We establish large deviation principles for convolutional neural networks.
problem Understanding the behavior of convolutional neural networks in the infinite-channel limit.
method We establish large deviation principles for convolutional neural networks under Gaussian prior and posterior distributions.
result We provide a large deviation principle for the sequence of conditional covariance matrices and the posterior distribution.
Large deviation principle for deep neural networks with ReLU activation.
problem Understanding the behavior of deep neural networks with ReLU activation.
method Proving a large deviation principle for networks with Gaussian weights and ReLU activation functions.
result Simplified expressions and power-series expansions for the ReLU case.
Study large deviations in fractional volatility models with non-Gaussian volatility.
problem Large deviations in fractional volatility models with non-Gaussian volatility.
method Established a small-noise large deviation principle for log-price.
result Logarithmic call price asymptotics for large strikes in a special case.
Study on Gaussian models reveals moment explosions under certain volatility conditions.
problem Understanding the behavior of asset price processes in Gaussian stochastic volatility models.
method Established large and moderate deviation principles, analyzed exit probabilities, and proved moment explosion results.
result If volatility grows faster than linearly, all moments of order greater than one are infinite for asset price processes.
Study volatility models with rough paths, focusing on large deviations and option behavior.
problem Analyzing volatility in financial markets with very rough paths.
method Introduced time-inhomogeneous stochastic volatility models with Volterra Gaussian processes.
result Obtained large deviation principles for log-price processes in super rough Gaussian models.
New private algorithms estimate location parameters with sub-Gaussian deviations.
problem Estimating location parameters with differential privacy and sub-Gaussian deviations for heavy-tailed data.
method Design two private algorithms for estimating the median and mean under differential privacy, showing sub-Gaussian deviations for unbounded random variables.
result Private median and mean estimators achieve sub-Gaussian deviations, unlike non-private counterparts which can have strictly worse deviations.
Pareto's 80/20 rule follows a Gaussian distribution with twice the mean standard deviation.
problem Understanding variations in the 80/20 rule across different contexts.
method Identifying the statistical distribution of the 80/20 rule and its variations.
result The 80/20 rule follows a Gaussian distribution with a standard deviation twice the mean.
The paper provides a finite-sample deviation bound for stable autoregressive processes.
problem Deviation bounds for least squares estimators in Gaussian AR(n) processes.
method Utilizes martingale concentration inequalities and tail-bound for χ² distributed variables.
result Problem-dependent finite-time bound on the deviation probability of AR(n) process parameters.
Study large deviation principle for fractional stochastic volatility models.
problem Large deviation principle for Volterra type fractional stochastic volatility models.
method Prove a small-noise large deviation principle under weaker conditions.
result Derive large deviation principle in small-time regime.
Large deviation principles for multivariate stochastic volatility models.
problem Understanding the behavior of log-processes in multivariate stochastic volatility models.
method Establishing a comprehensive sample path large deviation principle for log-processes.
result Asymptotic formulas for first exit times and barrier option prices derived from the LDP.
Estimates parameters in a deviated Gaussian mixture model.
problem Testing goodness-of-fit between a known function and a mixture of experts.
method Constructs novel Voronoi-based loss functions to estimate parameters.
result Characterizes local convergence rates of parameter estimation more accurately.
Improved median of means estimator with tighter bounds.
problem Improving the efficiency and reliability of median of means estimator.
method Modification of the median of means estimator with sub-Gaussian deviation bounds.
result Achieves nearly optimal constants under minimal assumptions.
Bayesian neural networks explore rare fluctuations for better feature learning.
problem Understanding rare but dominant fluctuations in Bayesian neural networks.
method Large-deviation theory and joint optimization over predictors and internal kernels.
result Posterior rate function optimization reveals data-dependent kernel selection.
The paper provides non-asymptotic Edgeworth expansions for neural network outputs.
problem Approximating deviations of finite-width neural networks from their Gaussian limit.
method Multidimensional Edgeworth expansions of arbitrary order for neural network outputs.
result Established a bound on the total variation distance between neural network output and its Edgeworth approximation.
Analysis of a stochastic system showing convergence to an averaged model with Gaussian deviations.
problem Convergence analysis of a perturbed compositional gradient flow system.
method Separation of scales and averaging principle applied to stochastic differential equations.
result The slow motion of the system can be approximated by a standard perturbed gradient flow or SCGD algorithm.
