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.

169,181 papers · 148 categories

Trend · papers per month

111222332443 · Jun 202019922001200920182026
48 results for sup-norm convergence rate

Deep neural networks with adversarial training achieve sup-norm convergence for nonparametric regression.

problem Achieving sup-norm convergence for deep neural network estimators in nonparametric regression.
method Developed an adversarial training scheme to address the sup-norm convergence issue.
result Deep neural network estimators achieve optimal sup-norm convergence with the proposed adversarial training.

The study analyzes convergence rates for sparse pivotal estimators in high-dimensional regression.

problem Sparse pivotal estimation in high-dimensional regression problems.
method Theoretical analysis and comparison of non-smooth + non-smooth optimization problems, including smoothing techniques.
result Minimax sup-norm convergence rates for square-root Lasso-type estimators are derived.

The higher order singular value decomposition (HOSVD) of tensors is a generalization of matrix SVD. The perturbation analysis of HOSVD under random noise is more delicate than its matrix counterpart. Recently, polynomial time algorithms have been proposed where statistically optimal estimates of the singular subspaces …

2017-07-05abs ↗pdf ↗

Paper analyzes frequentist coverage and convergence rates in Gaussian process regression.

problem Understanding frequentist coverage and convergence rates in Gaussian process regression.
method Develops a Bernstein von-Mises type result and compares posterior distributions to population level GPs.
result Frequentist coverage probabilities of Bayesian credible intervals and bands converge to a non-degenerate value.

This paper analyzes how machine learning models resist adversarial attacks in nonparametric regression.

problem Adversarial attacks on machine learning models in nonparametric regression.
method Theoretical analysis of minimax rates of convergence under adversarial sup-norm.
result The minimax rate under adversarial attacks is the sum of two terms: standard rate and deviation of true function.

This paper analyzes deep Stable neural networks, showing convergence rates under different growth settings.

problem Analyzing the behavior of deep Stable neural networks as width increases.
method Large-width asymptotic analysis and convergence rates for fully connected feed-forward deep Stable NNs.
result The rescaled deep Stable NN converges weakly to a Stable SP under joint growth, with sup-norm convergence rates established.

If (M,g)(M,g) is a compact real analytic Riemannian manifold, we give a necessary and sufficient condition for there to be a sequence of quasimodes of order o(λ)o(λ) saturating sup-norm estimates. In particular, it gives optimal conditions for existence of eigenfunctions satisfying maximal sup norm bounds. The condition is …

2013-11-15abs ↗pdf ↗

Study on QQ-function estimation for continuous state-action MDPs, deriving rates and conditions.

problem Estimating QQ-function in off-policy evaluation for continuous state-action Markov decision processes.
method Reformulated as nonparametric instrumental variables (NPIV) problem, derived minimax lower bounds, proposed sieve two-stage least squares estimator.
result First minimax lower bounds for QQ-function and its derivatives in sup-norm and L2L^2-norm, same as classical nonparametric regression.

New methods for estimating and inferring nonparametric structural functions and elasticities.

problem Estimating and inferring nonparametric structural functions and their derivatives.
method Data-driven sieve dimension choice and uniform confidence bands construction.
result Optimal estimation and inference procedures with minimax rates of convergence.

High regularity biharmonic wave maps shown to be locally well-posed.

problem Local wellposedness of biharmonic wave maps with high Sobolev regularity.
method Vanishing viscosity and parabolic regularization to prove existence; geometric nature exploited.
result Local wellposedness established in high Sobolev regularity.

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 ↗

A key problem in reinforcement learning for control with general function approximators (such as deep neural networks and other nonlinear functions) is that, for many algorithms employed in practice, updates to the policy or QQ-function may fail to improve performance---or worse, actually cause the policy performance …

2016-02-29abs ↗pdf ↗

We complete the quasi-isometric classification of irreducible lattices in semisimple Lie groups over nondiscrete locally compact fields of characteristic zero by showing that any quasi-isometry of a rank one S-arithmetic lattice in a semisimple Lie group over nondiscrete locally compact fields of characteristic zero is…

2005-04-11abs ↗pdf ↗

Analyzes Kodaira-Iitaka dimension and multiplicity using intersection theory.

problem Understanding Kodaira-Iitaka dimension and multiplicity in analytic terms.
method Expresses dimensions and multiplicity in terms of intersection theory of plurisubharmonic envelopes.
result Introduces non-pluripolar numerical Kodaira-Iitaka dimension and shows it dominates the classical dimension.

