New model stabilizes asynchronous LTI systems, independent of synchronous stability.
problem Stability of asynchronous LTI systems under randomization and asynchrony.
method Introduced a new model for random asynchronous LTI systems and developed a method for system identification.
result Stability of random asynchronous LTI systems is independent of synchronous stability.
New stability conditions for ZO methods reveal unique regularization effects.
problem Understanding optimization dynamics of ZO methods in deep learning.
method Explicit step size conditions and stability bounds derived for ZO methods.
result ZO methods operate near the edge of stability, with regularization effects specific to Hessian trace vs. eigenvalue.
This paper presents a stochastic behavior analysis of a kernel-based stochastic restricted-gradient descent method. The restricted gradient gives a steepest ascent direction within the so-called dictionary subspace. The analysis provides the transient and steady state performance in the mean squared error criterion. It…
New method reveals insights about stochastic optimization methods using modified equations.
problem Understanding the qualitative behavior of stochastic optimization algorithms.
method Developed a class of stochastic differential equations to approximate the dynamics of stochastic optimization methods.
result Mean-square stability of the modified equation provides qualitative insights about stochastic coordinate descent.
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 (…
Artificial neural network training with stochastic gradient descent can be destabilized by "bad batches" with high losses. This is often problematic for training with small batch sizes, high order loss functions or unstably high learning rates. To stabilize learning, we have developed adaptive learning rate clipping (A…
We study the stability vis a vis adversarial noise of matrix factorization algorithm for matrix completion. In particular, our results include: (I) we bound the gap between the solution matrix of the factorization method and the ground truth in terms of root mean square error; (II) we treat the matrix factorization as …
Paper analyzes robustness of data-selective Volterra NLMS algorithm.
problem Robustness analysis of data-selective Volterra NLMS algorithm.
method The paper analyzes the local robustness and proposes a global bound for the error in the coefficient vector.
result The DS-VNLMS algorithm is robust against noise and improves parameter estimation for most iterations.
WAVE improves stability in reinforcement learning by adaptively weighting critic's loss.
problem Inherent instability in actor-critic reinforcement learning algorithms.
method Wasserstein adaptive value estimation with Sinkhorn approximation.
result Achieves $\mathcal{O}\left(\frac{1}{k}
ight)$ convergence rate for critic's mean squared error.
Layer normalization (LayerNorm) has been successfully applied to various deep neural networks to help stabilize training and boost model convergence because of its capability in handling re-centering and re-scaling of both inputs and weight matrix. However, the computational overhead introduced by LayerNorm makes these…
Paper uses Time Series Transformer for bank stability prediction.
problem Predicting bank stability using complex financial data.
method Time Series Transformer model with self-attention mechanism.
result Time Series Transformer model outperforms other models in MSE and MAE.
New results show flat minima in neural networks suffer from high dimensionality.
problem Flat minima in neural networks generalize poorly in high dimensions.
method Theoretical analysis of two-layer ReLU networks with multivariate inputs.
result Flat minima lead to exponentially slower convergence in high dimensions.
Paper introduces stability in model averaging and proposes a L2-penalty method.
problem Theoretical properties of model averaging from stability perspective.
method Introduces stability, defines asymptotic empirical risk minimizer, and proposes L2-penalty model averaging method.
result Proposed L2-penalty method ensures stability and consistency under reasonable conditions.
New adaptive importance samplers improve stability and accuracy.
problem Improving the stability and accuracy of importance sampling estimators.
method Introducing AdaOAIS, a new adaptive importance sampler using adaptive optimisers to address the instability of OAIS.
result AdaOAIS leads to stable importance sampling estimators in practice.
Risk-aware MMSE improves stability in volatile scenarios.
problem In MMSE estimators, volatility of error is unconstrained, leading to significant performance differences.
method Introduces risk-aware MMSE by constraining expected predictive variance.
result Risk-aware MMSE provides better performance, especially in skewed, heavy-tailed distributions.
This study analyzes AdaGrad's stability and convergence in non-convex optimization.
problem Lack of theoretical analysis for AdaGrad in non-convex optimization.
method Novel stopping time-based techniques from probability theory.
result Established stability and derived convergence rates for AdaGrad.
Gradient filters track moving parameters under noisy data and misspecification.
problem Tracking multidimensional time-varying parameters under noisy observations and model misspecification.
method Gradient-based filters update parameters using the gradient of a postulated objective function, evaluated at either the predicted or updated parameters.
result Novel sufficient conditions for exponential stability of the filtered parameter path, and finite-sample and asymptotic mean squared error bounds.
DEQGAN uses GANs to solve differential equations without supervision.
problem Solving differential equations with neural networks.
method Generative Adversarial Networks (GANs) to learn the loss function.
result DEQGAN achieves lower mean squared errors and competitive solution accuracy compared to traditional methods.
Adaptive filtering algorithms operating in reproducing kernel Hilbert spaces have demonstrated superiority over their linear counterpart for nonlinear system identification. Unfortunately, an undesirable characteristic of these methods is that the order of the filters grows linearly with the number of input data. This …
Identifies bilinear systems from a single trajectory with optimal sample complexity.
problem Learning bilinear systems from a single trajectory of states and inputs.
method Uses a mild marginal mean-square stability assumption and martingale small-ball condition.
result Sample complexity and statistical error rates are optimal.
Double Q-learning has the same mean-squared error as Q-learning under certain conditions.
problem Comparing the mean-squared error of Double Q-learning and Q-learning.
method Theoretical analysis based on Lyapunov equations for both tabular and linear function approximation settings.
result The asymptotic mean-squared error of Double Q-learning is exactly equal to that of Q-learning under specific conditions.