In this paper, we study the risk bounds for samples independently drawn from an infinitely divisible (ID) distribution. In particular, based on a martingale method, we develop two deviation inequalities for a sequence of random variables of an ID distribution with zero Gaussian component. By applying the deviation ineq…
Sharp bounds for Dirichlet sums lead to improved Bayesian algorithm analysis.
problem Improving Bayesian algorithm performance through precise deviation bounds.
method Novel integral representation of Dirichlet sum density, Gaussian approximation, complex analysis.
result Significantly sharpened regret bounds for Multinomial Thompson Sampling.
The paper examines how SGD noise deviates from Gaussian distribution.
problem Understanding why SGD outperforms GD in neural networks.
method Analysis of SGN vectors' distribution during training.
result For large batch sizes, SGN vectors are mostly Gaussian in early phases.
Autotune optimizes Lasso tuning parameters efficiently and accurately.
problem Efficiently selecting Lasso tuning parameters in high-dimensional models.
method Alternates optimizing regression coefficients and noise standard deviation.
result Autotune outperforms existing methods in low signal-to-noise regimes.
Sparse non-Gaussian component analysis (SNGCA) is an unsupervised method of extracting a linear structure from a high dimensional data based on estimating a low-dimensional non-Gaussian data component. In this paper we discuss a new approach to direct estimation of the projector on the target space based on semidefinit…
Constrained adaptive filtering algorithms inculding constrained least mean square (CLMS), constrained affine projection (CAP) and constrained recursive least squares (CRLS) have been extensively studied in many applications. Most existing constrained adaptive filtering algorithms are developed under mean square error (…
This article provides a new toolbox to derive sparse recovery guarantees from small deviations on extreme singular values or extreme eigenvalues obtained in Random Matrix Theory. This work is based on Restricted Isometry Constants (RICs) which are a pivotal notion in Compressed Sensing and High-Dimensional Statistics a…
Model predicts composite structures assembly quality with input uncertainty.
problem Accurate prediction of dimensional deviations and residual stress in composite structures assembly.
method Neural Network Gaussian Process considering input uncertainty.
result NNGPIU model outperforms other methods for nonsmooth, nonlinear responses.
Study on zeros of Gaussian sections on semipositive line bundles on punctured Riemann surfaces.
problem Distribution of zeros of Gaussian sections on semipositive line bundles.
method Analysis of Bergman kernels and random zeros in high tensor powers.
result Equidistribution, large deviation estimates, central limit theorem, and number variances for zeros in the semi-classical limit.
New method for initializing RBM weights without datasets.
problem No dataset-free weight-initialization for RBMs.
method Statistical mechanical analysis to derive Gaussian distribution with optimized standard deviation.
result Optimal weight initialization improves learning efficiency in RBMs.
Detailed empirical studies of publicly traded business firms have established that the standard deviation of annual sales growth rates decreases with increasing firm sales as a power law, and that the sales growth distribution is non-Gaussian with slowly decaying tails. To explain these empirical facts, a theory is dev…
Sharp large deviations and Gibbs conditioning for portfolio credit risk models.
problem Analyzing the risk of default in financial portfolios with dependent factors.
method Sharp large deviation estimates and conditional Bahadur-Rao estimates for threshold models with diverging latent factors.
result Conditioned on a large exceedance event, default indicators become asymptotically i.i.d., and loss-given-default is exponentially tilted.
MONK improves mean embedding estimation by reducing outlier sensitivity.
problem Outliers severely affect classical mean embedding estimators.
method Uses median-of-means principle to design robust estimators.
result Optimal sub-Gaussian deviation bounds with resistance to outliers.
Bayesian inference for wide neural networks using Edgeworth expansion.
problem Analyzing the non-Gaussian behavior of wide neural networks in Bayesian inference.
method Proposed a non-Gaussian distribution using multivariate Edgeworth expansion for finite-width neural networks.
result Derived non-Gaussian posterior distribution in Bayesian regression tasks.
Study on U-statistics with heavy-tailed samples, providing tail bounds and LDP.
problem Deviation of U-statistics with heavy-tailed samples.
method Exponential tail bounds and Large Deviation Principle (LDP) for U-statistics.
result Obtained an exponential upper bound for U-statistics tail decay, showing two regions of decay.
Bayesian approach predicts brain-age from EEG sleep states across age.
problem Inconsistent brain-age predictions due to subjective sleep state classification.
method Unified Bayesian Network with Gaussian Mixture Models for EEG sleep states.
result Improved accuracy in brain-age prediction over a wider age range.
