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

19385776 · Jun 202619922001200920172026
48 results for Multiple-descent curve

Improved guarantees and multiple-descent curve for data approximations.

problem Improving the effectiveness of small low-rank approximations of large datasets.
method Spectral properties of the data matrix to obtain improved approximation guarantees.
result Revealed a multiple-descent curve in approximation factor as a function of k.

Unified analysis of generalization curves in large models using gradient flow.

problem Analyzing generalization error curves in simple learning models.
method Gradient flow in the Gaussian covariate model, using random matrix theory.
result Unified understanding of multiple descent structures in learning curves.

The paper studies multiple descent in multi-component prediction models.

problem Understanding the risk curves in multi-component prediction models.
method Investigates a 'double random feature model' and 'multiple random feature model' in ridge regression.
result Risk curves of multi-component prediction models can exhibit multiple descents.

The paper shows how the generalization curve can have multiple peaks, influenced by data and learning algorithm biases.

problem Understanding the generalization behavior of linear regression models under varying parameterizations.
method Analyzes generalization loss in linear regression models with varying parameterizations, both under- and over-parameterized.
result The generalization curve can have an arbitrary number of peaks, and their locations can be controlled.

The paper extends kernel ridge regression to product kernels and reveals new convergence behaviors.

problem Understanding kernel ridge regression in large dimensions with various kernels.
method Established a broad family of large dimensional kernels and derived convergence rates.
result Revealed new phenomena including minimax optimality, saturation effect, and multiple descent behavior.

Study shows double and triple descent in unsupervised autoencoders, improving performance in various tasks.

problem Exploring the phenomenon of double descent in unsupervised learning.
method Analytical demonstration and extensive experiments on synthetic and real datasets.
result Over-parameterized unsupervised autoencoders exhibit double and triple descent, enhancing performance in downstream tasks.

We analyze kernel matrices in polynomial high-dimensional settings and explain double descent in KRR.

problem Understanding the spectrum of kernel matrices in polynomial high-dimensional settings and its implications for KRR risk.
method Generalized decomposition of kernel matrices into low-rank spike matrix, identity, and Gegenbauer matrix.
result The test error in KRR can exhibit double descent behavior, depending on effective regularization and signal-to-noise ratio.

Framework mitigates risk non-monotonicity in high-dimensional predictions.

problem Risk non-monotonicity in high-dimensional predictions.
method Model-agnostic framework using cross-validation and data-driven methodologies (zero- and one-step).
result Modified prediction procedures achieve monotonic asymptotic risk behavior.

Study on optimal rate of kernel regression for large-dimensional data.

problem Characterizing the upper and lower bounds of kernel regression for large-dimensional data.
method Using Mendelson complexity and metric entropy, the study characterizes the upper and lower bounds of kernel regression for large-dimensional data.
result The minimax rate of the excess risk of kernel regression is \( n^{-1/2} \) for \( n \asymp d^γ \) with \( γ=2, 4, 6, 8, \cdots \).

New approach quantifies overfitting in high-dimensional regression.

problem Quantifying and avoiding overfitting in large neural networks.
method Information bottleneck theory to minimize residual information while maximizing relevant bits.
result Characterized the relative information efficiency of randomized regression compared to optimal algorithms.

The paper analyzes bagging in overparameterized learning, deriving risk properties and optimal subsample sizes.

problem Characterizing the risk of bagged predictors in overparameterized settings.
method General strategy using classical results on simple random sampling, specialized for ridge and ridgeless predictors.
result Derives exact asymptotic risk of bagged ridge and ridgeless predictors under various conditions.

TKRR improves KRR performance by aligning target functions with kernels.

problem Improving kernel ridge regression performance through target alignment.
method Focuses on truncated kernel ridge regression (TKRR) with an additional spectral truncation parameter.
result TKRR can achieve faster rates than full KRR, reaching parametric rates.

The paper studies the minimum ℓ₁-norm interpolator's risk behavior in over-parameterized settings.

problem Understanding the risk behavior of minimum ℓ₁-norm interpolators in high-dimensional settings.
method Exact characterization of the risk behavior through a system of two non-linear equations.
result Observation of a multi-descent phenomenon in the generalization risk of the minimum ℓ₁-norm interpolator.

A new decomposition explains over-parameterized models' counterintuitive behaviors.

problem Understanding predictive error in over-parameterized models.
method Introducing the Generalized Aliasing Decomposition (GAD) to explain predictive performance.
result The GAD decomposes predictive error into three parts: model insufficiency, data insufficiency, and generalized aliasing.

This study reveals fundamental trade-offs between memorization and robustness in neural networks.

problem Understanding the balance between memorization and robustness in neural networks.
method Analyzes two-layer neural networks in various high-dimensional linearized regimes, focusing on Sobolev-seminorm.
result Establishes fundamental trade-offs between memorization and robustness, with lower bounds on Sobolev-seminorm.

The study explores Bertrand and Mannheim curves in 4D Euclidean space for framed curves.

problem Exploring Bertrand and Mannheim curves in 4D Euclidean space for framed curves.
method Defining and investigating Bertrand and Mannheim curves of framed curves in 4D Euclidean space.
result Bertrand and Mannheim curves exist even for framed curves in 4D Euclidean space, contrary to regular curves.

The study examines Bertrand Legendre curves in the unit tangent bundle over Euclidean plane.

problem Investigating properties of Legendre curves and their associated curves.
method Analyzing Bertrand Legendre curves and their associated curves, including parallel, evolute, and involute curves.
result Existence conditions and inverse operation for Bertrand Legendre curves are provided.

