We propose a general framework for increasing local stability of Artificial Neural Nets (ANNs) using Robust Optimization (RO). We achieve this through an alternating minimization-maximization procedure, in which the loss of the network is minimized over perturbed examples that are generated at each parameter update. We…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “local parameter stability”
We study the problem of stochastic optimization for deep learning in the parallel computing environment under communication constraints. A new algorithm is proposed in this setting where the communication and coordination of work among concurrent processes (local workers), is based on an elastic force which links the p…
The paper improves SVM and localized SVM stability under triple perturbations.
problem Stability of SVMs and localized SVMs under triple perturbations.
method Generalizes and improves existing results, considering simultaneous variations in probability measure, regularization parameter, and kernel.
result Improved stability of SVMs and localized SVMs under triple perturbations.
Develops a diagnostic framework for interest rate model calibration, showing equivalence to Weighted Least Squares and revealing boundary-dominated leverage and local parameter instability.
problem Calibration of stochastic interest rate models
method Diagnostic framework using non-linear regression and analytical tractability of At-The-Money caps
result Reveals boundary-dominated leverage and local parameter instability
Study identifies key parameters and input dimensions making LLMs and VLMs brittle.
problem Vulnerability of large language and vision-language models to perturbations.
method Proposed FI measure based on information geometry to quantify sensitivity.
result Small subset of high FI parameters significantly contribute to brittleness.
We consider a transfer-learning problem by using the parameter transfer approach, where a suitable parameter of feature mapping is learned through one task and applied to another objective task. Then, we introduce the notion of the local stability and parameter transfer learnability of parametric feature mapping,and th…
Despite the growing prominence of generative adversarial networks (GANs), optimization in GANs is still a poorly understood topic. In this paper, we analyze the "gradient descent" form of GAN optimization i.e., the natural setting where we simultaneously take small gradient steps in both generator and discriminator par…
FedCONST adapts update magnitudes to enhance feature generalization in FL.
problem Heterogeneous client data in FL leads to overfitting and distorted transferable features.
method FedCONST uses linear convex constraints to stabilize training and preserve generalization.
result FedCONST enhances feature transferability and robustness, achieving state-of-the-art performance.
Paper proves stability of positive mass theorem for specific types of manifolds.
problem Stability of positive mass theorem for compact graphical manifolds.
method Used Federer--Fleming flat distance and static quasi-local Brown-York energy.
result Proved stability of positive mass theorem for compact (locally) hyperbolic graphical manifolds.
Study local properties of Chern-scalar curvature through linearization stability.
problem Local properties of Chern-scalar curvature function.
method Linearization analysis of the Chern-scalar curvature function.
result Stability of linearization and structure of metrics with prescribed curvature.
New method escapes local optima in neural architecture optimization.
problem Escaping local optima in neural architecture optimization.
method Signed neural splitting in steepest descent framework.
result Escapes local optima, leading to better performance.
New stabilization found in planar elasticae with degenerate diffusion.
problem Existence of local minimizers in degenerate -elasticae.
method Analysis of pinned planar -elasticae with degenerate diffusion.
result Uncountably many local minimizers with diverging energy in degenerate regime.
Proves stability of lcK spaces under holomorphic mappings.
problem Stability of locally conformally Kähler spaces with singularities.
method Analyzes sufficient conditions for proper open morphisms of lcK spaces.
result Extends Varouchas' result to lcK spaces with singularities.
Introduces stability conditions for polarized varieties, linking to K-stability.
problem Stability conditions for polarized varieties.
method Analogue of Bridgeland's stability for polarized varieties, Z-stability, Z-critical Kähler metrics.
result Polarized varieties with certain stability conditions admit Z-critical Kähler metrics.
Stability of a quasi-local positive mass theorem for graphical hypersurfaces of Euclidean spacemath.DG
The paper proves stability of a quasi-local positive mass theorem for graphical hypersurfaces.
problem Stability of a quasi-local positive mass theorem for graphical hypersurfaces.
method Worked with the Brown--York quasi-local mass, considering compact n-manifolds with boundary as graphs in R^(n+1).
result If the Brown--York mass of the boundary of a compact manifold is small, then the manifold is close to a Euclidean hyperplane.
