asymptotic formula for the number of one sided simple closed curves of length ≤L on any Fuchsian real projective plane with three points removed. The exponent of growth is independent of the hyperbolic structure, and it is noninteger, in contrast to counting results of Mirzakhani for…
Researchers simplify Einstein-scalar field equations on specific manifolds.
problem Complexity of Einstein-scalar field conformal constraint equations.
method Study under harmonic manifold assumptions, reducing equations to a single nonlinear equation.
result Solutions exist on Euclidean and hyperbolic manifolds, nonexistence on spheres.
New conditions for ACD model consistency and normality.
problem Random number of durations in ACD model.
method Additional sufficient conditions for consistency and normality of QMLE.
result Finite mean of durations is required for consistency and normality.
Refines geometric center of mass analysis for Einstein field equations.
problem Analyzing the geometric center of mass of Willmore surfaces in initial data for Einstein field equations.
method Refined Lyapunov-Schmidt analysis to study geometric center of mass of area-constrained Willmore surfaces.
result The geometric center of mass agrees with the Hamiltonian center of mass under specific conditions.
A new asymptotic expansion scheme for backward SDEs (BSDEs) is proposed.The perturbation parameter is introduced just to scale the forward stochastic variables within a BSDE. In contrast to the standard small-diffusion asymptotic expansion method, the dynamics of variables given by the forward SDEs is treated exactly. …
The paper compares Bayesian uncertainty to MAP estimator in random features regression.
problem Comparing Bayesian uncertainty to MAP estimator in random features regression.
method Analyzing the variance of the posterior predictive distribution and comparing it to the risk of the MAP estimator.
result Asymptotic agreement between Bayesian uncertainty and MAP estimator under specific signal-to-noise ratios and sample sizes.
In the context of the multi-dimensional infinite horizon optimal consumption-investment problem with proportional transaction costs, we provide the first order expansion in small transact costs. Similar to the one-dimensional derivation in our accompanying paper [42], the asymptotic expansion is expressed in terms of a…
Fast approximate nearest neighbor (NN) search in large databases is becoming popular. Several powerful learning-based formulations have been proposed recently. However, not much attention has been paid to a more fundamental question: how difficult is (approximate) nearest neighbor search in a given data set? And which …