2-regular points found in spaces with lower Ricci curvature bound.
problem Characterizing points in spaces with lower Ricci curvature bound.
method Analyzing measured Gromov-Hausdorff limits of Riemannian manifolds.
result 2-regular points in interior geodesics of limit spaces are 2-rectifiable.
Abstract reviews known and open questions on spaces with lower Ricci bounds.
problem Understanding the structure and regularity of spaces with lower Ricci curvature bounds.
method Review of known results and presentation of open questions.
result Presentation of new open questions in the field.
Lowered regularity assumption for a phase-dependent Helfrich energy equation.
problem Analyzing the phase separation line of the Helfrich energy.
method Used a carefully chosen test function with a signed distance function.
result Regularity assumption lowered from C2 to C1,1 for the phase separation line. Extends Margulis Lemma to RCD(K,N) spaces.
problem Applying Margulis Lemma to new geometric structures.
method Improved Regularity Estimates for Regular Langrangian Flows.
result Margulis Lemma extended to RCD(K,N) spaces.
This paper improves reinforcement learning policies in a scalable way.
problem Ensuring monotonic policy improvement in entropy-regularized RL.
method Derives an entropy-aware lower bound and proposes a novel RL algorithm.
result Demonstrates effectiveness in continuous-state tasks using a linear function approximator.
Lower bounds for PL 4-manifolds with boundary are improved.
problem Estimating PL 4-manifolds with boundary.
method Proved inequalities for regular genus and gem-complexity.
result Improved lower bounds for PL 4-manifolds with boundary.
Study on adaptivity to kernel regularity in bandit problems.
problem Adaptation to unknown kernel regularity in continuum-armed bandit problems.
method Derive adaptivity lower bound and verify with minimax non-adaptive kernelised bandit algorithms.
result Impossibility of achieving optimal cumulative regret in different RKHSs with varying regularities.
Careful tuning of a regularization parameter is indispensable in many machine learning tasks because it has a significant impact on generalization performances. Nevertheless, current practice of regularization parameter tuning is more of an art than a science, e.g., it is hard to tell how many grid-points would be need…
Optimal sampling bounds for various classification losses under different regularization terms.
problem Achieving optimal sampling complexity for classification losses under different regularization terms.
method Proved optimal sampling bounds for a broad class of Lipschitz continuous classification loss functions under various regularization terms.
result Proved k2/ε2 upper and lower bounds for ∥⋅∥2/k regularization, and k/ε2 upper and lower bounds for ∥⋅∥1/k regularization. The dynamical analysis of American options has motivated the development of robust versions of the classical Snell envelopes. The cost of superhedging an American option is characterized by the upper Snell envelope. The infimum of the arbitrage free prices is characterized by the lower Snell envelope. In this paper we …
Within crystallization theory, two interesting PL invariants for d-manifolds have been introduced and studied, namely {\it gem-complexity} and {\it regular genus}. In the present paper we prove that, for any closed connected PL 4-manifold M, its gem-complexity k(M) and its regular genus $ \mathcal G(M)…
The paper proves weak continuity of Cartan structural system on semi-Riemannian manifolds with lower regularity.
problem Weak continuity of the Cartan structural system on semi-Riemannian manifolds with lower regularity.
method Formulated and proved a geometric compensated compactness theorem, deduced Lp weak continuity of the Cartan structural system. result Weak continuity of the Cartan structural system and Gauss-Codazzi-Ricci system on semi-Riemannian manifolds with lower regularity.
The paper develops bounds and regularity for minimal boundaries in non-smooth spaces with Ricci curvature.
problem Minimal boundaries in non-smooth spaces with Ricci curvature.
method Intrinsic theory of Laplacian bounds, PDE principle, sharp Laplacian bounds on distance function, regularity theory for perimeter-minimizing boundaries.
result Sharp Laplacian bounds and regularity results for perimeter-minimizing boundaries.
We propose a new point of view for regularizing deep neural networks by using the norm of a reproducing kernel Hilbert space (RKHS). Even though this norm cannot be computed, it admits upper and lower approximations leading to various practical strategies. Specifically, this perspective (i) provides a common umbrella f…
Lower discount factors act as a regularizer in RL, improving performance.
problem Improving RL performance with limited data.
method Explicitly equating reduced discount factors to regularization terms.
result Regularization effectiveness depends on data properties.
ProxSPS improves on SPS for regularization tasks, offering better stability and performance.
problem Handling regularization terms in adaptive step size schemes for stochastic gradient descent.
method Developed a proximal variant of the stochastic Polyak step size (SPS) scheme.
result ProxSPS is easier to tune and more stable with regularization, and performs well in image classification tasks.
