Research
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

3667331,0991,465 · Jun 202019922001200920172026
48 results for model stability

To date, the instability of prognostic predictors in a sparse high dimensional model, which hinders their clinical adoption, has received little attention. Stable prediction is often overlooked in favour of performance. Yet, stability prevails as key when adopting models in critical areas as healthcare. Our study propo…

2016-09-28abs ↗pdf ↗

Paper improves zero-shot protein stability prediction by clarifying free-energy foundations.

problem Improving zero-shot protein stability prediction using inverse folding models.
method Clarifying the free-energy foundations of inverse folding models and proposing better estimates of relative stability.
result Significant gains in zero-shot performance can be achieved with simple methods.

Paper introduces stability in model averaging and proposes a L2-penalty method.

problem Theoretical properties of model averaging from stability perspective.
method Introduces stability, defines asymptotic empirical risk minimizer, and proposes L2-penalty model averaging method.
result Proposed L2-penalty method ensures stability and consistency under reasonable conditions.

Introduces valuative stability for polarised varieties, equivalent to K-stability.

problem Characterizing K-stability for polarised varieties.
method Introduces valuative stability, equivalent to K-stability for test configurations with integral central fibre.
result Equivalence of valuative stability and K-stability for polarised varieties.

Extends K-stability theory to projective klt pairs with a big anticanonical class.

problem Behavioral pathologies in K-stability for projective klt pairs with a big anticanonical class.
method Extends K-stability theory to projective klt pairs with a big anticanonical class, observing that K-semistability forces a klt anticanonical model with the same stability property.
result K-semistability forces projective klt pairs with a big anticanonical class to have a klt anticanonical model with the same stability property.

Proposes a new stability measure for model fitting on similar feature data sets.

problem Model fitting on data sets with similar features is challenging.
method Tuning hyperparameters in a multi-criteria fashion with predictive accuracy and feature selection stability.
result Our approach achieves similar or better predictive performance than single-criteria and stability selection approaches.

Paper relaxes stability and generalization assumptions for SGD.

problem Stability and generalization for SGD under restrictive assumptions.
method Introduces on-average model stability and develops novel bounds.
result First-ever-known fast bounds in low-noise setting using stability approach.

Paper analyzes stability and forgetting in score-based generative models.

problem Understanding the stability and long-time behavior of generative models.
method Quantitative bounds on sampling error using stability and forgetting properties of the Markov chain.
result Provides practical consequences of stability and contraction mechanism in sampling.

Geometric stability predicts steerability and detects drift in language models.

problem Predicting steerability and detecting drift in language models.
method Supervised and unsupervised geometric stability measures.
result Supervised geometric stability predicts steerability with high accuracy and detects drift earlier.

Stacking is a general approach for combining multiple models toward greater predictive accuracy. It has found various application across different domains, ensuing from its meta-learning nature. Our understanding, nevertheless, on how and why stacking works remains intuitive and lacking in theoretical insight. In this …

2019-01-26abs ↗pdf ↗

Stabilizes complex systems using diffusion models trained on Lyapunov functions.

problem Generating stabilizing controllers for complex dynamical systems.
method Trains a diffusion model on pairs of asymptotically stable vector fields and their Lyapunov functions to identify the closest stable field and adjust control functions.
result Efficient and rapid stabilization of unseen systems, showcasing generalizability.

Bayesian algorithm stabilizes unknown continuous-time systems from unstable data.

problem Learning and stabilizing unknown continuous-time systems with uncertain dynamics.
method Bayesian learning algorithm that learns from unstable data to stabilize the system in finite time.
result The algorithm stabilizes unknown continuous-time stochastic linear systems effectively after a short time period.

Proposes a stability evaluation criterion for learning models using distributional perturbations.

problem Ensuring reliable deployment of learning models in out-of-sample environments.
method Uses optimal transport discrepancy with moment constraints to quantify minimal perturbation required for model deterioration.
result Validates the practical utility of the stability evaluation criterion across various real-world applications.

Geometric stability measures neural network robustness, distinguishing from similarity metrics.

problem Lack of robustness in neural network representations.
method Introduces geometric stability, quantified by Shesha metric measuring self-consistency.
result Stability and similarity are uncorrelated, revealing distinct properties of neural network robustness.

The paper generalizes K-stability results to singular and weighted settings.

problem Generalizing K-stability to singular and weighted settings.
method Generalization of results in \cite{Li22a} to singular and weighted settings.
result The \(\mathbb{G}\)-uniform weighted K-stability for models implies \(\mathbb{G}\)-coercivity of the weighted Mabuchi functional.

