The paper improves PAC-Bayes bounds for losses with finite moments.
problem Bounding generalization for losses with heavy tails and finite moments.
method Truncation method and PAC-Bayes bounds for unbounded losses with heavy tails and bounded variance.
result Bounds interpolate between slow and fast rates depending on the moment.
The paper proves that Gaussian field critical points have finite moments.
problem Proving the finiteness of moments for Gaussian field critical points.
method General approach not specific to critical points, using Taylor polynomial non-degeneracy.
result The finiteness of moments of the number of critical points of Gaussian fields.
Unified framework for mean testing under truncation bias.
problem High-dimensional mean testing under arbitrary truncation.
method Characterizes fundamental limits and develops a simple second-order test.
result Unified framework connects finite-moment, sub-Gaussian, and median-regular structural regimes.
We provide conditions for the existence and the unicity of strictly stationary solutions of the usual Dynamic Conditional Correlation GARCH models (DCC-GARCH). The proof is based on Tweedie's (1988) criteria, after having rewritten DCC-GARCH models as nonlinear Markov chains. Moreover, we study the existence of their f…
New algorithm for robust regression with subgaussian error bound.
problem Linear regression in the presence of outliers and finite moments.
method Adaptation of spectral method to linear regression problem.
result Optimal sub-gaussian error bound for robust regression.
In linear stochastic bandits, it is commonly assumed that payoffs are with sub-Gaussian noises. In this paper, under a weaker assumption on noises, we study the problem of \underline{lin}ear stochastic {\underline b}andits with h{\underline e}avy-{\underline t}ailed payoffs (LinBET), where the distributions have finite…
We provide explicit conditions on the distribution of risk-neutral log-returns which yield sharp asymptotic estimates on the implied volatility smile. We allow for a variety of asymptotic regimes, including both small maturity (with arbitrary strike) and extreme strike (with arbitrary bounded maturity), extending previ…
This paper investigates analytic properties of American option prices under the finite moment log-stable (FMLS) model. Under this model the price of American options is characterised by the free boundary problem of a fractional partial differential equation (FPDE) system. Using the technique of approximation we prove t…
We establish an explicit pricing formula for the class of Lévy-stable models with maximal negative asymmetry (Log-Lévy model with finite moments and stability parameter 1<α≤2) in the form of rapidly converging series. The series is obtained with help of Mellin transform and the residue theory in C2. T…
New margin-based learning guarantees improve generalization bounds.
problem Improving generalization bounds for machine learning models.
method Relative deviation margin bounds using empirical margin loss and Rademacher complexity.
result Distribution-dependent generalization bounds for unbounded loss functions.
The study of random walks on hyperbolic spaces and Teichmüller spaces, proving central limit theorems and geodesic tracking.
problem Analyzing random walks on hyperbolic and Teichmüller spaces.
method Proving central limit theorems and geodesic tracking using finite moments and logarithmic moments.
result Translation lengths of random isometries satisfy a central limit theorem if and only if the random walk has finite second moment.
Affine jump-diffusions constitute a large class of continuous-time stochastic models that are particularly popular in finance and economics due to their analytical tractability. Methods for parameter estimation for such processes require ergodicity in order establish consistency and asymptotic normality of the associat…
In this paper we study the exponential functionals of the processes X with independent increments , namely It=∫0texp(−Xs)ds,,t≥0, and also I∞=∫0∞exp(−Xs)ds. When X is a semi-martingale with absolutely continuous characteristics, we derive recurrent integral equat…
New protocols show 1-bit mean estimation can be order-optimal without interaction.
problem Can 1-bit mean estimation be optimal without interaction?
method Adaptive and non-adaptive threshold and interval queries, with one adaptive transition.
result Arbitrary non-adaptive quantizers can match the adaptive rate, suggesting interaction is not necessary.
Study on queues with Hawkes arrivals, proving steady-state behavior and developing an efficient algorithm.
problem Analyzing the steady-state behavior of queues with Hawkes arrivals.
method Novel coupling techniques and exponential convergence results for workload and busy period processes.
result Exponential convergence of queueing processes to their stationary distribution.
