Arithmetic spaces' thin parts are negligible, impacting Betti numbers.
problem Understanding the structure of arithmetic locally symmetric spaces.
method Analyzing thin parts and deducing asymptotic results on Betti numbers.
result Arithmetic spaces' thin parts are negligible, impacting Betti numbers.
It is shown that under mild conditions, Benjamini-Schramm convergence of lattices in locally compact groups is equivalent to spectral convergence. Next both notions are extended to the relative case and are then expressed in terms of relative L2-theory.
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.
Criterion for periodic orbits convergence proved.
problem Periodic orbits convergence criterion.
method Criterion for Benjamini-Schramm convergence of periodic orbits of Lie groups.
result Criterion for periodic orbits convergence proved.
Random translation surfaces converge to a Poisson plane as genus grows.
problem Understanding the geometric behavior of high genus translation surfaces.
method Proving convergence of random translation surfaces to a Poisson plane using statistical local geometric properties.
result The radius-r neighborhood of a random point in an MSV-distributed random translation surface converges in distribution to the radius r neighborhood of the root in a Poisson translation plane. Random hyperbolic surfaces with punctures converge to the Brownian sphere.
problem Understanding the geometry of random hyperbolic surfaces with punctures.
method Rescaling and encoding via plane trees with continuous labels.
result Rescaled random hyperbolic surfaces converge to the Brownian sphere.
We study Betti numbers of sequences of Riemannian manifolds which Benjamini-Schramm converge to their universal covers. Using the Price inequalities we developed elsewhere, we derive two distinct convergence results. First, under a negative Ricci curvature assumption and no assumption on sign of the sectional curvature…
Study on hyperbolic polyhedra and their volume, proving finiteness of arithmetic groups.
problem Finiteness of arithmetic maximal reflection groups in hyperbolic polyhedra.
method Observation of volume distribution and recent work with M. Fraczyk and S. Hurtado.
result Proof of finiteness of arithmetic maximal reflection groups.
We construct hyperbolic integer homology 3-spheres where the injectivity radius is arbitrarily large for nearly all points of the manifold. As a consequence, there exists a sequence of closed hyperbolic 3-manifolds which Benjamini-Schramm converge to H^3 whose normalized Ray-Singer analytic torsions do not converge to …
We discuss the geometry of some arithmetic orbifolds locally isometric to a product of real hyperbolic spaces of dimension two and three, and prove that certain sequences of non-uniform orbifolds are convergent to this space in a geometric ("Benjamini--Schramm") sense for hyperbolic three--space and a product of hyperb…
We study the convergence of volume-normalized Betti numbers in Benjamini-Schramm convergent sequences of non-positively curved manifolds with finite volume. In particular, we show that if X is an irreducible symmetric space of noncompact type, X=H3, and (Mn) is any Benjamini-Schramm convergent sequ…
Quantum mixing for eigenfunctions on hyperbolic surfaces converging to the hyperbolic plane.
problem Mixing of quantum eigenfunctions on converging hyperbolic surfaces.
method Duhamel formula for hyperbolic wave equation, exponential mixing of geodesic flow.
result Quantum mixing for eigenfunctions in large spectral windows.
We relate small 1-form Laplacian eigenvalues to relative cycle complexity on closed hyperbolic manifolds: small eigenvalues correspond to closed geodesics no multiple of which bounds a surface of small genus. We describe potential applications of this equivalence principle toward proving optimal torsion homology growth…
We prove that for certain sequences of hyperbolic three--manifolds with cusps which converge to hyperbolic three--space in a weak ("Benjamini-Schramm") sense and certain coefficient systems the regularized analytic torsion approximates the L2-torsion of the universal cover under an additional hypothesis. We also pro…
We study the asymptotic behaviour of Betti numbers, twisted torsion and other spectral invariants of sequences of locally symmetric spaces. Our main results are uniform versions of the DeGeorge--Wallach Theorem, of a theorem of Delorme and various other limit multiplicity theorems. A basic idea is to adapt the notion o…
The paper studies random covers of torus knot complements and their statistical properties.
problem Understanding the statistical behavior of finite covers of torus knot complements.
method Asymptotic subgroup growth analysis and Benjamini-Schramm limit theorems.
result Determination of the linear growth rate of Betti numbers for random covers of torus knot complements.
