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

12.5%25.0%37.5%50.0% · Dec 199319922001200920172026
48 results for universal standardization

New method creates universal perturbations to fool neural network interpretations.

problem Vulnerability of gradient-based saliency maps to adversarial perturbations.
method Gradient-based optimization and PCA-based approach to create UPI.
result Existence and successful application of Universal Perturbation for Interpretation (UPI).

We analyze the constituents stocks of the Dow Jones Industrial Average (DJIA30) and the Standard & Poor's 100 index (S&P100) of the NYSE stock exchange market. Surprisingly, we discover the data collapse of the histograms of the DJIA30 price fluctuations and of the S&P100 price fluctuations to the universal non-paramet…

2008-10-14abs ↗pdf ↗

Unified framework for comparing classification metrics across different imbalance rates.

problem Differences in scale and sensitivity to class imbalance rates in classification metrics.
method Introduces outperformance standardization (OPS) function to map metrics to a common scale.
result Unified o-value metric provides clear comparison across different imbalance rates.

We extend a recently proposed 1-nearest-neighbor based multiclass learning algorithm and prove that our modification is universally strongly Bayes-consistent in all metric spaces admitting any such learner, making it an "optimistically universal" Bayes-consistent learner. This is the first learning algorithm known to e…

2019-06-24abs ↗pdf ↗

This work establishes universality for deep equivariant networks, overcoming limitations of previous approaches.

problem Rarity of universality results for equivariant neural networks, especially in high-dimensional settings.
method Develops a more general account of universality for equivariant networks, introducing entry-wise separability and readout layers.
result Deep equivariant networks achieve universality under entry-wise separability, with or without readout layers.

We show that there exists a transverse link in the standard contact structures on the 3-sphere such that all contact 3-manifolds are contact branched covers over this transverse link.

2017-12-28abs ↗pdf ↗

New findings on universal learning in contextual bandits with adversarial rewards.

problem Learning in contextual bandits with time-varying, adversarial rewards.
method Characterization of learnable processes and necessary/sufficient conditions for universal learning.
result Optimistic universal learning for contextual bandits with adversarial rewards is impossible in general.

Universal supervised learning is considered from an information theoretic point of view following the universal prediction approach, see Merhav and Feder (1998). We consider the standard supervised "batch" learning where prediction is done on a test sample once the entire training data is observed, and the individual s…

2018-12-22abs ↗pdf ↗

Study shows fine-tuned linear models outperform pretrained ones in transfer learning.

problem Transfer learning and fine-tuning in linear models for regression and binary classification.
method Stochastic gradient descent on pretrained linear models with small target data sets.
result Fine-tuned models outperform pretrained ones under certain conditions.

A new learning rule consistently reduces error over data samples.

problem Finding a learning rule that consistently reduces error over all data distributions.
method A deterministic, data-dependent partitioning rule that only partitions cyclic intervals with sufficient empirical diversity of labels.
result The expected error is monotone non-increasing with the sample size under every data distribution.

The Bayesian framework is a well-studied and successful framework for inductive reasoning, which includes hypothesis testing and confirmation, parameter estimation, sequence prediction, classification, and regression. But standard statistical guidelines for choosing the model class and prior are not always available or…

2007-09-11abs ↗pdf ↗

GNP models predictive correlations and outperforms NPs.

problem Training and understanding of Neural Processes.
method Proposed a new model, Gaussian Neural Process (GNP), which incorporates translation equivariance and provides universal approximation guarantees.
result Demonstrates encouraging performance and provides universal approximation guarantees.

Unified analytical tool for non-Markovian jump processes.

problem Analyzing history-dependent jump processes with non-Markovian behavior.
method Developed a standard form of master equations using Laplace-space embedding and asymptotic solution.
result Unified analytical toolset for general non-Markovian processes, leading to the GLE approximation.

We discuss when and why custom multi-factor risk models are warranted and give source code for computing some risk factors. Pension/mutual funds do not require customization but standardization. However, using standardized risk models in quant trading with much shorter holding horizons is suboptimal: 1) longer horizon …

2014-09-09abs ↗pdf ↗

Deep learning models converge to Gaussian dynamics with mixed structured inputs.

problem Understanding neural network dynamics with complex input distributions.
method Extended hidden manifold model to Gaussian mixtures, analyzed via SGD.
result Learning dynamics with mixed inputs converge to Gaussian behavior.

Enhances generative models by improving expressivity without high computational cost.

problem Improving expressivity in generative models without increasing computational complexity.
method Proposes a new family of generative flows on an augmented data space, proving they can approximate a Hamiltonian ODE as a universal transport map.
result Demonstrates state-of-the-art performance on flow-based generative modeling benchmarks.

