arXiv research

The study introduces a high-dimensional tail index model for viral post analysis.

Kurtosis is seen as a measure of the discrepancy between the observed data and a Gaussian distribution and is defined when the 4th moment is finite. In this work an empirical study is conducted to investigate the behaviour of the sample estimate of kurtosis with respect to sample size and the tail index when applied to…

Paper introduces a new robust method for estimating Pareto tail index from grouped data.

Cyclic and randomized stepsizes can lead to heavier tails in SGD, improving generalization.

Heavy-tailed distributions emerge in SGD's parameter evolution.

Bitcoin returns exhibit a distinct inverse cubic law scaling behavior.

We investigate the probability distribution of order imbalance calculated from the order flow data of 43 Chinese stocks traded on the Shenzhen Stock Exchange. Two definitions of order imbalance are considered based on the order number and the order size. We find that the order imbalance distributions of individual stoc…

Study improves policy search in continuous control by using heavy-tailed distributions.

This paper analyzes bias-variance trade-off for clipped SFOMs, improving complexity guarantees for heavy-tailed noise.

A neural network estimates sampling distributions for hard problems where classical methods fail.

Study reveals heavy-tailed behavior in training ReLU gates.

Detailed study of multifractal characteristics of the financial time series of asset values and of its returns is performed using a collection of the high frequency Deutsche Aktienindex data. The tail index ($α$), the Renyi exponents based on the box counting algorithm for the graph ($d_q$) and the generalized Hurst ex…

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…

AdaGrad converges under heavy-tailed noise without extra operations.

We build a methodology that takes a given option price in the tails with strike $K$ and extends (for calls, all strikes > $K$, for puts all strikes $< K$) assuming the continuation falls into what we define as "Karamata Constant" over which the strong Pareto law holds. The heuristic produces relative prices for options…

The study examines when large trades are considered news or liquidity shocks in a market model.

For a risk vector $V$, whose components are shared among agents by some random mechanism, we obtain asymptotic lower and upper bounds for the individual agents' exposure risk and the aggregated risk in the market. Risk is measured by Value-at-Risk or Conditional Tail Expectation. We assume Pareto tails for the componen…

The gradient noise (GN) in the stochastic gradient descent (SGD) algorithm is often considered to be Gaussian in the large data regime by assuming that the \emph{classical} central limit theorem (CLT) kicks in. This assumption is often made for mathematical convenience, since it enables SGD to be analyzed as a stochast…

This paper analyzes ETFs with Taiwan exposure, finding heavy tails and asymmetric volatility.

This paper presents a statistical analysis of Tehran Price Index (TePIx) for the period of 1992 to 2004. The results present asymmetric property of the return distribution which tends to the right hand of the mean. Also the return distribution can be fitted by a stable Levy distribution and the tails are very fatter th…

Modeling risk and performance with Levy-stable distributions.

This paper develops a structural credit risk model to characterize the difference between the economic and recorded default times for a firm. Recorded default occurs when default is recorded in the legal system. The economic default time is the last time when the firm is able to pay off its debt prior to the legal defa…

The hidden tail of empirical distributions is analyzed using extreme value theory.

We consider the problem of risk diversification of $α$-stable heavy tailed risks. We study the behaviour of the aggregated Value-at-Risk, with particular reference to the impact of different tail dependence structures on the limits to diversification. We confirm the large evidence of sub-additivity violations, particul…

Using daily returns of the S&P 500 stocks from 2001 to 2011, we perform a backtesting study of the portfolio optimization strategy based on the extreme risk index (ERI). This method uses multivariate extreme value theory to minimize the probability of large portfolio losses. With more than 400 stocks to choose from, ou…

We study the problems related to the estimation of the Gini index in presence of a fat-tailed data generating process, i.e. one in the stable distribution class with finite mean but infinite variance (i.e. with tail index $α\in(1,2)$). We show that, in such a case, the Gini coefficient cannot be reliably estimated usin…

The paper uses EVT to improve tail risk measures under ambiguity sets.

Basel II and Solvency 2 both use the Value-at-Risk (VaR) as the risk measure to compute the Capital Requirements. In practice, to calibrate the VaR, a normal approximation is often chosen for the unknown distribution of the yearly log returns of financial assets. This is usually justified by the use of the Central Limi…

Social and economic systems are complex adaptive systems, in which heterogenous agents interact and evolve in a self-organized manner, and macroscopic laws emerge from microscopic properties. To understand the behaviors of complex systems, computational experiments based on physical and mathematical models provide a us…

Proposes a tail-adaptive shrinkage method for robust sparse estimation.

Random matrix analysis reveals that neural network weights are mostly random, with some indicating learned information.

The gradient noise (GN) in the stochastic gradient descent (SGD) algorithm is often considered to be Gaussian in the large data regime by assuming that the classical central limit theorem (CLT) kicks in. This assumption is often made for mathematical convenience, since it enables SGD to be analyzed as a stochastic diff…

New framework controls generalization for heavy-tailed data in RLHF and SGLD.

Proposes a new tail risk measure based on the most probable maximum risk event size.

Proves generalization bounds for SGD using Feller processes and Hausdorff dimension.

The study analyzes how covariance estimation errors affect the global minimum-variance portfolio under heavy-tailed distributions.

Unified asymptotic theory and tests for ACD models reveal infinite-mean durations in cryptocurrency trading.

Recently, the study of heavy-tailed noises in first-order nonconvex stochastic optimization has gotten a lot of attention since it was recognized as a more realistic condition as suggested by many empirical observations. Specifically, the stochastic noise (the difference between the stochastic and true gradient) is con…

Sandpile Economics explains how economies can be prone to large crises from small shocks.

We study and generalize in various ways the model of rational expectation (RE) bubbles introduced by Blanchard and Watson in the economic literature. First, bubbles are argued to be the equivalent of Goldstone modes of the fundamental rational pricing equation, associated with the symmetry-breaking introduced by non-va…

DE-SGD shows heavy-tailed behavior in decentralized settings.

Study free energy in spherical spin glasses, proving universality dichotomy.

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…

Study quantifies model risk in cyber insurance, affecting premium pricing.