Learning to make decisions from observed data in dynamic environments remains a problem of fundamental importance in a number of fields, from artificial intelligence and robotics, to medicine and finance. This paper concerns the problem of learning control policies for unknown linear dynamical systems so as to maximize…
We provide a sufficient condition for the local stability of closed Einstein manifolds of positive Ricci curvature under the Ricci iteration in terms of the spectrum of the Lichnerowicz Laplacian acting on divergence-free tensor fields. We use this result to consider the stability of several Einstein manifolds under th…
Cross-validation (CV) is often used to select the regularization parameter in high dimensional problems. However, when applied to the sparse modeling method Lasso, CV leads to models that are unstable in high-dimensions, and consequently not suited for reliable interpretation. In this paper, we propose a model-free cri…
By use of a natural extension map and a power series method, we obtain a local stability theorem for p-Kähler structures with the -th mild -lemma under small differentiable deformations.
Cubic fourfolds have K-stability and admit Kähler-Einstein metrics.
problem Understanding K-stability and Kähler-Einstein metrics for cubic fourfolds.
method Local volume estimates and Ambro-Kawamata's non-vanishing theorem.
result All smooth cubic fourfolds admit Kähler-Einstein metrics.
Generalization in nonlinear least squares can be studied via algorithmic stability and effective dimension.
problem Generalization in nonlinear least squares models
method Deriving error bounds for local minimizers using algorithmic stability and effective dimension
result Bounds depend on learned geometry rather than parameter count
This paper analyzes a simplified strategy for nonlinear control using local linear models and iLQR updates.
problem Nonlinear policy optimization in control systems.
method Iterative estimation of local linear models and iLQR-like policy updates.
result Demonstrates polynomial sample complexity and overcomes exponential problem horizon dependence.
We prove a version the local Reeb-Thurston stability theorem for symplectic foliations.
In this article we develop a new approach to the problem of the stability of locally conformally Kähler structures (l.c.k structures) under small deformations of complex structures and deformations of flat line bundles. We show that under the certain cohomological condition the stability of l.c.k structures does hold. …
Gradient filters track moving parameters under noisy data and misspecification.
problem Tracking multidimensional time-varying parameters under noisy observations and model misspecification.
method Gradient-based filters update parameters using the gradient of a postulated objective function, evaluated at either the predicted or updated parameters.
result Novel sufficient conditions for exponential stability of the filtered parameter path, and finite-sample and asymptotic mean squared error bounds.
Neural network training is usually accomplished by solving a non-convex optimization problem using stochastic gradient descent. Although one optimizes over the networks parameters, the main loss function generally only depends on the realization of the neural network, i.e. the function it computes. Studying the optimiz…
We investigate the role of the initialization for the stability of the k-means clustering algorithm. As opposed to other papers, we consider the actual k-means algorithm and do not ignore its property of getting stuck in local optima. We are interested in the actual clustering, not only in the costs of the solution. We…
The study examines stability and instability of Poincaré-Einstein metrics using Ricci flow.
problem Stability and instability of Poincaré-Einstein metrics.
method Variant of expander entropy for asymptotically hyperbolic manifolds, local positive mass theorem, volume comparison.
result Characterization of stability and instability in terms of local positive mass theorem and volume comparison.
We prove that any limit-interface corresponding to a locally uniformly bounded, locally energy-bounded sequence of stable critical points of the van der Waals--Cahn--Hilliard energy functionals with perturbation parameter tending to 0 is supported by an embedded smooth stable minimal hypersurface in low dimensions and …
Introduces TPV to analyze model robustness without labels.
problem Analyzing post-training robustness of machine learning models.
method Parameter perturbations and test prediction variance (TPV) as a unifying framework.
result TPV connects various perturbations under a single lens, providing insights into model stability.
EAGLE improves reproducibility and stability of model explanations.
problem Creating reliable explanations for opaque machine learning models.
method Formulates perturbation selection as an information-theoretic active learning problem.
result EAGLE learns a linear surrogate model with feature importance scores and uncertainty estimates.
Paper analyzes robustness of data-selective Volterra NLMS algorithm.
problem Robustness analysis of data-selective Volterra NLMS algorithm.
method The paper analyzes the local robustness and proposes a global bound for the error in the coefficient vector.
result The DS-VNLMS algorithm is robust against noise and improves parameter estimation for most iterations.
