We show that domains, that allow for convex functions with unbounded gradient at their boundary, are convex.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “Unbounded Gradients”
The paper provides gradient estimates for Neumann semigroups on manifolds with boundary under unbounded curvature conditions.
problem Gradient estimates for Neumann semigroups on manifolds with boundary under unbounded curvature conditions.
method Establishes Bismut-type formulas and gradient estimates for Feynman--Kac semigroups on Riemannian manifolds with boundary, under geometric conditions formulated in terms of Ricci curvature and second fundamental form.
result Derives pointwise gradient estimates for the Neumann semigroup under variable, possibly unbounded, lower curvature bounds.
We present a version of the equivariant gradient degree defined for equivariant gradient perturbations of an equivariant unbounded self-adjoint operator with purely discrete spectrum in Hilbert space. Two possible applications are discussed.
Gradient estimates, Bakry-Emery Ricci curvature and ellipticity for unbounded graph Laplaciansmath.DG
In this article, we prove gradient estimates under Bakry-Emery curvature bounds for unbounded graph Laplacians which satisfy an ellipticity assumption. As applications, we study completeness and finiteness of stochastically complete graphs under Bakry-Emery curvature bounds.
Improved SGD with AdaGrad stepsizes adapts to unknown parameters and unbounded gradients.
problem Adaptive optimization with unknown parameters and unbounded gradients.
method Stochastic Gradient Descent with AdaGrad stepsizes, without assuming problem parameters or strong global Lipschitz conditions.
result Sharp rates of convergence in both low-noise and high-noise regimes, supporting an affine variance noise model.
New method stabilizes saddle-point optimization with unbounded gradients.
problem Stochastic saddle-point optimization faces instability due to large gradients.
method Proposes a regularization technique to stabilize iterates.
result Yields meaningful performance guarantees even with unbounded gradients.
The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variancestat.ML
AdaGrad-Norm achieves optimal convergence rates for non-convex objectives without tuning.
problem Optimal convergence rates for non-convex, smooth objectives with adaptive step sizes.
method Adaptive SGD (AdaGrad-Norm) with self-tuning step sizes, analyzing under unbounded gradients and affine variance scaling.
result AdaGrad-Norm achieves order optimal convergence rate of $\mathcal{O}\left(\frac{\mathrm{poly}\log(T)}{\sqrt{T}}
ight)$ under optimal assumptions.
The CD equalities were introduced to imply the gradient estimate of laplace operator on graphs. This article is based on the unbounded Laplacians, and finally concludes some equivalent properties of the CD(K,)and CD(K,n).
Understanding the convergence performance of asynchronous stochastic gradient descent method (Async-SGD) has received increasing attention in recent years due to their foundational role in machine learning. To date, however, most of the existing works are restricted to either bounded gradient delays or convex settings.…
In this paper, we analyze a real-valued reflected backward stochastic differential equation (RBSDE) with an unbounded obstacle and an unbounded terminal condition when its generator has quadratic growth in the -variable. In particular, we obtain existence, comparison, and stability results, and consider the opti…
We consider smooth radial solutions to the Hamiltonian stationary equation which are defined away from the origin. We show that in dimension two all radial solutions on unbounded domains must be special Lagrangian. In contrast, for all higher dimensions there exist non-special Lagrangian radial solutions over unbounded…
Paper characterizes nc-rank using gradient flow on symmetric space.
problem Characterizing the noncommutative rank of matrices.
method Interprets residuals as gradients of a convex function on symmetric space and uses unbounded gradient flow.
result Noncommutative corank equals half the minimum gradient-norm of residuals.
Stochastic gradient Langevin dynamics (SGLD) is a computationally efficient sampler for Bayesian posterior inference given a large scale dataset. Although SGLD is designed for unbounded random variables, many practical models incorporate variables with boundaries such as non-negative ones or those in a finite interval.…
Paper studies Adam's convergence under relaxed assumptions, proving a rate of O(poly(log T)/sqrt(T)).
problem Understanding Adam's convergence in non-convex, stochastic optimization with unbounded gradients and noise.
method Introduced a comprehensive noise model and used it to prove Adam's convergence rate.
result Adam finds a stationary point with a rate of O(poly(log T)/sqrt(T)) in high probability.
We study Online Convex Optimization in the unbounded setting where neither predictions nor gradient are constrained. The goal is to simultaneously adapt to both the sequence of gradients and the comparator. We first develop parameter-free and scale-free algorithms for a simplified setting with hints. We present two ver…
New method for differentially private optimization with general Lipschitz conditions.
problem Differentially private optimization under general Lipschitz conditions.
method Generalized Lipschitz condition for per-sample gradients, tuning clip norm based on minimum per-sample Lipschitz constant.
result Efficacy of the recommended clip norm tuning method verified on 8 datasets.
