Equivalence shown between two mathematical concepts for hyperbolic surfaces.
problem None explicitly stated, but related to mathematical equivalence of concepts.
method Benjamini-Schramm convergence and zeta functions equivalence demonstration.
result Equivalence of Benjamini-Schramm convergence and zeta functions for compact hyperbolic surfaces.
The paper connects different convergence concepts in geometric analysis.
problem Comparing convergence concepts in geometric analysis.
method Relating Lp convergence and volume convergence to Intrinsic Flat and Gromov-Hausdorff convergence. result Conditions for convergence of Riemannian manifolds under specific conditions.
Study extends null distance concept to Lorentzian length spaces for spacetime analysis.
problem Understanding spacetime convergence and topology in Lorentzian geometry.
method Extend null distance concept to Lorentzian length spaces, study Gromov-Hausdorff convergence.
result First results on compatibility of null distance with synthetic curvature bounds in warped product Lorentzian length spaces.
This work shows how transformers use multi-concept word semantics for efficient in-context learning.
problem Understanding the connection between transformer-based LLMs' multi-concept semantic representation and their innovative in-context learning abilities.
method A concept-based low-noise sparse coding prompt model, leveraging advanced techniques to analyze the exponential convergence of 0-1 loss over non-convex training dynamics.
result Transformers leverage multi-concept word semantics to enable powerful and excellent out-of-distribution in-context learning.
We introduce a new concept, data irrecoverability, and show that the well-studied concept of data privacy is sufficient but not necessary for data irrecoverability. We show that there are several regularized loss minimization problems that can use perturbed data with theoretical guarantees of generalization, i.e., loss…
Study introduces fractional mass concept for surfaces, proving its convergence.
problem Understanding fractional mass on surfaces.
method Introduces fractional s-mass, proves Γ-convergence and pointwise convergence. result Fractional s-mass converges to (n−2)-dimensional area. The paper proves stability of the positive mass theorem using intrinsic flat convergence.
problem Stability of the positive mass theorem in mathematical relativity.
method Intrinsic flat convergence of points and applications to stability.
result Revisits and strengthens the stability results for graphical hypersurfaces of Euclidean space.
New algorithm learns multiclass concepts with finite Littlestone dimension.
problem Agnostic online multiclass classification in adversarial settings.
method Multiplicative weights algorithm with experts based on subsequences.
result Proves agnostic learnability if and only if Littlestone dimension is finite.
Study Gromov-Hausdorff convergence of metric pairs and tuples.
problem Understanding convergence in metric spaces.
method Prove equivalence of definitions, embedding, completeness, and compactness theorems.
result Relative version of Fukaya's theorem and finiteness theorem for stratified spaces.
BC-LLM uses LLMs to find concepts without predefined sets, improving interpretability and performance.
problem Finding a balance between interpretability and accuracy in concept extraction models.
method Bayesian approach with LLMs as both concept extractor and prior.
result BC-LLM outperforms interpretable and black-box models across various datasets.
Theory extends optimal learning rates without realizability assumption.
problem Agnostic binary classification without realizability assumption.
method Identifies tetrachotomy of optimal rates and combinatorial structures.
result Optimal universal rates for binary classification in agnostic setting.
New method tackles concept shifts in nonparametric regression using robust and adaptive transfer learning.
problem Concept shifts and sample scarcity in target domains hinder nonparametric regression.
method Robust and adaptive transfer learning procedure leveraging fixed bandwidth Gaussian kernels.
result Spectral algorithms with fixed bandwidth Gaussian kernels attain minimax convergence rates for nonparametric regression.
Introduces generalized almost statistical convergence and its properties.
problem Developing a new convergence concept for sequences.
method Introducing generalized almost statistical convergence and proving its properties.
result Existence of a GAS convergent sequence that is neither statistical nor almost convergent.
This paper analyzes saddle points and minimax points in non-convex smooth games.
problem Understanding local optimal points in non-convex smooth games.
method Comprehensive analysis of local minimax points, including their optimality conditions and stability.
result Local saddle points are uniformly local minimax points under mild continuity assumptions.
New approach proves convergence of SA and SGD with weaker conditions.
problem Proving convergence of SA and SGD with relaxed noise conditions.
method Introduces GSLLN to decouple function and noise properties.
result Derives sufficient conditions for convergence of SA and SGD.