A new law limits kurtosis contrast in balanced mixtures.
problem Kurtosis-based ICA fails in wide, balanced mixtures.
method Proved a redundancy law and showed purification restores contrast.
result Kurtosis contrast obeys O(κmax/Reff) in balanced mixtures. In recent studies the truncated Levy process (TLP) has been shown to be very promising for the modeling of financial dynamics. In contrast to the Levy process, the TLP has finite moments and can account for both the previously observed excess kurtosis at short timescales, along with the slow convergence to Gaussian at …
Variational inference with α-divergences has been widely used in modern probabilistic machine learning. Compared to Kullback-Leibler (KL) divergence, a major advantage of using α-divergences (with positive α values) is their mass-covering property. However, estimating and optimizing α-divergences require to use importa…
Improved KL bounds and Wasserstein guarantees for diffusion flow matching under minimal conditions.
problem Theoretical convergence properties of Brownian motion based diffusion flow matching.
method Refined analysis under Kullback-Leibler and 2-Wasserstein distances.
result State-of-the-art scaling in KL convergence bounds under minimal conditions.
Revisits Lee's Moment Formula, relaxing moment assumptions for implied volatility.
problem Implied volatility constraints under finite log-moments.
method Analyzes stock price martingale with finite log-moments, derives new bounds and proof.
result New bounds on implied volatility growth, relaxes moment assumptions.
We study the estimation of the parametric components of single and multiple index volatility models. Using the first- and second-order Stein's identities, we develop methods that are applicable for the estimation of the variance index in the high-dimensional setting requiring finite moment condition, which allows for h…
High frequency data in finance have led to a deeper understanding on probability distributions of market prices. Several facts seem to be well stablished by empirical evidence. Specifically, probability distributions have the following properties: (i) They are not Gaussian and their center is well adjusted by Levy dist…
We tackle the problem of estimating a location parameter with differential privacy guarantees and sub-Gaussian deviations. Recent work in statistics has focused on the study of estimators that achieve sub-Gaussian type deviations even for heavy tailed data. We revisit some of these estimators through the lens of differ…
New robust estimators achieve subgaussian bounds using VC-dimension.
problem Robust estimation of sparse and corrupted data.
method Use of VC-dimension to measure statistical complexity.
result First robust estimators for sparse estimation with subgaussian rate.
In this paper, for μ and ν two probability measures on Rd with finite moments of order ρ≥1, we define the respective projections for the Wρ-Wasserstein distance of μ and ν on the sets of probability measures dominated by ν and of probability measures larger than μ in the convex order. Th…
Proposes a new ARCH framework for Hilbert space data.
problem Models for data in Hilbert spaces with evolving covariance operators.
method Defines an operator-level ARCH model for Hilbert space data.
result Establishes conditions for stationarity and consistency of estimators.
The paper improves Monte Carlo methods for optimization problems.
problem Efficiently solving optimization problems with biased Monte Carlo estimators.
method Introduces Multilevel Monte Carlo (MLMC) within Sample Average Approximation (SAA).
result Establishes uniform convergence and sample complexity for MLMC in SAA.
New method improves generative modeling on convex domains using regularized mirror maps and Student-t priors.
problem Challenges in generative modeling on convex domains with heavy-tailed targets.
method Mirror Flow Matching with regularized mirror maps and Student-t priors.
result Empirically outperforms baselines and achieves competitive sample quality.
New method finds closest martingale to Brownian motion.
problem Finding optimal martingale interpolating marginals.
method Martingale Sinkhorn algorithm, iterative scheme.
result Algorithm yields Bass potential in arbitrary dimension.
Understanding and developing a correlation measure that can detect general dependencies is not only imperative to statistics and machine learning, but also crucial to general scientific discovery in the big data age. In this paper, we establish a new framework that generalizes distance correlation --- a correlation mea…
The COS method for European options pricing is improved with a new bound for the number of terms.
problem Determining the optimal number of terms in the COS method for accurate European option pricing.
method Using Fourier-cosine expansion, the study finds an explicit bound for the number of terms N in the cosine series approximation.
result The COS method achieves exponential convergence when the log-return density is smooth, but not when it has heavy tails.
