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

4896144192 · May 202619922001200920172026
48 results for Hölder Smoothness

Adversarial online nonparametric regression achieves optimal rates with locally adaptive learning.

problem Adversarial online nonparametric regression with general convex losses.
method Parameter-free learning algorithm leveraging chaining trees to compete against H{ö}lder functions, dynamically tracking and adapting to local smoothness variations.
result First computationally efficient algorithm with locally adaptive optimal rates for online regression in an adversarial setting.

In the context of stochastic continuum-armed bandits, we present an algorithm that adapts to the unknown smoothness of the objective function. We exhibit and compute a polynomial cost of adaptation to the H{ö}lder regularity for regret minimization. To do this, we first reconsider the recent lower bound of Locatelli an…

2019-05-24abs ↗pdf ↗

Efficient algorithms for contextual bandits with smooth regret in continuous action spaces.

problem Efficient learning in large or continuous action spaces.
method Smooth regret notion and efficient algorithms for general function approximation.
result Statistically and computationally efficient algorithms for contextual bandits with smooth regret.

We find a local solution to the Ricci flow equation under a negative lower bound for many known curvature conditions. The flow exists for a uniform amount of time, during which the curvature stays bounded below by a controllable negative number. The curvature conditions we consider include 2-non-negative and weakly $\t…

2018-04-22abs ↗pdf ↗

Study shows zero-shot super-resolution in neural operators is impossible in many cases.

problem Understanding the theoretical limits of zero-shot super-resolution in neural operators.
method Systematic theoretical study including information-theoretic and generalization bounds analysis.
result Zero-shot super-resolution is information-theoretically impossible in many settings.

This paper selects features in deep neural networks with theoretical guarantees.

problem Feature selection in deep neural networks with unknown nonlinear functions.
method Reformulate neural networks as index models, estimate feature sets using Stein's formula, and apply screening-and-selection mechanism.
result Consistent feature selection with theoretical guarantees, even in high-dimensional settings.

We study finite energy classes of quasiplurisubharmonic (qpsh) functions in the setting of toric compact K{ä}hler manifolds. We characterize toric qpsh functions and give necessary and sufficient conditions for them to have finite (weighted) energy, both in terms of the associated convex function in R n , and through t…

2018-04-10abs ↗pdf ↗

Let SS be a closed oriented surface of genus at least 22, and denote by T(S)\mathcal{T}(S) its Teichm{ü}ller space. For any isotopy class of closed curves γγ, we compute the first three derivatives of the length function _γ:T(S)R_+\ell\_γ:\mathcal{T}(S)\rightarrow\mathbf{R}\_+ in the shearing coordinates associated to a maxim…

2015-06-22abs ↗pdf ↗

We consider the problem of online nonparametric regression with arbitrary deterministic sequences. Using ideas from the chaining technique, we design an algorithm that achieves a Dudley-type regret bound similar to the one obtained in a non-constructive fashion by Rakhlin and Sridharan (2014). Our regret bound is expre…

2015-02-26abs ↗pdf ↗

Validates economic scenarios using statistical tests on stochastic processes.

problem Ensuring the accuracy of real-world economic scenario models.
method Applies Chevyrev and Oberhauser's (2022) signature and maximum mean distance test to various stochastic processes.
result Demonstrates the test's effectiveness across different path properties relevant to financial modeling.

New algorithms for interactive learning match minimax bounds efficiently.

problem Interactive learning in the realizable setting with computational efficiency.
method General framework, computationally efficient algorithms, Monte Carlo hit-and-run sampling.
result Sample complexities quantifiable in terms of combinatorial quantities, computationally efficient.

General lower bounds on neural network approximation in L^p norm.

problem Fundamental limits of neural network expressivity.
method General lower bound proof on approximation in L^p norm, applied to feed-forward neural networks.
result Neural networks can't approximate certain functions as well as previously thought.

Introduces a space of almost complex structures for complex Lie group bundles.

problem Integrability of almost complex structures on complex Lie group bundles.
method Introduces a space of bundle almost complex structures and studies their properties.
result Locally pseudo-holomorphic sections exist if and only if the obstruction form is zero.

Smooth families of biholomorphisms between strongly pseudoconvex domains are shown to be smooth.

problem Smoothness of families of biholomorphisms between strongly pseudoconvex domains.
method Riemannian geometry of Bergman metrics and smoothness of families of isometries.
result Smoothness of families of biholomorphisms between strongly pseudoconvex domains.