The paper reconstructs Lorentzian spacetimes from causal sets.
problem Reconstructing Lorentzian spacetimes from causal sets.
method Introduced a concept of isomorphy and three types of convergence.
result Established Gromov's reconstruction theorem in Lorentzian geometry.
New approach for testable learning using moment matching and Rademacher complexity.
problem Replacing hard-to-verify distributional assumptions with testable ones.
method Moment matching and metric distances in probability.
result Improved sample complexity bounds for various concept classes and distributions.
New varifold solutions for mean curvature flow converge and are unique.
problem Mean curvature flow and Allen-Cahn equation convergence and uniqueness.
method Evolving varifolds coupled to phase volumes, weak-strong uniqueness principle.
result Limits of Allen-Cahn solutions are varifold solutions, and classical flows are unique.
The article introduces a new convergence concept for Lorentzian spaces and applies it to generalized cones.
problem Stability of curvature bounds in generalized Lorentzian cones.
method Introduces ℓ-convergence for Lorentzian pre-length spaces, applies it to generalized cones, and proves stability of curvature bounds. result Sharp timelike curvature and curvature-dimension bounds for generalized cones are established.
We consider the learning algorithms under general source condition with the polynomial decay of the eigenvalues of the integral operator in vector-valued function setting. We discuss the upper convergence rates of Tikhonov regularizer under general source condition corresponding to increasing monotone index function. T…
A new algorithm for K-means clustering in evolving data streams.
problem Clustering of continuously arriving data in streaming scenarios with concept drift.
method Formal definition of Streaming K-means, surrogate error function, algorithm for minimizing surrogate error. result The surrogate error function effectively approximates the Streaming K-means error. Variational method for eigenvalues on manifolds.
problem Optimizing functionals involving eigenvalues of Riemannian manifolds.
method New Palais-Smale sequences and min-max methods for locally-Lipschitz functionals.
result Convergence of Palais-Smale sequences in Laplace and Steklov eigenvalues.
We study the density estimation problem with observations generated by certain dynamical systems that admit a unique underlying invariant Lebesgue density. Observations drawn from dynamical systems are not independent and moreover, usual mixing concepts may not be appropriate for measuring the dependence among these ob…
Given a sequence of asymptotically flat 3-manifolds of nonnegative scalar curvature with outermost minimal boundary, converging in the pointed C0 Cheeger--Gromov sense to an asymptotically flat limit space, we show that the total mass of the limit is bounded above by the liminf of the total masses of the sequence. I…
Service robots benefit from encoding information in semantically meaningful ways to enable more robust task execution. Prior work has shown multi-relational embeddings can encode semantic knowledge graphs to promote generalizability and scalability, but only within a batched learning paradigm. We present Incremental Se…
One of the most fundamental concepts in statistics is the concept of sample mean. Properties of the sample mean that are well-defined in Euclidean spaces become unwieldy or even unclear in graph spaces. Open problems related to the sample mean of graphs include: non-existence, non-uniqueness, statistical inconsistency,…
We present an actor-critic framework for MDPs where the objective is the variance-adjusted expected return. Our critic uses linear function approximation, and we extend the concept of compatible features to the variance-adjusted setting. We present an episodic actor-critic algorithm and show that it converges almost su…
Researchers define quantiles on Riemannian manifolds using optimal transport.
problem Defining quantiles on nonlinear manifolds.
method Measure-transportation-based approach.
result Theoretical and empirical properties of quantile functions on manifolds.
Study homogenizes equations on parallelizable manifolds using tensor localization and periodicity.
problem Homogenizing oscillating linear elliptic equations on parallelizable manifolds.
method Two-scale convergence through localization and periodicity induced by geometry.
result Explicit cell formulae for the homogenization limit and a theory of two-scale convergence of tensors.
The subject of this article is the introduction of a new concept of well-posedness of Bayesian inverse problems. The conventional concept of (Lipschitz, Hellinger) well-posedness in [Stuart 2010, Acta Numerica 19, pp. 451-559] is difficult to verify in practice and may be inappropriate in some contexts. Our concept sim…
This thesis investigates belief propagation's performance in graphical models with loops.
problem Belief propagation's performance and convergence guarantees in models with loops are uncertain.
method Investigates how model parameters affect belief propagation's performance, convergence, and approximation quality.
result Model parameters influence the number of fixed points, convergence properties, and approximation quality of belief propagation.