Persistence diagrams from random matrices follow RMT universality, offering a new spectral diagnostic.

problem Understanding spectral properties of random matrices using topological data analysis.
method Applying Morse theory to persistence diagrams of quadratic forms restricted to unit spheres.
result Persistence entropy outperforms traditional level spacing ratios in discriminating random matrix ensembles.

This paper begins the study of relations between Riemannian geometry and global properties of contact structures on 3-manifolds. In particular we prove an analog of the sphere theorem from Riemannian geometry in the setting of contact geometry. Specifically, if a given three dimensional contact manifold (M,ξ) admits a …

2009-06-18abs ↗pdf ↗

Prototype rules simplify multiclass classification in metric spaces, achieving consistency and reduced complexity.

problem Multiclass classification in metric spaces, focusing on universal consistency and convergence rates.
method Novel Proto-NN and hybrid rules for multiclass classification in metric spaces, analyzing convergence rates.
result Proto-NN is universally consistent and simpler to implement, with similar computational advantages.

The study proves CR structures on specific three-manifolds are equivalent to standard structures.

problem Proving CR structures on three-manifolds are equivalent to standard structures.
method Analyzing Yamabe constant and total QQ^\prime-curvature to deduce CR equivalence.
result Closed CR three-manifolds with certain curvature properties are equivalent to standard structures.

Study on contact forms with constant curvature on CR manifolds.

problem Existence of non-homothetic contact forms with constant Tanaka-Webster scalar curvature.
method Analysis of universal covers and profinite completions of CR manifolds.
result Existence of infinitely many non-homothetic contact forms on compact CR manifolds.

The universe's shape and size are determined in general cosmological models.

problem Determining the shape and size of the universe in general cosmological models.
method Using differential geometry and extensions of the Bonnet-Myers theorem, the researchers derived conditions for a finite universe and provided a list of possible topologies.
result The spatial sections of the universe can be either S1imesS2S^1 imes S^2, S1ildeimesS2S^1 ilde{ imes}S^2, S1imesRP2S^1 imes\mathbb{RP}^2, RP3#RP3\mathbb{RP}^3 \# \mathbb{RP}^3, or covered by the sphere S3S^3 or torus T3T^3.

Constructs new topological theories in 2D not fitting standard axioms.

problem Developing new topological theories in 2D that don't conform to traditional axioms.
method Universal construction by Blanchet et al., Kronecker's characterization, field extension, Hankel matrices, Schur polynomials, and foam evaluation.
result Introduction of non-multiplicative theories and classification over finite-dimensional state spaces.

We study noncompact surfaces evolving by mean curvature flow. Without any symmetry assumptions, we prove that any solution that is C3C^3-close at some time to a standard neck will develop a neckpinch singularity in finite time, will become asymptotically rotationally symmetric in a space-time neighborhood of its singul…

2013-08-26abs ↗pdf ↗

The paper critiques UBI as ineffective for addressing technological unemployment.

problem Technological unemployment due to automation.
method Empirical data analysis and theoretical projections of UBI's impact.
result UBI is not an effective solution for improving living standards and employability among displaced workers.

We give necessary and sufficient conditions for a closed connected co-orientable contact 33-manifold (M,ξ)(M,ξ) to be a standard lens space based on assumptions on the Reeb flow associated to a defining contact form. Our methods also provide rational global surfaces of section for nondegenerate Reeb flows on $(L(p,q),ξ_{…

2013-06-27abs ↗pdf ↗

We prove the existence of a degree 7 Vassiliev invariant of long (or string) two-component links which is not preserved under the simultaneous change of orientation of both components. The non-invertibility of this invariant can be detected by the standard weight system with values in the tensor square of the universal…

2005-07-01abs ↗pdf ↗

PieClam autoencodes graphs into communities, improving graph anomaly detection.

problem Graph anomaly detection and universal graph autoencoding.
method Probabilistic graph model with overlapping inclusive and exclusive communities.
result PieClam is a universal autoencoder that uniformly approximates any graph.

Analyzes the differential expansion of knot polynomials, focusing on its applicability and modifications.

problem Understanding the differential expansion of colored knot polynomials, especially for non-trivial knots and those with defects.
method Examines the current status of differential expansion, analyzes its applicability to non-trivial knots, and introduces a new transformation.
result A new transformation VV that converts Z\cal{Z} to standard ZZ-factors and allows for the calculation of FF.

ULFS-KDPE estimates parameters efficiently without influence functions.

problem Estimating pathwise differentiable parameters in nonparametric models.
method Kernel debiased plug-in estimator based on universal least favorable submodel.
result Semiparametric efficiency achieved without influence function derivation.