KCRL learns stable policies for nonlinear systems with formal guarantees.

problem Lack of stabilization guarantees in RL methods for safety-critical systems.
method KCRL uses Krasovskii's Lyapunov functions as a stability constraint and a primal-dual approach to learn stabilizing policies.
result KCRL guarantees learning a stabilizing policy in a finite number of interactions.

Inspired by convolutional neural networks on 1D and 2D data, graph convolutional neural networks (GCNNs) have been developed for various learning tasks on graph data, and have shown superior performance on real-world datasets. Despite their success, there is a dearth of theoretical explorations of GCNN models such as t…

2019-05-03abs ↗pdf ↗

GNMR controls runtime stability in low-precision language model training.

problem Efficient low-precision training faces numerical risks at specific operators.
method GNMR compares gradient norms to historical means, applying bounded recovery actions.
result GNMR preserves high-fidelity quality with sparse, budgeted recovery.

The paper develops a convex parameterization for robust RNNs ensuring stability and robustness.

problem Lack of stability and robustness guarantees in RNNs for sequence-to-sequence mapping applications.
method Formulated convex sets of RNNs with stability and robustness guarantees using incremental quadratic constraints.
result The proposed model structure ensures global exponential stability and bounds on incremental 2 \ell_2 gain.

New model stabilizes asynchronous LTI systems, independent of synchronous stability.

problem Stability of asynchronous LTI systems under randomization and asynchrony.
method Introduced a new model for random asynchronous LTI systems and developed a method for system identification.
result Stability of random asynchronous LTI systems is independent of synchronous stability.

The study identifies conditions under which algorithmic stability explains generalization in interpolating learning systems.

problem Understanding when algorithmic stability explains generalization in interpolating learning systems.
method Modeling training as a function-space trajectory and measuring sensitivity to single-sample perturbations.
result There exist interpolating regimes with small risk where contractive sensitivity cannot hold, showing that stability is not a universal explanation.

This work ensures stability in POD basis interpolation for pMOR in hyperelasticity.

problem Stability of POD basis interpolation on Grassmann manifolds for pMOR in hyperelasticity.
method Stability conditions derived from Grassmannian Exponential map and principal angles.
result Explicit stability conditions for practical pMOR applications and non-monotonic error behavior.

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…

2013-01-30abs ↗pdf ↗

Weight decay stabilizes training dynamics by slowing progressive sharpening.

problem Understanding how weight decay affects training stability in deep learning models.
method Analyzing weight decay effects at the Edge of Stability, developing a mathematical framework.
result Weight decay dampens oscillations and stabilizes sharpness in CNNs, causing a phase transition in MLPs.

The paper analyzes stability and generalization of decentralized SGD.

problem Stability and generalization of decentralized stochastic gradient descent.
method Novel formulation of decentralized stochastic gradient descent combined with non/convex optimization theory.
result First stability and generalization guarantees for decentralized stochastic gradient descent.

New stability conditions for ZO methods reveal unique regularization effects.

problem Understanding optimization dynamics of ZO methods in deep learning.
method Explicit step size conditions and stability bounds derived for ZO methods.
result ZO methods operate near the edge of stability, with regularization effects specific to Hessian trace vs. eigenvalue.

Paper addresses LSTM stability for thermal systems using infinity-norm.

problem Stability of LSTM networks in thermal systems.
method Derived ISS_{\infty} condition for LSTM, developed training strategy.
result ISS_{\infty}-promoted LSTM outperforms other models in thermal system case study.

In variable or graph selection problems, finding a right-sized model or controlling the number of false positives is notoriously difficult. Recently, a meta-algorithm called Stability Selection was proposed that can provide reliable finite-sample control of the number of false positives. Its benefits were demonstrated …

2017-12-13abs ↗pdf ↗

Flashback Learning balances model stability and plasticity in continual learning.

problem Balancing model stability and plasticity in continual learning.
method Flashback Learning (FL) uses a bidirectional regularization approach to balance stability and plasticity.
result FL improves model accuracy by up to 4.91% in Class-Incremental and 3.51% in Task-Incremental settings.

Modeling financial systemic risk with optimal control theory for stability.

problem Analyzing and stabilizing systemic risk in interconnected financial entities.
method Developed a theoretical model using optimal control theory, including steps for synthesizing stabilizing controllers.
result The model ensures that the HH^{\infty} norms of the mappings from disturbance to output are less than a predefined constant, stabilizing the system.