New concept of proper-calibeating extends classic calibrated forecasts to proper scoring rules.
problem Defining and extending calibrated forecasts to proper scoring rules.
method Extending the concepts of calibrated and calibeating forecasts to proper scoring rules and proving their properties.
result Proper-calibration always implies calibration, but proper-calibeating does not necessarily imply calibeating.
New sampling and diffusion models methods introduced without density function assumptions.
problem Sampling and diffusion models without regularity assumptions.
method Inspired by reverse diffusion process, novel sampling and diffusion algorithms.
result Explicit convergence rate and dimension-free particle approximation convergence result.
Under short sales prohibitions, no free lunch with vanishing risk (NFLVR-S) is known to be equivalent to the existence of an equivalent supermartingale measure for the price processes (Pulido [22]). For two given price processes, we translate the property (NFLVR-S) in terms of so called structure conditions and we intr…
We derive scaling laws for optimizing neural networks in hardware.
problem Optimizing the large parameter space of neural networks in hardware.
method Analytical derivation of scaling laws for Coordinate Descent optimization.
result Convergence is exponential and scales linearly with the number of neurons.
The (global) Lipschitz smoothness condition is crucial in establishing the convergence theory for most optimization methods. Unfortunately, most machine learning and signal processing problems are not Lipschitz smooth. This motivates us to generalize the concept of Lipschitz smoothness condition to the relative smoothn…
Paper proves Shapley value convergence in Bayesian learning games.
problem Measuring contributions in cooperative games using Bayesian inference.
method Established convergence of Shapley value in parametric Bayesian learning games.
result Shapley value differences converge in probability to a limiting game.
This study analyses, through cross-section estimation methods, the influence of spatial effects and human capital in the conditional productivity convergence (product per worker) in the economic sectors of NUTs III of mainland Portugal between 1995 and 2002. To analyse the data, Moran's I statistics is considered, and …
We extend the concept of renormalized volume for geometrically finite hyperbolic 3-manifolds, and show that is continuous for geometrically convergent sequences of hyperbolic structures over an acylindrical 3-manifold M with geometrically finite limit. This allows us to show that the renormalized volume attains its…
Deep learning models viewed through tame geometry for convergence guarantees.
problem Understanding convergence guarantees in deep learning models.
method Introducing tame geometry concepts and tools for nonsmooth nonconvex settings.
result Illustrates tame geometry as a natural framework for AI systems, especially deep learning.
Enhanced Markov chain sampler learns network statistics faster.
problem Learning network statistics efficiently.
method Integrates graph Forman curvature into Markov chain transition probabilities and stationary distribution.
result Curved Markov chain Monte Carlo achieves faster convergence.
We study two important concepts in adversarial deep learning---adversarial training and generative adversarial network (GAN). Adversarial training is the technique used to improve the robustness of discriminator by combining adversarial attacker and discriminator in the training phase. GAN is commonly used for image ge…
New method shows how order of gradient updates impacts stability and convergence in deep learning.
problem Training deep learning models can be unstable and computationally expensive.
method Theoretical analysis and experiments with backward-SGD.
result The order of gradient updates affects stability and convergence, leading to improved performance.
Inspired by the work of Leung-Wan, we study the mean curvature flow in hyperkähler manifolds starting from hyper-Lagrangian submanifolds, a class of middle dimensional submanifolds, which contains the class of complex Lagrangian submanifolds. For each hyper-Lagrangian submanifold, we define a new energy concept called …
The paper studies invariant weighted Bergman metrics on domains.
problem Investigating invariant weighted Bergman metrics under biholomorphisms.
method Introducing invariant weight assignments, using Bergman's minimum integral method and domain version of Tian-Yau-Zelditch expansion.
result Uniform convergence of weighted Bergman kernels and metrics on uniform squeezing domains.
Deep reinforcement learning enables algorithms to learn complex behavior, deal with continuous action spaces and find good strategies in environments with high dimensional state spaces. With deep reinforcement learning being an active area of research and many concurrent inventions, we decided to focus on a relatively …
We prove a Gamma-convergence result for a family of bending energies defined on smooth surfaces in R3 equipped with a director field. The energies strongly penalize the deviation of the director from the surface unit normal and control the derivatives of the director. Such type of energies for example arise…
Proves continuum limits of Lipschitz learning using Γ-convergence.
problem Semi-supervised learning with graph-based methods and continuum limits of p-Laplacian learning. method Proves continuum limits of Lipschitz learning using Γ-convergence.
result Proves Γ-convergence in the L∞-topology to the supremum norm of the gradient.