Two algorithms improve federated learning efficiency and resilience.
problem Scalability issues in federated learning due to communication, privacy, and Byzantine attacks.
method Proposes two algorithms, Ada-StoSign and -StoSign, that compress gradients into bit vectors to reduce communication.
result Ada-StoSign converges with a rate of and outperforms existing methods.
We consider a curvature flow in the band domain , where, for a graphic curve , denotes its normal velocity and denotes its curvature. If contacts the two boundaries of with constant slopes, in 1993, Altschular and Wu \cite{AW1} proved that converge…
Nonlinear eigenvalue problems for a class of quasilinear operator on complete Riemannian manifoldsmath.AP
Study eigenvalue problems on Riemannian manifolds with specific curvature conditions.
problem Finding eigenvalues and eigenfunctions for quasilinear equations on Riemannian manifolds.
method Generalized Cheng--Yau gradient estimate for quasilinear equations on complete Riemannian manifolds.
result Eigenvalues give rise to unbounded eigenfunctions under certain conditions.
Gradient descent on Hadamard manifolds converges to boundary points, solving optimization problems.
problem Optimization on Hadamard manifolds with unbounded convex functions.
method Gradient descent, duality theorem, moment-weight inequality.
result Gradient descent converges to boundary points, solving optimization problems.
We construct exhaustion and cut-off functions with controlled gradient and Laplacian on manifolds with Ricci curvature bounded from below by a (possibly unbounded) nonpositive function of the distance from a fixed reference point, without any assumptions on the topology or the injectivity radius. Along the way we prove…
Hessian stability and convergence rates for entropic and Sinkhorn potentials via semiconcavitymath.PR
The paper analyzes stability and convergence rates of entropic and Sinkhorn potentials.
problem Stability and convergence rates of entropic and Sinkhorn potentials.
method Semiconcavity properties of entropic potentials and Schrödinger bridges.
result Exponential convergence rates for gradient and Hessian of Sinkhorn iterates.
New method for faster convergence in non-convex optimization with unbounded smoothness.
problem Finding first-order stationary points of non-convex functions with unbounded smoothness.
method Developed a stopped analysis technique to prove convergence rates for -smooth functions.
result Achieved convergence rates without uniform noise bounds.
Two new algorithms improve performance in adversarial bandits with unbounded losses.
problem Adversarial Multi-Armed Bandits with unbounded losses.
method Developed UMAB-NN and UMAB-G for non-negative and general unbounded losses respectively.
result UMAB-NN achieves the first adaptive and scale-free regret bound for non-negative unbounded losses.
Unbounded convex domains have zero mean curvature on disconnected boundaries.
problem Understanding mean curvature in unbounded convex domains.
method Analyzing mean curvature on disconnected boundary components.
result Mean curvature is zero on disconnected boundary components of unbounded mean convex domains.
We consider complete non-compact manifolds with either a sub-quadratic growth of the norm of the Riemann curvature, or a sub-quadratic growth of both the norm of the Ricci curvature and the squared inverse of the injectivity radius. We show the existence on such a manifold of a distance-like function with bounded gradi…
Nonlinear SGD achieves high-probability rates in non-convex optimization with heavy-tailed noise.
problem Optimization in non-convex problems with heavy-tailed noise.
method General nonlinear framework for SGD, including symmetrization techniques.
result Achieves rate for heavy-tailed noise.
We propose Zeno++, a new robust asynchronous Stochastic Gradient Descent~(SGD) procedure which tolerates Byzantine failures of the workers. In contrast to previous work, Zeno++ removes some unrealistic restrictions on worker-server communications, allowing for fully asynchronous updates from anonymous workers, arbitrar…
The paper proves homotopy equivalences for spaces of unbounded Fredholm operators.
problem Spaces of unbounded Fredholm operators and their properties.
method Analyzing the spaces and proving homotopy equivalences.
result Natural maps between four spaces of unbounded Fredholm operators are homotopy equivalences.