Linear upper bounds are provided for the size of the torsion homology of negatively curved manifolds of finite volume in all dimensions d=3. This extends a classical theorem by Gromov. In dimension 3, as opposed to the Betti numbers, the size of torsion homology is unbounded in terms of the volume. Moreover, the…
We show that there exist hyperbolic knots in the 3-sphere such that the set of points of large injectivity radius in the complement take up the bulk of the volume. More precisely, given a finite volume hyperbolic manifold, for any bound R>0 on injectivity radius, consider the set of points with injectivity radius at le…
Random harmonic maps into spheres converge to a specific metric under strong convergence of representations.
problem Understanding the behavior of harmonic maps into spheres under representation convergence.
method Introduced renormalized energy and harmonic representatives, proving convergence to a rescaled hyperbolic metric.
result Renormalized energies and harmonic representatives converge to a specific metric under strong convergence of representations.
We introduce a spectrum of monotone coarse invariants for metric measure spaces called Poincaré profiles. The two extremes of this spectrum determine the growth of the space, and the separation profile as defined by Benjamini--Schramm--Timár. In this paper we focus on properties of the Poincaré profiles of groups with …
Study different topologies on locally homogeneous spaces, finding new convergence examples.
problem Understanding convergence of locally homogeneous spaces under various topologies.
method Examined three topologies on moduli space of equivariant isometry classes of locally homogeneous Riemannian spaces.
result Found first examples of locally homogeneous spaces converging in one topology but not in another.
SGD converges with positive probability for non-convex deep neural networks under specific conditions.
problem Convergence of SGD for non-convex deep neural networks.
method Established local convergence with positive probability under local Łojasiewicz condition and additional structural assumption.
result SGD converges with positive probability for non-convex deep neural networks under specific conditions.
We analyze the local convergence of proximal splitting algorithms to solve optimization problems that are convex besides a rank constraint. For this, we show conditions under which the proximal operator of a function involving the rank constraint is locally identical to the proximal operator of its convex envelope, hen…
Local Bayesian optimization shows strong performance and converges well, contrary to folklore.
problem Understanding the behavior and convergence of local Bayesian optimization methods.
method Studied the behavior of local optimization strategies and rigorously analyzed a specific algorithm.
result Local Bayesian optimization algorithms converge well and perform strongly, contrary to the folklore.
Local adaptive methods in FL can accelerate convergence but introduce bias, which is corrected.
problem The effect of using adaptive optimization methods for local updates in federated learning.
method Proposed correction techniques to overcome the bias introduced by local adaptive methods.
result Correction techniques can achieve faster convergence and higher test accuracy than baseline methods.
Proves convergence of gradient Ricci shrinkers with uniform bounds.
problem Compactness and energy concentration in gradient Ricci shrinkers.
method Bubble-tree convergence and local energy analysis.
result No energy concentrates in neck regions, leading to a local diffeomorphism finiteness theorem.
New continuous-time optimization algorithms converge in finite time to local minima.
problem Finding local minima in optimization problems.
method Discontinuous dynamical systems with finite-time convergence via Lyapunov-based differential inequality.
result Finite-time convergence to strict local minima with provable settling time.
Local Gradient Descent with local steps converges to the centralized model in the interpolation regime.
problem Understanding the implicit bias of Local Gradient Descent in the interpolation regime.
method Analyzing the implicit bias of Local Gradient Descent for classification tasks with linearly separable data.
result The aggregated global model from Local-GD converges exactly to the centralized model in the interpolation regime.
Gradient method converges locally linearly for overparameterized Gaussian mixtures.
problem Learning Gaussian mixtures under overparameterization.
method Gradient-based method alternating short descent steps and long Polyak steps.
result Gradient method converges locally linearly to minimizers.
Randomly glued tetrahedra form connected 3-manifolds with a single boundary.
problem Understanding the properties of random three-manifolds formed by truncated tetrahedra.
method Asymptotic analysis of random glued manifolds, proving laws of large numbers, and bounding various topological and geometric properties.
result The random manifolds are connected, have a single boundary component, and admit a unique hyperbolic metric with a uniform spectral gap.
We investigate finite-time decoupled convergence in nonlinear two-time-scale stochastic approximation.
problem Achieving decoupled convergence in nonlinear two-time-scale stochastic approximation.
method Nested local linearity assumption, suitable step size selection, convergence analysis of matrix cross term, fourth-order moment convergence rates.
result Finite-time decoupled convergence rates can be achieved in nonlinear two-time-scale stochastic approximation with proper step size selection.
Paper develops a new local convexity condition for non-isolated minima in non-convex optimization.
problem Lack of theory for non-isolated minima in non-convex optimization.
method Formulates a new local convexity condition and studies SGD convergence under this condition.
result Shows SGD can converge locally under the new condition.
