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.

168,742 papers · 148 categories

Trend · papers per month

17345067 · Jun 202619922001200920172026
48 results for Non-degenerate Dual Certificates

Paper estimates GMMs with unknown covariances using sparse regularization.

problem Estimating GMMs with unknown diagonal covariances from samples.
method Employed Beurling-LASSO (BLASSO) for sparse estimation of component means, covariances, and weights.
result Established non-asymptotic recovery guarantees with nearly parametric convergence rates.

New proof shows certain 4D metrics are non-degenerate if curvature is negative definite.

problem Proving non-degeneracy of Poincaré-Einstein metrics.
method Proved non-degeneracy for 4D metrics satisfying a chiral curvature inequality.
result 4D Poincaré-Einstein metrics are non-degenerate if curvature is negative definite.

In this paper, the following three are shown. (1) For a CC^\infty convex integrand γ:SnR+γ: S^n\to \mathbb{R}_+, its dual convex integrand δ:SnR+δ: S^n\to \mathbb{R}_+ is of class CC^\infty. (2) For a stable convex integrand γ:SnR+γ: S^n\to \mathbb{R}_+, its dual convex integrand δ:SnR+δ: S^n\to \mathbb{R}_+ is stable. (3) Let $γ: S…

2016-03-28abs ↗pdf ↗

Algorithm for exact partitioning of high-order models using convex tensor relaxation.

problem Exact partitioning of high-order models.
method Defining a general class of mm-degree Homogeneous Polynomial Models, relaxing the high-order combinatorial problem to a convex conic form problem, defining the Carathéodory symmetric tensor cone, and constructing a primal-dual certificate.
result The solution of the convex relaxation is correct and provides a statistical upper bound for exact partitioning.

Given a convex optimization problem and its dual, there are many possible first-order algorithms. In this paper, we show the equivalence between mirror descent algorithms and algorithms generalizing the conditional gradient method. This is done through convex duality, and implies notably that for certain problems, such…

2012-11-27abs ↗pdf ↗

In this paper, we investigate simultaneous properties of a convex integrand γγ and its dual δδ. The main results are the following three. (1) For a CC^\infty convex integrand γ:SnR+γ: S^n\to \mathbb{R}_+, its dual convex integrand δ:SnR+δ: S^n\to \mathbb{R}_+ is of class CC^\infty if and only if γγ is a strictly convex in…

2017-07-06abs ↗pdf ↗

This paper investigates the statistical estimation of a discrete mixing measure μμ0 involved in a kernel mixture model. Using some recent advances in l1-regularization over the space of measures, we introduce a "data fitting and regularization" convex program for estimating μμ0 in a grid-less manner from a sample of …

2019-07-23abs ↗pdf ↗

Classifies Heisenberg-invariant self-dual Einstein manifolds with explicit metrics.

problem Classifying self-dual Einstein manifolds invariant under Heisenberg group actions.
method Explicit construction of metrics and analysis of completeness.
result Einstein constants can vary and solutions exist for non-zero Ricci curvature.

There exist non-degenerate 3-form dωIdω_I, ωI(X,Y)=g(IX,Y)ω_I(X,Y)=g(IX,Y), for each leftinvariant almost Hermitian structure (g,I)(g,I), where gg is Killing-Cartan metric on the M=S3×S3=SU(2)×SU(2)M=S^3\times S^3=SU(2)\times SU(2). Known \cite{H1}, that arbitrary non-degenerate 3-form on the 6-dimensional manifold, with some additional properties def…

2010-01-18abs ↗pdf ↗

The aim of this work is to study the foliations on the complex projective plane with flat \textsc{Legendre} transform (dual web). We establish some effective criteria for the flatness of the dual dd-web of a homogeneous foliation of degree dd and we describe some explicit examples. These results allow us to show that…

2016-07-04abs ↗pdf ↗

This paper certifies cluster assignments from sum-of-norms clustering algorithms.

problem Certifying the correct cluster assignments from approximate solutions of sum-of-norms clustering.
method Presented a clustering test that identifies and certifies the correct cluster assignment from an approximate solution.
result The correct cluster assignment is guaranteed to be certified by a primal-dual path following algorithm after sufficient iterations.

New algorithms learn stability certificates from data, avoiding complex dynamics.

problem Synthesizing stability certificates from complex dynamical systems.
method Developed algorithms to learn certificate functions from trajectory data, establishing generalization error bounds.
result Efficiently learned certificates can be used for adaptive control.

Improved neural network robustness certification through tighter convex relaxations.

problem Certifying neural network robustness to perturbed and adversarial inputs.
method Exploiting ReLU network structure, novel partition-based certification procedure.
result Tightens existing linear programming relaxations to achieve zero relaxation error asymptotically.

The study classifies homogeneous Sasaki manifolds over quaternionic Kähler spaces.

problem Classifying homogeneous Sasaki manifolds over quaternionic Kähler spaces.
method Locally defined Riemannian submersions and homogeneous space constructions.
result Complete classification of homogeneous Sasaki manifolds in the non-degenerate case.

New method closes certification gap for adversarially trained models.

problem Certifying robustness of adversarially trained neural networks.
method Nonconvex low-rank SDP relaxation with polynomial-time optimization.
result Strong certifications comparable to SDP methods, but with fewer variables.