The paper defines weak lower scalar curvature bounds for C0 metrics and shows their stability under Ricci flow.
problem Defining and proving stability of weak lower scalar curvature bounds for metrics with low regularity.
method Proposes local definitions of weak lower scalar curvature bounds for C0 metrics, shows stability under perturbation, and defines a Ricci flow for C0 initial data. result Weak lower scalar curvature bounds are preserved under Ricci flow from C0 initial data. Uniform sampling of modest size is a coreset for regularized loss minimization.
problem Designing efficient algorithms for large data with restricted access.
method Sampling-based algorithms for regularized loss minimization problems.
result Uniform sample of modest size is a coreset for certain regularized loss minimization problems.
Proves existence and regularity of spherical minimizers for lipid membrane energy.
problem Existence and regularity of minimizers for the Canham-Helfrich energy.
method Establishes lower semicontinuity and proves existence through weak convergence of immersions.
result Proves existence and regularity of minimizers for the Canham-Helfrich energy on spheres.
Lower bounds on cone density for nontrivial complements in low dimensions.
problem Finding density limits for minimal cones with nontrivial complements.
method Proving lower bounds on cone density for cones of dimensions less than seven with nontrivial complements.
result Established lower bounds on cone density for minimal cones with nontrivial complements in dimensions less than seven.
Paper develops proper, lower-bounded losses for weakly supervised classification.
problem Weakly supervised classification with corrupted labels.
method Representation theorem for proper losses, derived condition for lower-boundedness, generalized logit squeezing.
result Proper and lower-bounded losses for weak-label learning.
For the problem of high-dimensional sparse linear regression, it is known that an ℓ0-based estimator can achieve a 1/n "fast" rate on the prediction error without any conditions on the design matrix, whereas in absence of restrictive conditions on the design matrix, popular polynomial-time methods only guarante…
Improved fast rates for decision making with forward-KL regularization in contextual bandits.
problem Improving fast rates for decision making with forward-KL regularization in contextual bandits.
method Streamlined analysis of forward-KL-regularized offline CBs, exploiting the pessimism principle and convex-analytical pipeline.
result First ildeO(ε−1) upper bounds in tabular and general function approximation settings. We prove a new kind of estimate that holds on any manifold with lower Ricci bounds. It relates the geometry of two small balls with the same radius, potentially far apart, but centered in the interior of a common minimizing geodesic. It reveals new, previously unknown, properties that all generalized spaces with a lowe…
We consider isotropic non lower semicontinuous weighted perimeter functionals defined on partitions of domains in Rn. Besides identifying a condition on the structure of the domain which ensures the existence of minimizing configurations, we describe the structure of such minima, as well as their regularity…
Surveying Ricci flow for weak lower scalar curvature bounds.
problem Creating local definitions for weak lower scalar curvature bounds for C0 metrics. method Using Ricci flow to define and analyze weak lower scalar curvature bounds.
result Properties and applications of Ricci flow in defining weak lower scalar curvature bounds.
We prove that pseudo-holomorphic discs attached to a maximal totally real submanifold inherit their regularity from the regularity of the submanifold and of the almost complex structure. The proof is based on the computation of an explicit lower bound for the Kobayashi metric in almost complex manifolds, which also yie…
In this paper, we study the structure of the pointed-Gromov-Hausdorff limits of sequences of Ricci shrinkers. We define a regular-singular decomposition following the work of Cheeger-Colding for manifolds with a uniform Ricci curvature lower bound, and prove that the regular part of any Ricci shrinker limit space is co…
Exact minimax risk derived for linear prediction with sample covariance analysis.
problem Understanding the minimax risk in linear prediction under various covariate distributions.
method Exact minimax risk analysis, leveraging statistical leverage scores and PAC-Bayes techniques.
result The minimax risk is of order d/(n−d+1) for any covariate distribution, nearly matching the risk for Gaussian design. Study on Lin-Lu-Yau curvature and diameter of amply regular graphs.
problem Lower bounds of Lin-Lu-Yau curvature in amply regular graphs.
method Application of Hall's marriage theorem and geometric proof.
result Conference graphs have positive Lin-Lu-Yau curvature.
Sharp bounds on diameter and eigenvalues for amply regular graphs.
problem Finding bounds for amply regular graphs' diameter and eigenvalues.
method New ideas relating discrete Ricci curvature to local matching properties, including a novel construction of a regular bipartite graph.
result Sharp diameter and eigenvalue bounds for amply regular graphs.
Uniform curvature bounds for regularized metrics with bounds on Ricci tensor and injectivity radius.
problem Bounding curvature of regularized metrics with constraints on Ricci tensor and injectivity radius.
method Mollification of riemannian metrics, uniform W2,p-harmonic radius bounds, Ricci tensor bounds, injectivity radius bounds. result Uniform estimate on the change of sectional curvature for regularized metrics.