In this study, we introduce a new approach to curve pairs by using integral curves. We consider the direction curve and donor curve to study curve couples such as involute-evolute curves, Mannheim partner curves and Bertrand partner curves. We obtain new methods to construct partner curves of a unit speed curve and giv…

2017-01-09abs ↗pdf ↗

The paper characterizes curves in pseudo-Galilean 4-space.

problem Characterizing curves in the pseudo-Galilean 4-space G14G_{1}^{4}.
method Investigation and characterisation of admissible curves in terms of curvature functions.
result Necessary and sufficient conditions for admissible rectifying curves in G14G_{1}^{4}.

In this paper, we introduce a new approach to non-lightlike curve pairs by using integral curves in Minkowski 3-space. We consider direction curve and donor curve to study non-lightlike curve couples such as involute-evolute curves, Mannheim partner curves and Bertrand partner curves. We obtain new methods to construct…

2017-03-28abs ↗pdf ↗

The paper examines how closed curves on surfaces intersect and how this intersection determines the curves.

problem Determining closed curves on surfaces based on their intersections.
method Constructing and studying kk-equivalent curves, analyzing intersections with other curves.
result Curves are determined by their intersections with all other curves, but non-simple curves require infinitely many intersections to distinguish.

Flow deforms locally convex curves to curves of constant k-order width.

problem Evolve locally convex curves to curves of constant k-order width.
method Introduced a nonlocal curvature flow to evolve locally convex curves in the plane.
result The flow converges to a smooth, locally convex curve of constant k-order width as time goes to infinity.

Study on CR curves in 3-sphere, focusing on critical curves integration and existence.

problem Addressing the integration and existence of critical curves in the CR 3-sphere.
method Provided a procedure for the explicit integration of general critical curves and characterized closed curves.
result Existence of infinite countably many closed critical curves.

Unified description of aesthetic curves through self-affinities.

problem Characterizing log-aesthetic curves and their properties.
method Reformulating and proving self-affinities of planar curves, integrating equiaffine geometry.
result Unified characterization of constant curvature curves in similarity and equiaffine geometries.

Study on Bertrand lightcone framed curves in Lorentz-Minkowski 3-space.

problem Analyzing mixed types of curves with singular points in Lorentz-Minkowski 3-space.
method Using lightcone frame to consider Bertrand types for lightcone framed curves.
result Existence conditions of Bertrand lightcone framed curves in all cases.

In this study, we introduce a new type of surface curves called D-type curve. This curve is defined by the property that the unit Darboux vector W0 of a space curve r(s) and unit surface normal n along the curve r(s) satisfy the condition <n,W0>=constant. We point out that a D-type curve is a geodesic curve or an asymp…

2016-02-26abs ↗pdf ↗

Study on triharmonic curves in f-Kenmotsu manifolds.

problem Characterizing triharmonic curves in f-Kenmotsu manifolds.
method Investigation of necessary and sufficient conditions for Frenet curves, slant, and Legendre curves to be triharmonic. Proof of specific properties of triharmonic Frenet curves.
result Triharmonic Frenet curves with constant curvature are Frenet helices in three dimensional f-Kenmotsu manifolds.

The paper generalizes rectifying and normal curves in Lorentzian n-space.

problem Characterizing and classifying gg-rectifying and gg-normal curves in Lorentzian n-space.
method Introducing a gg-position vector field and defining gg-rectifying and gg-normal curves based on this field.
result Comprehensive characterization and classification of gg-rectifying and gg-normal curves.

New findings on hyperbolicity of fine curve graphs and their subgraphs.

problem Investigating hyperbolicity of fine curve graphs and their subgraphs.
method Analyzing large subgraphs of fine curve graphs and computing distances in specific cases.
result Large subgraphs of fine curve graphs contain flats of every finite dimension, indicating they are not hyperbolic.

In this paper we study null Bertrand curves in R14R_{1}^{4} under the assumption the curve has a Cartan frame. We show that if the derivative vectors of the null Cartan curve in R14R_{1}^{4} is linearly independent, then this curve is not a Bertrand curve. Since then the already known notion of null Bertrand curves in $R…

2011-01-31abs ↗pdf ↗

In this study, we define a new type of direction curves in the Euclidean 3-space such as osculating-direction curve. We give the characterizations for these curves. Moreover, we obtain the relationships between osculating direction curves and some special curves such as helix, slant helix or rectifying curves.

2015-02-16abs ↗pdf ↗

We classify curves in the moduli space of curves that are both Shimura- and Teichmueller curves: Except for the moduli space of genus one curves there is only a single such curve. We start with a Hodge-theoretic description of Shimura curves and of Teichmueller curves that reveals similarities and differences of the tw…

2005-01-20abs ↗pdf ↗

In this paper we consider the idea of Bertrand curves for curves lying on surfaces and by considering the Darboux frames of them we define these curves as Bertrand D-curves and give the characterizations for these curves. We also find the relations between the geodesic curvatures, the normal curvatures and the geodesic…

2010-03-10abs ↗pdf ↗

The paper studies a curve flow preserving anisotropic length for convex curves, leading to a homothetic limit.

problem Anisotropic length preservation in curve deformation.
method A curve flow that maintains anisotropic length, analyzed for convex closed curves.
result Convex curves evolve to homothetic limits of Wulff shapes as time approaches infinity.

We study pairs of curves with Poncelet's porism properties and compute their vertex curves.

problem Understanding pairs of curves with Poncelet's porism properties.
method Developed formulas to compute vertex curves for given envelope curves and vice versa, for all sufficiently regular pairs of Poncelet curves.
result Formulas produce all possible sufficiently regular pairs of Poncelet curves, including sets of curves analogous to pencils of conic sections.