arXiv research

The paper introduces risk consistency properties for credit ratings.

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

Develops a framework for consistent pricing of interest rate derivatives.

New theorem for generalized group sparsity improves consistency and convergence rates.

The paper studies multi-curve interest rate models and their consistency and finite-dimensional realizations.

Deep neural networks without regularization can achieve consistent estimates with good convergence rates.

We derive high-probability finite-sample uniform rates of consistency for $k$-NN regression that are optimal up to logarithmic factors under mild assumptions. We moreover show that $k$-NN regression adapts to an unknown lower intrinsic dimension automatically. We then apply the $k$-NN regression rates to establish new …

Research on nearest-neighbor methods tends to focus somewhat dichotomously either on the statistical or the computational aspects -- either on, say, Bayes consistency and rates of convergence or on techniques for speeding up the proximity search. This paper aims at bridging these realms: to reap the advantages of fast …

We establish the consistency of an algorithm of Mondrian Forests, a randomized classification algorithm that can be implemented online. First, we amend the original Mondrian Forest algorithm, that considers a fixed lifetime parameter. Indeed, the fact that this parameter is fixed hinders the statistical consistency of …

Proof of Gaussian ML estimator consistency in linear auto-regressive models.

Study optimal stopping for group with diverse discount rates using an attitude function.

We introduce a solvable model of randomly growing systems consisting of many independent subunits. Scaling relations and growth rate distributions in the limit of infinite subunits are analysed theoretically. Various types of scaling properties and distributions reported for growth rates of complex systems in a variety…

This article studies the achievable guarantees on the error rates of certain learning algorithms, with particular focus on refining logarithmic factors. Many of the results are based on a general technique for obtaining bounds on the error rates of sample-consistent classifiers with monotonic error regions, in the real…

The paper proves neural networks' consistency and optimal convergence rates for various function classes.

In this paper we study the consistency of an empirical minimum error entropy (MEE) algorithm in a regression setting. We introduce two types of consistency. The error entropy consistency, which requires the error entropy of the learned function to approximate the minimum error entropy, is shown to be always true if the…

A new model for short rates using pure-jump processes.

We theoretically investigate the convergence rate and support consistency (i.e., correctly identifying the subset of non-zero coefficients in the large sample limit) of multiple kernel learning (MKL). We focus on MKL with block-l1 regularization (inducing sparse kernel combination), block-l2 regularization (inducing un…

Triangular flows ensure statistical consistency and fast rates in generative modeling.

Paper bounds convergence rate of adversarial surrogate risk.

The paper proposes a new method to estimate interest rates consistently under both risk-neutral and real-world measures.

Study optimal transport for stationary processes, estimating joinings and costs.

In this paper we improve the spectral convergence rates for graph-based approximations of Laplace-Beltrami operators constructed from random data. We utilize regularity of the continuum eigenfunctions and strong pointwise consistency results to prove that spectral convergence rates are the same as the pointwise consist…

Study identifies and validates a method for system identification of Markov jump linear systems.

This note fills the gap in market-consistent valuation of lifelong health insurance products.

Large learning rates cause oscillations in NN weights that improve generalization.

Paper optimizes federated PCA for covariance estimation under privacy constraints.

Investigates RI strategies for life insurers with LRD mortality rates.

Paper establishes a universal growth rate for smooth surrogate losses in classification.

We introduce a new concept, data irrecoverability, and show that the well-studied concept of data privacy is sufficient but not necessary for data irrecoverability. We show that there are several regularized loss minimization problems that can use perturbed data with theoretical guarantees of generalization, i.e., loss…

Improved nonparametric regression with debiasing for root-n consistency.

Demographic projections of future mortality rates involve a high level of uncertainty and require stochastic mortality models. The current paper investigates forward mortality models driven by a (possibly infinite dimensional) Wiener process and a compensated Poisson random measure. A major innovation of the paper is t…

Classical scaling is shown to be optimal under various noisy conditions.

OptiNet achieves near-minimax error rates with compression in Euclidean space.

Paper develops Euler scheme for fractional delay diff. eqs with additive noise.

Presently the most successful approaches to semi-supervised learning are based on consistency regularization, whereby a model is trained to be robust to small perturbations of its inputs and parameters. To understand consistency regularization, we conceptually explore how loss geometry interacts with training procedure…

Linear-Core Surrogates combine fast optimization and statistical efficiency in classification and structured prediction.

Unified model for equity option pricing and interest-rate risk assessment.

In our recent paper, we showed that in exponential family, contrastive divergence (CD) with fixed learning rate will give asymptotically consistent estimates \cite{wu2016convergence}. In this paper, we establish consistency and convergence rate of CD with annealed learning rate $η_t$. Specifically, suppose CD-$m$ gener…

We consider the effect of recovery rates on a pool of credit assets. We allow the recovery rate to depend on the defaults in a general way. Using the theory of large deviations, we study the structure of losses in a pool consisting of a continuum of types. We derive the corresponding rate function and show that it has …

Study on $H$-consistency bounds for machine learning surrogates.

New methods lift weak supervision to structured prediction, providing robustness guarantees.

In this work we introduce Heath-Jarrow-Morton (HJM) interest rate models driven by fractional Brownian motions. By using support arguments we prove that the resulting model is arbitrage free under proportional transaction costs in the same spirit of Guasoni [Math. Finance 16 (2006) 569-582]. In particular, we obtain a …

Paper compares ETF and futures carry rates in segmented Bitcoin markets.

The general problem of asset pricing when the discount rate differs from the rate at which an asset's cash flows accrue is considered. A pricing kernel framework is used to model an economy that is segmented into distinct markets, each identified by a yield curve having its own market, credit and liquidity risk charact…

We establish the first nonasymptotic error bounds for Kaplan-Meier-based nearest neighbor and kernel survival probability estimators where feature vectors reside in metric spaces. Our bounds imply rates of strong consistency for these nonparametric estimators and, up to a log factor, match an existing lower bound for c…

We study the set G of growth rates of of ideal Coxeter groups in hyperbolic 3-space which consists of real algebraic integers greater than 1. We show that (1) G is unbounded above while it has the minimum, (2) any element of G is a Perron number, and (3) growth rates of of ideal Coxeter groups with $n$ generators are l…

Study confirms learning rates for vector-valued spectral algorithms, proving consistency.

Maximum Variance Unfolding is one of the main methods for (nonlinear) dimensionality reduction. We study its large sample limit, providing specific rates of convergence under standard assumptions. We find that it is consistent when the underlying submanifold is isometric to a convex subset, and we provide some simple e…