Risk control and optimal diversification constitute a major focus in the finance and insurance industries as well as, more or less consciously, in our everyday life. We present a discussion of the characterization of risks and of the optimization of portfolios that starts from a simple illustrative model and ends by a …
In a recent paper [\textit{M. Cristelli, A. Zaccaria and L. Pietronero, Phys. Rev. E 85, 066108 (2012)}], Cristelli \textit{et al.} analysed relation between skewness and kurtosis for complex dynamical systems and identified two power-law regimes of non-Gaussianity, one of which scales with an exponent of 2 and the oth…
Proposes a new model for EHR data using time-dependent Gaussian processes.
problem Joint modeling of multiple clinical variables over time.
method Multivariate nonstationary Gaussian processes with time-varying parameters and posterior inference via HMC.
result The proposed model outperforms stationary models and reveals latent correlations predictive of patient risk.
Extends Gaussian process regression for non-Gaussian data.
problem Inadequate modeling of uncertainty and over-smoothing in non-Gaussian datasets.
method Time-changed Gaussian processes with Lévy processes.
result Improved modeling of heavy-tailed non-Gaussian behaviors.
New algorithm reduces sketching dimension to effective problem size.
problem Solving L2-regularized least-squares problems efficiently.
method Randomized algorithm using Gaussian and SRHT embeddings.
result Preserves convergence guarantees with reduced embedding dimension.
Recursive KalmanNet combines neural networks with Kalman filters for precise state estimation.
problem State estimation in systems with noisy measurements and non-Gaussian noise.
method Recursive KalmanNet uses a recurrent neural network to estimate states with consistent error covariance, optimizing for Gaussian negative log-likelihood.
result Recursive KalmanNet outperforms conventional Kalman filters and deep learning-based estimators in non-Gaussian noise conditions.
Annealed Entropic Allocation improves ranking and selection by mitigating hard switching and improving finite-budget discrimination.
problem Sequential budget allocation in ranking and selection
method Annealed weighted soft-min framework
result Surrogate converges uniformly to the hard minimum, soft-min weights concentrate on active challengers, and target allocation map is continuous.
Trading affects grid frequency fluctuations, making them more extreme.
problem Impact of trading on grid frequency stability.
method Analysis of frequency time series from 2011 and 2017.
result Trading modifies frequency fluctuation statistics, making large deviations more likely.
The paper provides bounds for high-dimensional U-statistics with novel order-explicit inequalities.
problem Bounding the deviation of high-dimensional U-statistics from their Hájek projections.
method Develops novel order-explicit moment inequalities for higher-order Hoeffding components.
result The maximum deviation of a high-dimensional U-statistic from its Hájek projection is of order Op(φbn−1log2(dn)). Suppose k centers are fit to m points by heuristically minimizing the k-means cost; what is the corresponding fit over the source distribution? This question is resolved here for distributions with p≥4 bounded moments; in particular, the difference between the sample cost and distribution cost decays with $…
The paper analyzes Asian options in local volatility models at short maturity.
problem Short-maturity pricing and hedging of Asian options in local volatility models.
method Approximation of local volatility model by Gaussian process at short maturity, combined with Malliavin calculus.
result Short-maturity Asian option prices and delta values approximate European counterparts with a specific volatility function.
IPGP framework improves psychological assessment by integrating shared and unique traits.
problem Tackles the debate on shared vs unique personality traits across individuals.
method Uses Gaussian process coregionalization model for non-Gaussian ordinal data, with stochastic variational inference for scalability.
result Improves prediction and estimation of individualized factor structures compared to existing methods.
Detects anomalous patterns in non-independent data streams.
problem Low detection power for subtle, emerging irregularities in non-iid data.
method Combines Gaussian processes with subset scanning techniques.
result Powerful, interpretable methods for anomalous pattern detection.
Introduces Star-Shaped deviation measures for risk analysis.
problem Risk measurement and analysis in finance.
method Characterizes Star-Shaped deviation measures through acceptance sets and convex deviation measures.
result Exposes the relationship between Star-Shaped risk measures and deviation measures.
Bayesian methods improve nuclear mass predictions for unstable nuclei.
problem Improving predictions of nuclear masses far from stability.
method Bayesian Gaussian processes and neural networks applied to 10 models.
result Significant reduction in rms deviation from experimental data.
Proposes a deep model for Bayesian quantile regression without Gaussian assumptions.
problem Uncertainty quantification from single forward-pass models is computationally expensive and restrictive.
method Deep evidential learning for Bayesian quantile regression.
result Achieves calibrated uncertainties on non-Gaussian distributions.
Extends moderate deviations for a randomised Heston model.
problem Analyzing deviations in the Heston model with randomisation.
method Used Gärtner-Ellis theorem and sharp large deviations tools.
result Extended moderate deviations results for the randomised Heston model.