We consider prediction with expert advice under the log-loss with the goal of deriving efficient and robust algorithms. We argue that existing algorithms such as exponentiated gradient, online gradient descent and online Newton step do not adequately satisfy both requirements. Our main contribution is an analysis of th…
Golden L surface has unbounded bunching of saddle connections
problem Unbounded bunching of saddle connections on translation surfaces
method Translation surface with golden ratio
result Every positive integer K has a ball containing at least K saddle connection periods
We construct an unbounded representative for the shriek class associated to the embeddings of spheres into Euclidean space. We equip this unbounded Kasparov cycle with a connection and compute the unbounded Kasparov product with the Dirac operator on . We find that the resulting spectral triple for the…
This memoir presents a systematic study of the utility maximization problem of an investor in a constrained and unbounded financial market. Building upon the work of Hu et al. (2005) [Ann. Appl. Probab., 15, 1691--1712] in a bounded framework, we extend our analysis to the more challenging unbounded case. Our methodolo…
It is shown that the compactly supported identity component of the diffeomorphism group of the 2-dimensional punctured torus is an unbounded group. It follows that the fragmentation norm of is unbounded.
New inequalities for unbounded functions improve denoising score matching.
problem Statistical error bounds for denoising score matching with unbounded objective functions.
method Derive new concentration inequalities using McDiarmid's inequality and Rademacher complexity bounds.
result Improved statistical error bounds for denoising score matching.
Study focal surfaces of wave fronts with unbounded curvatures.
problem Characterizing singularities of focal surfaces near non-degenerate singular points.
method Characterizations based on types of singularities and geometrical properties of initial fronts.
result Investigation of Gaussian curvature behavior of focal surfaces.
FedBuff improves federated learning scalability with asynchronous updates.
problem Limited scalability of federated learning with synchronous updates.
method Introduces asynchronous updates (staleness) in federated learning.
result Theoretical analysis shows improved convergence rate with boundedness removed.
UDN adapts depth to data complexity, outperforming standard neural networks.
problem Adapting neural network depth to data complexity.
method Variational inference for infinitely deep neural networks with a novel algorithm.
result UDN outperforms standard neural networks and other infinite-depth approaches.
Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clippingcs.LG
New method improves fairness in DP learning by preventing excessive gradient suppression.
problem Disparate impact on model predictions for minority groups in DP learning.
method Bounded adaptive clipping to prevent excessive gradient suppression.
result Improves worst-class accuracy by over 10 percentage points compared to existing methods.
Study shows unbounded Pontryagin numbers on curved manifolds.
problem Understanding unbounded Pontryagin numbers on curved manifolds.
method Analyzing rational linear combinations of Pontryagin numbers and their relation to the universal elliptic genus.
result Proves existence of unbounded Pontryagin numbers on nonnegatively curved spin manifolds.
Paper tackles online control of linear systems with unbounded noise.
problem Online control of linear systems under unbounded noise with unknown convex cost functions.
method Developed an algorithm achieving high-probability regret under unbounded noise, and established regret bound for strongly convex costs and sub-Gaussian noise.
result Achieved high-probability regret under unbounded noise, and regret bound for specific noise and cost conditions.
Optimizes shortfall risk using gradient-based methods.
problem Optimizing utility-based shortfall risk measures.
method Gradient-based stochastic optimization, non-asymptotic bounds derivation.
result Non-asymptotic convergence rate for optimizing UBSR.
New approach finds solutions to games with unbounded controls.
problem Existence of equilibrium in mean-field games with unbounded controls.
method Weak formulation and new existence/stability results for quadratic-growth generalized McKean-Vlasov BSDEs.
result Existence of equilibrium result for non-Markovian mean-field games with unbounded control space.
New aggregation strategy handles unbounded losses with regret bounds.
problem Online optimization with unbounded loss functions.
method Follow The Regularized Leader (FTRL) with φ-divergence.
result Worst regret bound for unbounded losses with alternative divergences.
New algorithms optimize without tuning, matching tuned SGD performance.
problem Optimizing machine learning models without manual hyperparameter tuning.
method Formalizes tuning-free algorithms for matching SGD performance with loose hints.
result Tuning-free algorithms can match SGD performance, but not optimal convergence rates.
Improved sampling from Gaussian distributions with privacy constraints.
problem Sampling from unbounded Gaussian distributions with differential privacy.
method First $\widetilde{\mathcal{O}}\left(d
ight)$-sample algorithm for unbounded Gaussians under $\left(\varepsilon, δ
ight)$-differential privacy.
result A quadratic improvement over previous results, settling an open question.
Generalizes Ricci flow starting from small curvature concentration with a Morrey-type condition.
problem Ricci flow starting from manifolds with unbounded curvature.
method Replaces bounded curvature with a Morrey-type condition on the gradient of the metric relative to a complete bounded curvature metric.
result Long-time existence of Ricci flow with curvature decay estimates and diffeomorphic manifold.
New PAC-Bayes bounds for unbounded loss functions.
problem Generalization bounds for learning problems with unbounded loss functions.
method Introducing HYPE, a new notion for loss range, and deriving a novel PAC-Bayesian generalization bound.
result PAC-Bayes framework extended to unbounded loss functions.