Self-focal points on ellipsoids of dimension 3 or higher are rare.

problem Existence of self-focal points on Riemannian manifolds of dimension 3 or higher.
method Analyzing geodesics and umbilic points on ellipsoids of various dimensions.
result Ellipsoids of dimension 3 or higher with at least 4 distinct axes have no self-focal points.

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.

Let YY be a compact, oriented 3-manifold with a contact form aa and a metric ds2ds^2. Suppose that FYF\to Y is a principal bundle with structure group U(2)=SU(2)×±1S1U(2) = SU(2)\times_{\pm1}S^1 such that F/S1F/S^1 is the principal SO(3) bundle of orthonormal frames for TYTY. A unitary connection A0A_0 on the Hermitian line bundle $…

2013-07-17abs ↗pdf ↗

We prove uniform sup-norm estimates for the Monge-Ampere equation with respect to a family of Kahler metrics which degenerate towards a pull-back of a metric from a lower dimensional manifold. This is then used to show the existence of generalized Kahler-Einstein metrics as the limits of the Kahler-Ricci flow for some …

2007-10-05abs ↗pdf ↗

Existence of Q-processes for Brownian motion on hyperbolic spaces with Poissonian potentials shown.

problem Existence of path limits (Q-processes) for Brownian motion on hyperbolic spaces with Poissonian potentials.
method Analysis of stationary random potentials with spectral and sup norm bounds, and use of foliated space defined by the point process.
result Existence of Q-processes for Brownian motion on hyperbolic spaces with Poissonian potentials shown.

The study connects norms and filtrations on section rings of projective manifolds.

problem Understanding norms and filtrations on section rings of polarized projective manifolds.
method Analyzes submultiplicative norms and their equivalence to sup-norms, discusses applications to spectral theory and holomorphic extension.
result Injective and projective tensor norms on symmetric algebras are asymptotically equivalent.

Study convergence rates of variational posterior distributions for inference.

problem Characterize convergence rates of variational posterior distributions for nonparametric and high-dimensional inference.
method Formulate general conditions on prior, likelihood, and variational class to characterize convergence rates. Propose novel prior mass conditions for specific prior distributions.
result The convergence rate of variational posterior distributions is the sum of the convergence rate of the true posterior and the variational approximation error.

Study shows convergence rates for BSDEs approximated by compound Poisson processes.

problem Analyzing convergence rates of BSDEs driven by Lévy processes.
method Approximating Lévy processes by compound Poisson processes and studying BSDEs.
result Optimal convergence rates derived for BSDEs in L2\mathbb L^2-norm and Wasserstein distance.

Paper establishes convergence rates and concentration bounds for stochastic approximation and reinforcement learning with Markovian noise.

problem Analyzing convergence rates and concentration bounds for stochastic approximation and reinforcement learning with Markovian noise.
method Novel discretization of the mean ODE of stochastic approximation algorithms using intervals with diminishing length.
result First almost sure convergence rate and maximal concentration bound with exponential tails for contractive stochastic approximation algorithms with Markovian noise.

Paper analyzes faster convergence rates for reinforcement learning from offline data.

problem Analyzing faster convergence rates for reinforcement learning from offline data.
method Fine analysis of reinforcement learning from offline data, providing fast rates for regret convergence.
result The paper provides fast rates for the regret convergence, showing that the level of exponentiation depends on the noise in the decision-making problem.

Study shows LDA topic models converge at rate n^-1/4 without strict topic separability.

problem Convergence rates of Latent Dirichlet Allocation (LDA) topic models.
method Maximum likelihood estimator, Wasserstein's distance metric, without separability or non-degeneracy assumptions.
result Maximum likelihood estimator converges at rate n^-1/4, optimal in worst case.

Study Hamiltonian diffeomorphisms on symplectic manifolds and properties of invariant convex functions.

problem Properties of invariant convex functions under Hamiltonian diffeomorphisms.
method Analysis of the adjoint action and properties of invariant convex functions.
result Continuous convex functions invariant under Hamiltonian diffeomorphisms are also invariant under strict rearrangements.

Gradient descent achieves exact linear convergence rate for symmetric matrix completion.

problem Low-rank symmetric matrix completion using gradient descent.
method Local analysis of gradient descent for symmetric matrices without additional assumptions.
result Closed-form expression of exact linear convergence rate matches practice.