On a compact, oriented, Riemannian manifold, the Hodge decomposition theorem associates a smooth primitive to any exact smooth form omega. In this paper, we show that given a smooth family of exact smooth forms omega(t), the family of associated primitives is also a smooth family with respect to t.

2009-11-16abs ↗pdf ↗

Estimates time-varying network connections using multi-stage smoothing.

problem Estimating edge probabilities of time-varying networks.
method Multi-stage smoothing: temporal local smoothing followed by node-domain smoothing.
result Captures both smooth temporal evolution and structural patterns in connectivity.

We define a diffeomorphism invariant of smooth 4-manifolds which we can estimate for many smoothings of R^4 and other smooth 4-manifolds. Using this invariant we can show that uncountably many smoothings of R^4 support no Stein structure. (Gompf has constructed uncountably many smoothings of R^4 which do support Stein …

1997-12-06abs ↗pdf ↗

Smooth activations enable optimal error rates in neural networks for Sobolev function classes.

problem Achieving optimal approximation and estimation error rates for neural networks in Sobolev function classes.
method Study of neural networks with smooth activations, proving optimal rates via approximation and statistical properties.
result Constant-depth networks with smooth activations achieve optimal rates of approximation and estimation, demonstrating smoothness adaptivity.

Variant of previous work on smooth algebraic functions with compact and non-compact preimages.

problem Constructing smooth algebraic functions with specific preimage properties.
method Explicit construction of smooth real algebraic functions with controlled preimage compactness.
result New results in singularity theory and real algebraic geometry.

The study bounds and characterizes surfaces containing smooth conics and twistor fibers in a flag threefold.

problem Bounding and characterizing surfaces containing smooth conics and twistor fibers in a flag threefold.
method Analyzing the family of smooth conics and using algebraic properties to construct surfaces.
result The only smooth cases of surfaces containing infinitely many twistor fibers are of bidegree (1,1).

In this note we introduce the notion of a smooth structure on a conical pseudomanifold MM in terms of CC^\infty-rings of smooth functions on MM. For a finitely generated smooth structure C(M)C^\infty (M) we introduce the notion of the Nash tangent bundle, the Zariski tangent bundle, the tangent bundle of MM, and the …

2010-06-29abs ↗pdf ↗

Kontsevich's classes distinguish smooth structures on fiber bundles.

problem Distinguishing smooth structures on fiber bundles.
method Using Kontsevich's characteristic classes and real blow-up construction.
result Kontsevich's classes are determined by the topology of the 2-point configuration space bundle.

Label smoothing improves model performance even with noisy labels.

problem Mitigating label noise in deep learning models.
method Examined label smoothing as a technique to cope with label noise and compared it to loss-correction methods.
result Label smoothing is competitive with loss-correction techniques under label noise and beneficial for distillation from noisy data.

We construct an analytic multiplicative model of smooth K-theory. We further introduce the notion of a smooth K-orientation of a proper submersion and define the associated push-forward which satisfies functoriality, compatibility with pull-back diagrams, and projection and bordism formulas. We construct a multiplicati…

2007-06-30abs ↗pdf ↗

Theory of smooth relative connections on quiver bundles developed.

problem Existence of smooth relative connections over quiver bundles.
method Developed a theory over RQ\mathbb{R}Q on smooth twisted quiver bundles, provided obstructions and necessary/sufficient conditions.
result Established a necessary and sufficient condition for the existence of smooth relative connections on tree-type quiver bundles.

We show that every smooth manifold admits a smooth triangulation transverse to a given smooth map. This removes the properness assumption on the smooth map used in an essential way in Scharlemann's construction [5].

2010-12-17abs ↗pdf ↗

Smooth actions of cyclic groups on 3-manifolds are conjugate to smooth ones.

problem Understanding smoothness in group actions on 3-manifolds.
method Finite cyclic group actions by (1+ε)(1+\varepsilon)-bilipschitz homeomorphisms on closed 3-manifolds.
result Finite cyclic group actions by (1+ε)(1+\varepsilon)-bilipschitz homeomorphisms on closed 3-manifolds are conjugate to smooth actions.

Smooth Schrödinger Bridges improve trajectory inference by smoothing Gaussian processes.

problem Improving trajectory inference in applications like particle tracking.
method Generalizes Schrödinger Bridge problem to smooth Gaussian processes, solving the problem on phase space.
result The method outperforms existing methods on real datasets.