Econometric framework integrates heavy-tailed distributions with behavioral probability weighting for better asset pricing.
problem Underestimation of Value-at-Risk by traditional models in asset pricing.
method Developed an econometric framework combining heavy-tailed Student's t distributions with behavioral probability weighting. result Student's t specifications outperform Gaussian models in 88.4% of cases, reducing underestimation of Value-at-Risk by 16.5 percentage points. New class of heavy-tailed distributions shows weighted averages dominate individual variables.
problem Understanding and comparing risks in heavy-tailed distributions.
method Introducing a new class of heavy-tailed distributions and proving stochastic dominance relations.
result Weighted averages of random variables in this class are stochastically larger than individual variables.
Heavy-tailed regularization improves deep neural network performance.
problem Improving generalization of deep neural networks.
method Introducing Heavy-Tailed Regularization, using differentiable penalty terms and Bayesian statistics.
result Heavy-tailed regularization outperforms conventional regularization techniques.
This work compresses heavy-tailed weight matrices for tighter generalization bounds.
problem Empirical evidence linking heavy-tailed weight matrices to test set accuracy but lack of formal relationship with generalization bounds.
method Utilized the compression framework to show that heavy-tailed matrices can be compressed, resulting in sparse weight matrices.
result Demonstrated a non-vacuous generalization bound for compressed networks with heavy-tailed weight matrices.
Study heavy-tailed weights' impact on neural network's spectral distribution.
problem Analyzing spectral distribution of conjugate kernel matrices with heavy-tailed weights.
method Computed limiting eigenvalue distribution through moments, considering heavy-tailed distributions and nonlinear activation functions.
result Heavy-tailed weights induce strong correlations, leading to fundamentally different spectral behavior.
Bayesian deep learning with heavy-tailed weights achieves near-optimal performance.
problem Deep neural networks with heavy-tailed weights achieve near-optimal performance in various contexts.
method Introduced a Bayesian deep learning prior based on heavy-tailed weights and ReLU activation, showing near-optimal minimax contraction rates.
result Posterior distribution achieves near-optimal minimax contraction rates, adaptive to smoothness and intrinsic dimension.
The difficulty of classification affects the weight matrices' heavy tail appearance in deep learning networks.
problem Understanding the spectral properties of weight matrices in deep learning networks.
method Spectral analysis of weight matrices in different modules of DNNs, classification difficulty as a driving factor for heavy tail appearance.
result Higher classification difficulty leads to more frequent appearance of heavy tails in weight matrices spectra.
New theory predicts deep neural networks can operate in an extended critical regime without fine-tuning.
problem Understanding the dynamics and computational principles of deep neural networks.
method Combining theories of heavy-tailed random matrices and non-equilibrium statistical physics.
result Deep neural networks can operate in an extended critical regime without fine-tuning parameters.
Is AdamW effective under heavy-tailed noise?
problem Stochastic gradient noise in LLM pretraining is typically heavy-tailed.
method Formulate as an open problem, prove a positive weighted-metric benchmark, and give a corridor lower-bound mechanism.
result No rigorous convergence theory for AdamW established in heavy-tailed regime.
TTF improves performance of normalizing flows for heavy-tailed distributions.
problem Improving performance of normalizing flows for heavy-tailed distributions.
method Uses a Gaussian base distribution and a final transformation layer to produce heavy tails.
result Experimental results show TTF outperforms current methods, especially in high-dimensional or heavy-tailed scenarios.
Deep neural networks with heavy-tailed weights converge to stable distributions.
problem Understanding the convergence of heavy-tailed weights in infinitely-wide neural networks.
method Analyzing infinitely-wide multi-layer perceptrons with i.i.d. symmetric α-stable weight distributions. result The vector of pre-activation values converges to i.i.d. symmetric α-stable distributions. Optimizes option portfolios for skewed-t returns using VaR and variance measures.
problem Optimizing portfolios for skewed-t returns with heavy tails and skewness.
method Uses variance and VaR measures, departing from normal returns, and provides explicit portfolio weights.
result Optimal portfolio weights differ significantly from variance optimal weights due to skewness.
Study uses spectral risk for learning with heavy-tailed data.
problem Learning with heavy-tailed loss distributions.
method Spectral risk with Lipschitz-continuous density, derivative-free learning.
result Excess risk guarantees and improved performance over traditional methods.
New models explain heavy-tailed behavior in neural networks.
problem Heavy-tailed spectral densities in neural networks.
method High-temperature Marchenko-Pastur (HTMP) ensemble models.
result Heavy-tailed behavior arises from three factors: data structure, training temperature, and eigenvector entropy.
COS method convergence conditions expanded for heavy-tailed distributions.
problem Ensuring convergence of the COS method for various densities.
method Analyzing truncation error and providing conditions for convergence.
result Conditions for COS method convergence extended to include heavy-tailed distributions.