New algorithm reduces regret in collaborative multi-agent bandit problems.
problem Optimizing decisions in a network of agents with communication delays.
method Follow-the-Regularized-Leader (FTRL) algorithm with suitable regularizers and communication protocols.
result Upper bound on individual regret matches lower bound up to a constant factor.
New models for short rates show longer periods at higher rates.
problem Modeling longer periods of higher interest rates.
method Developed a class of time-homogeneous one-factor Markov diffusion models with specific boundary conditions.
result Explicit expressions for bond prices and transition densities in new probability measure.
Improved prediction of hierarchical time series using structured regularization.
problem Making coherent forecasts for hierarchical time series.
method Structured regularization method for bottom-level time series predictions.
result Superior prediction accuracy and computational efficiency compared to previous methods.
GAN+VER improves GANs by regularizing entropy to reduce mode collapse.
problem Mode collapse in GANs where the generator fails to capture all modes.
method Maximizing a variational lower bound on the entropy of generated samples.
result Significant improvement in evaluation metrics for real and generated samples.
Unified framework for sparse logistic regression with nonconvex regularization.
problem Sparse logistic regression with nonconvex regularization.
method Unified framework, line search criteria for nonconvex terms.
result Effective classification and feature selection at lower computational cost.
The paper provides gradient estimates for solutions on manifolds with integral Ricci bounds.
problem Global regularity estimates for solutions of Δu=f on Riemannian manifolds. method Proves Lp-gradient estimates under integral Ricci bounds and constructs a counterexample. result Optimal constant lower bounds on Ricci curvature are shown in the pointwise sense.
New bounds on geodesic dimension and curvature exponent in Carnot groups.
problem Characterizing geodesic dimension and curvature exponent in Carnot groups.
method Characterization and lower bound calculation for geodesic dimension and curvature exponent.
result Found an example where curvature exponent is greater than geodesic dimension.
Improves deep transfer learning by preventing performance degradation.
problem Deep transfer learning can degrade performance when using inappropriate pre-trained weights.
method Proposes a novel strategy to compute new descent directions that preserve regularization effects.
result DTNH strategy improves performance of deep transfer learning tasks by 0.1%--7%.
Stability of timelike Ricci bounds in low-regularity spacetimes.
problem Stability of synthetic timelike Ricci curvature bounds under C0-limits. method Constructing smooth approximations and analyzing limiting behavior via Lorentzian optimal transport.
result Impulsive gravitational waves satisfy synthetic timelike Ricci curvature lower bounds.
We prove that any two Kahler potentials on a compact Kahler manifold can be connected by a geodesic segment of C^{1,1} regularity. This follows from an a priori interior real Hessian bound for solutions of the nondegenerate complex Monge-Ampere equation, which is independent of a positive lower bound for the right hand…
We are concerned with the global weak rigidity of the Gauss-Codazzi-Ricci (GCR) equations on Riemannian manifolds and the corresponding isometric immersions of Riemannian manifolds into the Euclidean spaces. We develop a unified intrinsic approach to establish the global weak rigidity of both the GCR equations and isom…
Positive mass theorem for asymptotically flat manifolds with non-negative distributional scalar curvature
problem Positive mass theorem
method Ricci flow smoothing
result Asymptotically flat manifolds with non-negative ADM mass
New principles prove precompactness of domains with lower Ricci curvature bound.
problem Proving precompactness of domains with lower Ricci curvature bound.
method Quantitative Hopf-Rinow theorem and doubling property.
result New precompactness principles applicable to incomplete Riemannian manifolds.
New bound on Gaussian process improves generalization.
problem Improving generalization in Gaussian process regression.
method Introducing a new closed-form lower bound on Gaussian process likelihood based on Rényi α-divergence.
result The new bound can control and tune regularization, potentially improving over traditional methods.
This paper sets lower bounds for scalar curvatures in Ricci flow singularity models.
problem Understanding scalar curvatures in Ricci flow singularity models.
method Developed high-dimensional theory of Hamilton's Ricci flow, including new monotonicity formulas, compactness theorem, and partial regularity theory.
result Obtained a quadratic decay lower bound for the scalar curvature in 4-dimensional non-Ricci-flat steady soliton singularity models.
Eigenvalue estimates without Bakry-Emery-Ricci bounds established.
problem Eigenvalue estimates for Laplace-Beltrami operators with drift.
method Establishes a lower bound for real eigenvalues without assuming self-adjointness or additional regularity of the drift.
result Establishes a lower bound on the spectrum of Laplace-Beltrami operators without assuming a lower bound for the Bakry-Emery Ricci tensor.