In this note we give necessary and sufficient conditions for the validity of the local spectral convergence, in balls, on the RCD∗-setting.
Study local convergence of GDA for training GANs with kernel-based discriminators.
problem Analyzing the local dynamics of GDA for GANs with kernel-based discriminators.
method Linearization of a non-linear dynamical system, under an isolated points model assumption.
result Showed phase transitions indicating convergence, oscillation, or divergence of GDA.
New method improves convergence in federated learning for nonconvex problems.
problem Optimizing global objective in distributed learning with non-i.i.d. data.
method Generalized local stochastic and full gradient descent with periodic averaging.
result Demonstrates convergence rates for nonconvex federated optimization.
Policy gradient converges linearly with Hadamard parameterization in tabular settings.
problem Convergence of policy gradient methods under Hadamard parameterization.
method Studied convergence rate and established linear convergence after k0 iterations. result Algorithm converges linearly with rate $O( rac{1}{k})$ and faster locally after k0. FedSARSA converges with heterogeneous agents, achieving linear speed-up.
problem Convergence analysis of Federated SARSA with heterogeneous agents.
method Linear function approximation, local training, multi-step error expansion.
result FedSARSA achieves linear speed-up with respect to the number of agents.
Improved Local SGD convergence for general convex objectives with bounded second-order heterogeneity.
problem Understanding when and why Local SGD outperforms alternatives in distributed optimization.
method Established improved convergence guarantees for Local SGD on general convex objectives under bounded second-order heterogeneity.
result Upper bounds for Local SGD are nearly tight, providing a sharper convergence theory.
Optimizes convergence time of federated learning over wireless networks.
problem Limited resource blocks in wireless networks affect federated learning convergence time and performance.
method Formulates an optimization problem to minimize convergence time while optimizing performance, proposes a probabilistic user selection scheme and uses ANNs for estimation.
result Improves convergence time and performance of federated learning over wireless networks.
SGD with large learning rates can converge to local maxima.
problem Understanding the behavior of SGD with large learning rates.
method Constructing worst-case optimization problems.
result SGD can converge to local maxima under certain conditions.
Paper analyzes convergence of GDA for nonconvex-nonconcave minimax problems.
problem Understanding convergence of GDA for nonconvex-nonconcave minimax problems.
method Local convergence analysis of GDA with stepsize ratio Θ(κ).
result Stepsize ratio of Θ(κ) is necessary and sufficient for local convergence of GDA to a Stackelberg Equilibrium.
The abstract discusses convergence properties of Lipschitz functions and sets defined by equations.
problem Convergence of Lipschitz functions and sets defined by equations.
method Painlevé-Kuratowski convergence applied to Lipschitz functions and sets defined by equations.
result Generalizations and reverses of classical theorems on convergence of functions and sets.
Stochastic gradient methods are dominant in nonconvex optimization especially for deep models but have low asymptotical convergence due to the fixed smoothness. To address this problem, we propose a simple yet effective method for improving stochastic gradient methods named predictive local smoothness (PLS). First, we …
New insights into continual learning for deep models, showing convergence issues but local linear solutions.
problem Challenges in continual learning for homogeneous deep models.
method Sequential projections onto task margin sets, leveraging nonconvex projection theory.
result Local linear convergence under certain conditions for homogeneous deep networks.
Paper proposes FR algorithm to solve minimax optimization locally.
problem Gradient descent fails to find local minimax in minimax optimization.
method Follow-the-Ridge (FR) algorithm, addressing rotational behavior of gradient dynamics.
result FR algorithm provably converges to local minimax.
Proves local convergence of various online and recurrent optimization algorithms.
problem Proves local convergence of online and recurrent optimization algorithms not covered by standard stochastic gradient descent theory.
method Uses a general set of assumptions for learning dynamical systems online, adopting an 'ergodic' viewpoint.
result Local convergence results for online and recurrent optimization algorithms, including RMSProp, NoBackTrack, UORO, Adam, and RTRL.
In this note we define a distance between two pointed locally integral current spaces. We prove that a sequence of pointed locally integral current spaces converges with respect to this distance if and only if it converges in the sense of Lang-Wenger. This enables us to state the compactness theorem by Lang-Wenger for …
Matrix completion has attracted much interest in the past decade in machine learning and computer vision. For low-rank promotion in matrix completion, the nuclear norm penalty is convenient due to its convexity but has a bias problem. Recently, various algorithms using nonconvex penalties have been proposed, among whic…