Generalized Linear Models (GLM) form a wide class of regression and classification models, where prediction is a function of a linear combination of the input variables. For statistical inference in high dimension, sparsity inducing regularizations have proven to be useful while offering statistical guarantees. However…

2019-07-12abs ↗pdf ↗

While neural networks have achieved high performance in different learning tasks, their accuracy drops significantly in the presence of small adversarial perturbations to inputs. Defenses based on regularization and adversarial training are often followed by new attacks to defeat them. In this paper, we propose attack-…

2019-02-01abs ↗pdf ↗

This paper focuses on a topological version on the Strominger-Yau-Zaslow mirror symmetry conjecture. Roughly put, the SYZ conjecture suggests that mirror pairs of Calabi-Yau manifolds are related by the existence of dual special Lagrangian torus fibrations. We explore this conjecture without reference to the special La…

1999-09-02abs ↗pdf ↗

New framework improves adversarial robustness certification for various perturbations.

problem Certifying robustness against adversarial attacks in deep learning models.
method Unified functional optimization approach with non-Gaussian smoothing noise for multiple types of attacks.
result Achieves better certification results and identifies key trade-offs between accuracy and robustness.

Bayesian method synthesizes barrier certificates for unknown systems with latent states.

problem Certifying safety in systems with unknown dynamics and latent states.
method Bayesian inference with Metropolis-Hastings sampler and sum-of-squares program.
result Probabilistic validity of barrier certificates for unknown systems.

CITE algorithm provides anytime-valid certification of model outputs.

problem Challenges in controlling error levels in LLM self-consistency.
method Certification by Intersection-union Testing with E-processes (CITE) algorithm.
result Provable control of false certification at any prescribed level under arbitrary stopping rules.

Paper develops tighter risk certificates for contrastive learning models.

problem Statistical theory for contrastive learning is lacking, especially for practical models like SimCLR.
method Develops non-vacuous PAC-Bayesian risk certificates considering practical SimCLR factors.
result Risk certificates for contrastive loss and downstream prediction are much tighter than previous results.

The performance of a reinforcement learning algorithm can vary drastically during learning because of exploration. Existing algorithms provide little information about the quality of their current policy before executing it, and thus have limited use in high-stakes applications like healthcare. We address this lack of …

2018-11-07abs ↗pdf ↗

New method provides tighter robustness guarantees for adversarial attacks.

problem Ensuring robustness against adversarial attacks in machine learning models.
method Developed a Second-order Smoothing (SoS) robustness certificate using Gaussian random smoothing.
result SoS certificates are tighter and provide improved robustness on high-dimensional datasets.

This paper studies the geometry of immersions into statistical manifolds. A necessary and sufficient condition is obtained for statistical manifold structures to be dual to each other for a non-degenerate equiaffine immersion. Then we obtain conditions for realizing an n-dimensional statistical manifold in an (n+1)-dim…

2018-03-07abs ↗pdf ↗

Method solves nonconvex constrained optimization problems with a new augmented Lagrangian approach.

problem Nonconvex composite functional constraints with inequality constraints.
method First-order augmented Lagrangian method with smoothed prox-linear reformulation.
result Explicit convergence rates for the proposed method in terms of KKT residual.

TUV Austria proposes certification for ML applications to ensure reliability.

problem Ensuring trust in AI applications to meet societal reliance requirements.
method Holistic approach analyzing security, functionality, data quality, ethics, and criticality levels.
result Certification process for low-risk ML applications in supervised learning.

When Daan Krammer and Stephen Bigelow independently proved that braid groups are linear, they used the Lawrence-Krammer-Bigelow representation for generic values of its variables q and t. The t variable is closely connected to the traditional Garside structure of the braid group and plays a major role in Krammer's alge…

2014-11-04abs ↗pdf ↗

Paper provides efficient robustness certificates for neural networks.

problem Ensuring neural networks are robust against adversarial attacks.
method Two-step approach: 1) Efficient convex optimization for robustness certificates with bounded Hessian eigenvalues, 2) Curvature-based regularization during training.
result Significantly higher certified robust accuracy achieved compared to existing methods.

New robustness certificates for streaming models with a sliding window.

problem Applying robustness certificates to streaming data with correlated inputs.
method Deriving robustness certificates for models using a sliding window over a sequence of potentially correlated inputs.
result Guarantees hold for the average model performance across the entire stream, independent of stream size.

The paper improves risk certificate tightness for neural networks using PAC-Bayes bounds.

problem Improving the usability of risk certificates for neural networks based on PAC-Bayes bounds.
method Theoretical contributions including KL divergence bounds, efficient methodology for optimization, and methods for optimizing non-differentiable objectives.
result First non-vacuous generalization bounds on CIFAR-10 for neural networks.

Study adversarial perturbations in classification, analyzing learning and certification.

problem Formal study of classification under adversarial perturbations from both learner and third-party perspectives.
method PAC-type semi-supervised learning framework, black-box certification under limited query budget, adversary analysis.
result Existence of a polynomial query complexity adversary implies the existence of a sample efficient robust learner.

New method improves robustness of smoothed classifiers against adversarial attacks.

problem Improving robustness of smoothed classifiers against adversarial attacks.
method Proposes worst-case adversarial loss over input distributions as a robustness certificate, and uses duality and smoothness properties to provide an easy-to-compute upper bound.
result Shows superior robustness performance over state-of-the-art certified or heuristic methods.

SREC markets are a relatively novel market-based system to incentivize the production of energy from solar means. A regulator imposes a floor on the amount of energy each regulated firm must generate from solar power in a given period and provides them with certificates for each generated MWh. Firms offset these certif…

2019-04-12abs ↗pdf ↗