Wider networks improve natural accuracy but worsen perturbation stability, affecting overall robustness.
problem Understanding the tradeoff between natural accuracy and perturbation stability in wider neural networks for adversarial robustness.
method Careful examination of the relationship between network width, robust regularization parameter λ, and perturbation stability using neural tangent kernels.
result Wider networks can achieve better natural accuracy but worse perturbation stability, leading to potentially worse overall model robustness.
The study proves stabilizing of ascending chains in specific groups.
problem Stabilization of ascending chains in bounded rank subgroups of 3-manifold groups.
method Reduction to hyperbolic 3-manifolds and use of geometrization.
result Ascending chains in toral relatively hyperbolic groups stabilize.
Paper analyzes adaptive ISTA with MAD for LASSO problem.
problem Finding solutions to LASSO problems without tuning .
method Adaptive ISTA with median absolute deviation (MAD) for estimating noise level.
result Local linear convergence and global convergence of the algorithm.
Recently, many regularized procedures have been proposed for variable selection in linear regression, but their performance depends on the tuning parameter selection. Here a criterion for the tuning parameter selection is proposed, which combines the strength of both stability selection and cross-validation and therefo…
We prove an estimate for spherical functions on , establishing uniform decay in the spectral parameter when the group parameter is restricted to a compact subset of the abelian subgroup . In the case of , it improves a result by J.…
We formulate and analyze a multi-agent model for the evolution of individual and systemic risk in which the local agents interact with each other through a central agent who, in turn, is influenced by the mean field of the local agents. The central agent is stabilized by a bistable potential, the only stabilizing force…
Adaptive estimation of alpha-Stable distribution and Hurst exponent for nonstationary time series.
problem Nonstationary time series require adaptive models to avoid bias.
method Moving estimator with exponentially weakening weights of old values, optimized using EMA of absolute central moments.
result Continuous adaptive estimation of alpha-Stable distribution and Hurst exponent for market stability evaluation.
Stability of the Catenoid for the Hyperbolic Vanishing Mean Curvature Equation Outside Symmetrymath.AP
Stability of catenoid in hyperbolic space proven without symmetry assumptions.
problem Stability of catenoid in hyperbolic space.
method Profile construction, modulation analysis, integrated local energy decay, vectorfield method.
result Nonlinear asymptotic stability of catenoid for without symmetry assumptions.
MARL improves LBM stability and accuracy across scales.
problem Stability and accuracy issues in under-resolved LBM simulations.
method Multi-Agent Reinforcement Learning (MARL) to dynamically control local relaxation parameters.
result MARL closures stabilize simulations and recover spectra of fully resolved models.
The paper studies Yamabe metrics and stability in Riemannian manifolds.
problem Existence of complete Yamabe metrics with zero scalar curvature.
method Yamabe flow and local -stability analysis.
result Local -stability of the Yamabe flow on manifolds with non-negative Ricci curvature.
We provide a proof of the controlled surgery sequence, including stability, in the special case that the local fundamental groups are trivial. Stability is a key ingredient in the construction of exotic homology manifolds by Bryant, Ferry, Mio and Weinberger, but no proof has been available. The development given here …
Survey explores geometric aspects of policy optimization in control systems.
problem Understanding the geometric relationships between control design and optimization.
method Geometric perspective on policy optimization, focusing on parameterization and topology.
result Implications of policy geometry on stability and performance of local search algorithms.
AOPU stabilizes NN training by approximating natural gradient, improving stability and convergence.
problem Stability and interpretability in online NN training for industrial soft sensors.
method AOPU truncates gradient backpropagation, optimizing trackable parameters, and approximating natural gradient.
result AOPU achieves stable convergence and superior performance on chemical process datasets.
By use of a natural map introduced recently by the first and third authors from the space of pure-type complex differential forms on a complex manifold to the corresponding one on the small differentiable deformation of this manifold, we will give a power series proof for Kodaira-Spencer's local stability theorem of Kä…
Generalizes tools for studying collapsed manifolds to new geometry.
problem Studying collapsed manifolds with bounded sectional curvature.
method Generalizes fibration and stability theorems for compact group actions on manifolds with local bounded Ricci covering geometry.
result Two generalized results used in Xiaochun Rong's work on almost flat manifolds.
GLIME improves LIME's stability and local fidelity.
problem LIME's instability and low local fidelity.
method Introducing GLIME, an enhanced framework that derives an equivalent formulation of LIME with faster convergence and improved stability.
result GLIME generates explanations with higher local fidelity and is independent of reference choice.