BBVI converges nearly dimensionally independent for log-concave targets.
problem Efficiently optimizing variational parameters in high-dimensional spaces.
method Proved convergence rate of BBVI with reparametrization gradient for log-concave targets.
result BBVI converges with nearly independent dimension dependence for log-concave targets.
Study uses Wasserstein distance to identify causal orders and unmix sources.
problem Identifying causal relationships and separating sources in non-Gaussian data.
method Wasserstein distance for non-Gaussianity, linear ICA, causal inference.
result Exact identification of ICA unmixing matrix and causal orders.
Study on random matrices in deep neural networks using Gaussian data.
problem Distribution of singular values in product of random matrices in deep learning.
method Free probability theory combined with standard techniques of random matrix theory.
result Justification for applying free probability theory to non-independent random data matrices.
In the paper "On Truncated Variation of Brownian Motion with Drift" (Bull. Pol. Acad. Sci. Math. 56 (2008), no.4, 267 - 281) we defined truncated variation of Brownian motion with drift, Wt=Bt+μt,t≥0, where (Bt) is a standard Brownian motion. Truncated variation differs from regular variation by neglect…
A new method for estimating causal parameters from observables reduces the need for finite moment conditions.
problem Estimating causal parameters from observational data with unknown or infinite moment conditions.
method Variational Method of Moments (VMM) for a general class of estimators, including kernel and neural net-based methods.
result VMM estimators are consistent, asymptotically normal, and semiparametrically efficient.
New method makes reinforcement learning robust to heavy-tailed rewards.
problem Heavy-tailed rewards cause statistical outliers in reinforcement learning.
method Dynamic gradient clipping in TD learning and NAC.
result Provably robust TD and NAC achieve optimal sample complexities.
Develops a contraction framework for MCMC mixing rates.
problem Proving mixing-time bounds for MCMC algorithms.
method Global and local contraction coefficients under Eγ-divergence. result Explicit global contraction coefficients for Gaussian smoothing.
This paper shows universality in spectrum behavior for random inner-product kernel matrices in polynomial regime.
problem Understanding spectrum behavior of random inner-product kernel matrices in polynomial regime.
method Analyzing matrices formed by a nonlinear function applied entrywise to a sample-covariance matrix, considering i.i.d. entries with all finite moments.
result The spectrum of random inner-product kernel matrices is universally described by the free convolution of the semicircular and Marčenko-Pastur distributions, with relative weights given by expanding the nonlinear function in the Hermite basis.
Improved portfolio optimization method reduces risk and improves performance.
problem Minimizing risk in large portfolios with limited data.
method Combines Tikhonov regularization and direct shrinkage of portfolio weights.
result Significantly reduces out-of-sample variance and Sharpe ratio compared to existing methods.
Paper introduces robust kernel ridge regression using Cauchy loss for handling various noise types.
problem Developing robust regression methods for noisy data.
method Introduces kernel Cauchy ridge regressor (KCRR) using Cauchy loss function.
result Establishes almost minimax-optimal convergence rate for KCRR in terms of L2-risk. This note presents an operational measure of fat-tailedness for univariate probability distributions, in [0,1] where 0 is maximally thin-tailed (Gaussian) and 1 is maximally fat-tailed. Among others,1) it helps assess the sample size needed to establish a comparative n needed for statistical significance, 2) allows…
New diffusion models learn distributions from samples with improved error bounds.
problem Statistical guarantees for score-based diffusion models on low-dimensional data.
method Derive finite-sample error bounds for Wasserstein-p distance. result Error bounds scale as n−1/dp,q∗(μ) for diffusion models. We derive a new radial link for binary classification under shared elliptical distributions.
problem Binary classification under shared-generator elliptical class-conditional distributions.
method We derive the Bayes radial-link family from the within-class radius law and estimate it by a finite fractional-power stochastic-polynomial projection.
result The derived link is asymptotically Bayes-optimal and significantly better than QDA on various benchmarks.