The paper develops a robust algorithm for contextual bandits with heavy-tailed rewards.
problem Contextual bandits with heavy-tailed rewards.
method Develops an algorithm based on Catoni's estimator for robust statistics, applying it to contextual bandits with general function approximation.
result Establishes regret bounds that depend on cumulative reward variance and logarithmically on the reward range and number of rounds.
This paper analyzes sampling from heavy-tailed distributions using discretized Itô diffusions.
problem Sampling from heavy-tailed distributions with finite variance.
method Mean-square analysis of discretized Itô diffusions with weighted Poincaré inequalities.
result Explicit iteration complexity for obtaining samples close to target distributions in Wasserstein-2 metric.
New insights into why neural networks generalize well.
problem Understanding why neural networks generalize well despite heavy-tailed weight distributions.
method Developed a simple model to analyze the emergence of heavy-tailed empirical spectral densities (ESDs) in two-layer neural networks without gradient noise.
result Learning rates play a crucial role in shaping the ESDs of two-layer neural networks, leading to better generalization.
New initialization schemes preserve fractional moments of weights in deep networks, improving training and test performance.
problem Heavy-tailed distribution of stochastic gradients in DNNs during training.
method Developed initialization schemes that preserve any given fractional moment of order s < 2 over layers for various activations.
result The network output admits a heavy-tailed distribution with finite moments, improving training and test performance.
Proofs high-dimensional spectrum convergence of weighted sample covariance.
problem High-dimensional spectrum convergence of weighted sample covariance.
method Proposes a new, concise proof with stronger assumptions.
result Spectrum convergence proven for different weight distributions.
New study shows diversification can increase risk for heavy-tailed losses.
problem Diversification can increase tail risk for heavy-tailed losses.
method Comparison of diversified portfolio to a 'one-basket' benchmark.
result Diversified portfolio has larger tail probabilities than a 'one-basket' benchmark for all thresholds.
Given two or more Deep Neural Networks (DNNs) with the same or similar architectures, and trained on the same dataset, but trained with different solvers, parameters, hyper-parameters, regularization, etc., can we predict which DNN will have the best test accuracy, and can we do so without peeking at the test data? In …
This paper analyzes ETFs with Taiwan exposure, finding heavy tails and asymmetric volatility.
problem Heavy tails and asymmetric volatility in Taiwan-related ETFs.
method Tail-risk diagnostics, asymmetric volatility modeling, and portfolio optimization under mean--variance and CVaR criteria.
result CVaR optimization produces more concentrated allocations, favoring SMH during the post-COVID AI-driven expansion.
Investigates spectral properties of neural networks, showing invariance under certain conditions.
problem Understanding the spectral evolution and invariance in linear-width neural networks.
method Empirical and theoretical analysis of spectra of weight matrices in high-dimensional settings.
result Spectra of weight matrices are invariant under certain training conditions, with implications for feature learning.
New method improves covariance estimation for weighted samples.
problem Improving covariance estimation for weighted sample data.
method Asymptotic non-linear shrinkage formulas for covariance and precision matrix estimators of weighted sample covariances.
result Asymptotic non-linear shrinkage formulas for covariance and precision matrix estimators of weighted sample covariances.
Paper proposes a new method for covariance estimation using M-estimators with eigenvalue shrinkage.
problem Estimating covariance matrices in heavy-tailed distributions.
method Replaces shrinkage sample covariance matrix with M-estimator of scatter matrix and optimizes shrinkage parameter.
result Shrinkage M-estimators outperform shrinkage SCM in heavy-tailed distributions.
This work creates a CS for non-negative heavy-tailed data with bounded mean.
problem Constructing a confidence sequence for non-negative heavy-tailed data with bounded mean.
method Non-parametric, non-asymptotic lower confidence sequence construction.
result The constructed CS is efficient and can be converted into a closed-interval CS.
Unified approach for robust and heavy-tailed mean estimation in high dimensions.
problem Estimating mean in high dimensions with adversarial corruption or heavy-tailed distributions.
method Unified meta-problem and duality theorem leading to Filter algorithm and QUE scheme.
result Unified and efficient algorithms for both robust and heavy-tailed mean estimation.
A new method estimates parameters in heavy-tailed corrupted regression with unknown covariance and heterogeneous noise.
problem Estimating parameters in regression with heavy-tailed errors and unknown covariance.
method Near-optimal computationally tractable estimator based on power method and Multiplicative Weight Update algorithm.
result The estimator achieves the optimal statistical rate and breakdown-point under near-optimal sample size.
Paper develops sparse learning for heavy-tailed time series with locally stationary dynamics.
problem Sparse learning for high-dimensional heavy-tailed locally stationary time series.
method Additive modeling with kernel smoothing, sparsity-inducing penalized estimation.
result Prediction-error bounds and convergence rates for different sparsity structures.
Random Matrix Theory (RMT) is applied to analyze the weight matrices of Deep Neural Networks (DNNs), including both production quality, pre-trained models such as AlexNet and Inception, and smaller models trained from scratch, such as LeNet5 and a miniature-AlexNet. Empirical and theoretical results clearly indicate th…
Exponential Lasso improves Lasso's robustness to outliers and heavy-tailed noise.
problem Lasso's sensitivity to outliers and heavy-tailed noise in high-dimensional statistics.
method Integrates an exponential-type loss function into the Lasso framework.
result Achieves strong statistical convergence rates robust to heavy-tailed contamination.
