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.

169,341 papers · 148 categories

Trend · papers per month

117234351468 · Jun 202019922001200920182026
48 results for viewpoint analysis

ViewFool identifies adversarial viewpoints to test image recognition robustness.

problem Lack of robustness to viewpoint changes in visual recognition models.
method Neural Radiance Fields (NeRF) and entropic regularizer to find adversarial viewpoints.
result Common image classifiers are highly vulnerable to generated adversarial viewpoints.

Improves deep neural network training and accuracy with adaptive basis approach.

problem Gap between theoretical and practical performance of deep neural networks.
method Adaptive basis viewpoint, novel initializations, hybrid optimizer.
result Dramatic increases in accuracy and convergence rate for various DNN applications.

Efficient algorithm for clustering and classification using MBO scheme.

problem Data clustering and classification tasks.
method Introduces constraints on cluster size leading to a linear integer problem, proving it's induced by a novel order statistic. Develops exact and efficient algorithms based on variational viewpoint connecting to volume-preserving mean curvature flow.
result Estimates computational complexity better than state-of-the-art, proving rigorous analysis.

The paper studies groupoid structures from different viewpoints.

problem Understanding groupoid morphisms and their structures.
method Constructing two groupoids from morphisms of groupoids, one from a categorical viewpoint and the other from a geometric viewpoint. Showing equivalence of the two kinds of groupoids of morphisms.
result Equivalence of two kinds of groupoids of morphisms for each pair of groupoids.

The paper sets limits for sequential prediction and recursive algorithms using entropy analysis.

problem Fundamental limitations in sequential prediction and recursive algorithms.
method Entropic analysis to investigate underlying relationships of data and noises.
result Derives Lp\mathcal{L}_{p} bounds quantifiable in conditional entropy.

Survey on geometric properties of special minimal surfaces.

problem Understanding [φ,e3][\varphi,\vec{e}_{3}]-minimal surfaces in R3\mathbb{R}^{3}.
method Systematic geometric study of [φ,e3][\varphi,\vec{e}_{3}]-minimal surfaces.
result Fundamental results in the theory of [φ,e3][\varphi,\vec{e}_{3}]-minimal surfaces.

Addresses theoretical and practical aspects of Gaussian differential privacy.

problem Theoretical and practical challenges in privacy-preserving data analysis.
method Discussion of f-differential privacy and Gaussian differential privacy.
result Gaussian differential privacy can enhance privacy in various applications.

We report a statistical analysis of the Island ECN (NASDAQ) order book. We determine the static and dynamic properties of this system, and then analyze them from a physicist's viewpoint using an equivalent particle system obtained by treating orders as massive particles and price as position. We identify the fundamenta…

2001-06-06abs ↗pdf ↗

Paper studies the theoretical equivalence between implicit and explicit neural networks in high dimensions.

problem Lack of theoretical analysis of implicit and explicit neural networks.
method Examined high-dimensional implicit neural networks and established their equivalence to explicit networks.
result Equivalence between implicit and explicit neural networks in high dimensions.

Multi-class classification methods based on both labeled and unlabeled functional data sets are discussed. We present a semi-supervised logistic model for classification in the context of functional data analysis. Unknown parameters in our proposed model are estimated by regularization with the help of EM algorithm. A …

2011-02-22abs ↗pdf ↗

We study the problem of supervised linear dimensionality reduction, taking an information-theoretic viewpoint. The linear projection matrix is designed by maximizing the mutual information between the projected signal and the class label (based on a Shannon entropy measure). By harnessing a recent theoretical result on…

2012-06-27abs ↗pdf ↗

Improved data analysis with robust SPCA algorithm.

problem Identifying localized spatial structures and disambiguating time scales in low-rank data.
method Formulated as a value-function optimization problem, then extended with randomized linear algebra methods for scalability.
result Robust and efficient sparse principal components in corrupted data.

Robustly estimates posterior with adversarial outliers using Rob-ULA.

problem Estimating posterior distribution in the presence of adversarial outliers.
method Proposes Rob-ULA, a robust variant of ULA, and provides finite-sample analysis.
result Sampling from pTp_T with extdist(pT,p)εextsfacc+ildeO(ε) ext{dist}(p_T, p^*) \leq \varepsilon_{ extsf{acc}} + ilde{\mathcal{O}}(ε) after T=ildeO(d/εextsfacc)T= ilde{\mathcal{O}}(d/\varepsilon_{ extsf{acc}}) iterations.

We present a probabilistic viewpoint to multiple kernel learning unifying well-known regularised risk approaches and recent advances in approximate Bayesian inference relaxations. The framework proposes a general objective function suitable for regression, robust regression and classification that is lower bound of the…

2011-03-04abs ↗pdf ↗

Unified analysis of EG and OGDA for saddle point problems using proximal point method.

problem Solving saddle point problems in bilinear and strongly convex-strongly concave settings.
method Unified analysis as approximations of the proximal point method.
result Unified analysis of EG and OGDA for saddle point problems.