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…
Bayesian priors for neural networks are improved by incorporating weight correlations and tail behavior.
problem Improving Bayesian priors for neural networks to better reflect true beliefs and performance.
method Analyzed summary statistics of neural network weights in different architectures and incorporated these observations into new priors.
result Improved performance on image classification datasets by using new priors that account for weight correlations and tail behavior.
We consider a Gaussian process formulation of the multiple kernel learning problem. The goal is to select the convex combination of kernel matrices that best explains the data and by doing so improve the generalisation on unseen data. Sparsity in the kernel weights is obtained by adopting a hierarchical Bayesian approa…
Adaptive experiment designs can dramatically improve statistical efficiency in randomized trials, but they also complicate statistical inference. For example, it is now well known that the sample mean is biased in adaptive trials. Inferential challenges are exacerbated when our parameter of interest differs from the pa…
SHIFT improves robustness in estimating dose-response functions with heavy-tailed contamination.
problem Outliers bias estimates of average dose-response functions in heavy-tailed data.
method SHIFT combines cross-fit nuisance orthogonalization, Welsch-loss, and defensive OLS refit.
result SHIFT reduces RMSE from 1.03 to 0.33 on localized contamination test.
Researchers have constantly asked whether stock returns can be predicted by some macroeconomic data. However, it is known that macroeconomic data may exhibit nonstationarity and/or heavy tails, which complicates existing testing procedures for predictability. In this paper we propose novel empirical likelihood methods …
New study reveals how heavy-tailed SGD dynamics lead to compressible neural networks.
problem Understanding why large neural networks can be compressed effectively.
method Linking SGD dynamics to compressibility properties of neural networks.
result Large step-size/batch-size ratios and overparametrization lead to heavy-tailed SGD dynamics, making networks compressible.
Optimal algorithm identifies best arm for risk measures in heavy-tailed distributions.
problem Identifying the arm with smallest CVaR, VaR, or weighted sum of CVaR and mean from heavy-tailed distributions.
method Multi-armed bandit best-arm identification framework, solving non-convex optimization problem.
result Optimal δ-correct algorithm with matching lower bound on expected samples.
The paper integrates behavioral distortions into portfolio optimization using implied probability weighting functions.
problem Behavioral distortions in probability weighting affect portfolio optimization under different return distributions.
method Developed a unified framework to extract probability weighting functions from optimal portfolios modeled under Gaussian and NIG distributions.
result Increasing tail fatness amplifies behavioral distortions, and shifts in risk-free rates alter the curvature of these distortions.
Structured sparsity has recently emerged in statistics, machine learning and signal processing as a promising paradigm for learning in high-dimensional settings. All existing methods for learning under the assumption of structured sparsity rely on prior knowledge on how to weight (or how to penalize) individual subsets…
Study of deep neural networks with dependent weights leading to new model limits and properties.
problem Characterizing deep neural networks with dependent weights in the infinite-width limit.
method Modeling weights as a mixture of Gaussian distributions and analyzing the infinite-width limit.
result Characterization of neural network layers by scalar parameters and Lévy measures, leading to new model limits.
The study analyzes how covariance estimation errors affect the global minimum-variance portfolio under heavy-tailed distributions.
problem The impact of covariance estimation errors on the global minimum-variance portfolio under heavy-tailed distributions.
method Characterization of covariance-estimation error's effect on GMVP suboptimality, derivation of regret identity and bound, application to heavy-tailed returns.
result The decision geometry of GMVP regret is invariant to a (p-1)-dimensional projection of the error matrix, with invariance to the covariance-scale direction as an exact special case.
Unified view of Lion and Muon as Stochastic Frank-Wolfe methods.
problem Optimization of constrained problems in deep learning.
method Interpreting Lion and Muon as Stochastic Frank-Wolfe methods and extending the approach to heavy-tailed noise.
result Convergence guarantees and KKT point convergence for Lion and Muon.
Paper establishes sufficient condition for comparing linear combinations of infinite-mean risks.
problem Comparing linear combinations of infinite-mean risks under stochastic dominance.
method Introduced a new class of distributions and used majorization order to compare weights.
result Linear combinations of random variables are stochastically larger when their weight vectors are smaller in majorization order.
New convergence bounds for online learning with heavy-tailed noise.
problem Learning on streaming data with heavy-tailed noise.
method Nonlinear stochastic gradient descent (SGD) for non-convex and strongly convex costs.
result Strong convergence rates for various nonlinearities and noise distributions.
Study improves ERM for heavy-tailed data with dependent inputs.
problem Empirical Risk Minimization with dependent and heavy-tailed data.
method Extending risk bounds for ERM with heavy-tailed, dependent data.
result Established risk bounds for ERM with dependent and heavy-tailed data.