Adaptive optimization methods bias neural network trajectories towards regions of lower local geometry.

problem The success of adaptive optimization methods in neural networks is not fully explained by traditional second-order methods.
method Local trajectory analysis and introduction of a new statistic RextmedextOPTR^{ ext{OPT}}_{ ext{med}}.
result Adaptive methods like Adam bias trajectories towards regions of lower local geometry, leading to faster convergence.

This paper improves SGMs by using a predictor-corrector scheme to converge faster.

problem Theoretical and practical limitations of existing SGMs when T1oT_1 o \infty.
method Integrates a predictor-corrector scheme after the forward process to converge in finite time.
result Convergence guarantees for SGMs require only a fixed finite time T1T_1.

This paper tackles catastrophic forgetting in neural networks by providing a unified framework for regularization-based continual learning.

problem Catastrophic forgetting in neural networks trained sequentially on multiple tasks.
method Formulates regularization-based continual learning as a second-order Taylor approximation of the loss function, leading to a unified framework.
result Theoretical results indicate the importance of accurate approximation of the Hessian matrix for optimization and generalization.

This paper is devoted to the development and applications of some (new) basic concepts in Lie theory, both from `computational" and "observability" viewpoint. We specify set of all "G-equivariant" maps from a given Lie group G to the underlying manifold M, namely GG-set, and also we introduce "conjugacy" in Lie group …

2012-01-18abs ↗pdf ↗

The Piyavskii-Shubert algorithm is analyzed for global optimization of Lipschitz functions.

problem Maximizing a non-concave Lipschitz function over a compact domain.
method Sequential function evaluations using a bandit-optimization approach.
result New bounds on the number of evaluations needed for optimization accuracy.

Unified framework for imitating tasks across domains with discrepancies.

problem Learning tasks across domains with embodiment, viewpoint, and dynamics mismatches.
method Two-step approach: alignment followed by adaptation. Alignment uses Generative Adversarial MDP Alignment (GAMA) for state and action correspondences from unpaired, unaligned demonstrations. Adaptation leverages these correspondences for zero-shot imitation.
result Effectiveness of the proposed approach in embodiment, viewpoint, and dynamics mismatch scenarios.

Proposes KMvDA for object recognition from multi-view data.

problem Recognizing objects from different views, even when views are heterogeneous.
method Introduces kernel multi-view discriminant analysis (KMvDA) and uses random Fourier features (RFF) for large-scale learning.
result KMvDA and RFF approximation improve object recognition from multi-view data.

We consider a triality between the Zermelo navigation problem, the geodesic flow on a Finslerian geometry of Randers type, and spacetimes in one dimension higher admitting a timelike conformal Killing vector field. From the latter viewpoint, the data of the Zermelo problem are encoded in a (conformally) Painleve-Gullst…

2008-11-18abs ↗pdf ↗

The paper tackles hierarchical clustering with structural constraints, providing approximation guarantees and improving upon current techniques.

problem Exploiting prior information in hierarchical clustering for real-world applications.
method Top-down algorithms with provable approximation guarantees, using optimization viewpoint and constraint-based regularization.
result Improved solutions for hierarchical clustering with conflicting prior information.

A conceptual framework for cluster analysis from the viewpoint of p-adic geometry is introduced by describing the space of all dendrograms for n datapoints and relating it to the moduli space of p-adic Riemannian spheres with punctures using a method recently applied by Murtagh (2004b). This method embeds a dendrogram …

2007-07-27abs ↗pdf ↗

Paper explores why overfitted DNNs in adversarial training can generalize.

problem Understanding why overfitted DNNs in adversarial training can generalize despite poor robust generalization.
method An approximation viewpoint to analyze the robust overfitting of over-parameterized DNNs.
result Existence of infinitely many overfitted DNNs that achieve good robust generalization under certain conditions.

In 1929, Paul Funk and Ludwig Berwald gave a characterization of Hilbert geometries from the Finslerian viewpoint. They showed that a smooth Finsler metric in a convex bounded domain of Rn\mathbb{R}^n is the Hilbert geometry in that domain if and only if it is complete, if its geodesics are straight lines and if its fl…

2013-11-11abs ↗pdf ↗

Stacked Capsule Autoencoders reconstruct objects from images using part relationships.

problem Reconstructing objects from images with robustness to viewpoint changes.
method Two-stage unsupervised capsule autoencoder that predicts part templates and object capsules.
result State-of-the-art results for unsupervised classification on SVHN and MNIST.

Discrete Morse functions induce shellings with critical tiles corresponding to function's critical faces.

problem Mapping discrete Morse functions to shellings for topological analysis.
method Inducing Morse shellings on the second barycentric subdivision of a simplicial complex.
result Critical tiles of induced shellings correspond to critical faces of the discrete Morse function.

The purpose of this article is to present the theory of higher order connections on vector bundles from a viewpoint inspired by projective differential geometry.

2009-08-11abs ↗pdf ↗