The kernel least mean squares (KLMS) algorithm is a computationally efficient nonlinear adaptive filtering method that "kernelizes" the celebrated (linear) least mean squares algorithm. We demonstrate that the least mean squares algorithm is closely related to the Kalman filtering, and thus, the KLMS can be interpreted…
New activation function BrownianReLU improves LSTM network performance on financial time series.
problem Gradient instability in noisy financial time series data.
method Introduces BrownianReLU, a stochastic activation function based on Brownian motion.
result Significantly improved predictive accuracy and generalization on financial datasets.
A new method for estimating adversarial strategies in nonlinear systems.
problem Inferring an intelligent adversarial agent's strategy in highly nonlinear systems.
method Formulated inverse cognition as a nonlinear Gaussian state-space model and developed an inverse UKF (IUKF) system.
result The estimation error of IUKF converges and closely follows the recursive Cramér-Rao lower bound.
Paper shows ERM's suboptimality due to bias, not variance.
problem Understanding why ERM fails to achieve optimal rates.
method Probabilistic and admissibility proofs for ERM in various settings.
result ERM's suboptimality is due to bias, not variance.
In this work we propose an adversarial learning approach to generate high resolution MRI scans from low resolution images. The architecture, based on the SRGAN model, adopts 3D convolutions to exploit volumetric information. For the discriminator, the adversarial loss uses least squares in order to stabilize the traini…
The paper provides mean-square error bounds for stochastic approximation algorithms.
problem Error bounds for recursive equations with Markovian disturbances.
method Analysis of mean-square error for stochastic approximation algorithms.
result Mean-square error achieves the optimal rate of O(1/n) under certain conditions. 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.
Neural network training is usually accomplished by solving a non-convex optimization problem using stochastic gradient descent. Although one optimizes over the networks parameters, the main loss function generally only depends on the realization of the neural network, i.e. the function it computes. Studying the optimiz…
Machine learning improves American option pricing accuracy.
problem Complexities of American options and traditional models' limitations.
method Monte Carlo simulations combined with machine learning algorithms (Least Square Method, LSTM, GRU).
result GRU model outperforms LSTM in predicting bid prices, enhancing accuracy and stability.
This study calculates the maximum error of a famous estimation method.
problem Estimating rare items not seen in a sample.
method Characterizes the maximal mean-squared error of the Good-Turing estimator.
result Characterizes the maximal mean-squared error of the Good-Turing estimator.
Paper proposes a DNN-driven AF framework for improved generalization.
problem Generalization challenge in adaptive filtering.
method Structural embedding of DNN into AF system, using maximum likelihood as implicit cost function.
result Demonstrates improved generalization capability through extensive experiments.
The paper evaluates company investment value using machine learning models.
problem Evaluating the investment value of companies based on machine learning.
method Data mining, feature selection, cross-validation, stacking model, Bayesian Ridge Regression.
result The RMSE of the final model is 3.047, indicating improved stability and generalization.
We consider adaptive system identification problems with convex constraints and propose a family of regularized Least-Mean-Square (LMS) algorithms. We show that with a properly selected regularization parameter the regularized LMS provably dominates its conventional counterpart in terms of mean square deviations. We es…
Generative adversarial networks (GANs) are highly effective unsupervised learning frameworks that can generate very sharp data, even for data such as images with complex, highly multimodal distributions. However GANs are known to be very hard to train, suffering from problems such as mode collapse and disturbing visual…
New method optimizes tail dependence coefficient estimation.
problem Estimating tail dependence in nonparametric data.
method Optimal threshold selection combining mean squared error and copula estimation.
result Improved accuracy in tail dependence coefficient estimation.
This paper explains CART random forests using stochastic control theory.
problem Understanding the inner workings of CART random forests.
method Developed a stochastic-control perspective on CART random forests, interpreting feature subsampling as a random feasible action set and the split rule as a policy.
result Established that the CART policy is locally stabilizing but globally suboptimal for the forest objective.
Nonparametric modeling approaches show very promising results in the area of system identification and control. A naturally provided model confidence is highly relevant for system-theoretical considerations to provide guarantees for application scenarios. Gaussian process regression represents one approach which provid…
The Matérn covariance function is a popular choice for prediction in spatial statistics and uncertainty quantification literature. A key benefit of the Matérn class is that it is possible to get precise control over the degree of mean-square differentiability of the random process. However, the Matérn class possesses e…
Improved Least-Squares Monte Carlo with finite-difference ansatz.
problem Improving accuracy and stability in option pricing.
method Constructing an ansatz using finite-difference solution for conditional expected continuation payoffs.
result Reduces mean squared error and final pricing error.
Cryptocurrency prices predicted using LSTM, SVM, and polynomial regression.
problem Uncertainty in crypto coin values.
method Long Short Term Memory, Support Vector Machine, Polynomial Regression models.
result Support Vector Machine with linear kernel had the smallest mean square error.
We formulate the problem of neural network optimization as Bayesian filtering, where the observations are the backpropagated gradients. While neural network optimization has previously been studied using natural gradient methods which are closely related to Bayesian inference, they were unable to recover standard optim…
Proposes adversarial method to estimate Riesz representer.
problem Estimating causal parameters as linear functionals of an underlying regression.
method Adversarial framework using general function spaces.
result Nonasymptotic mean square rate proved for neural networks, random forests, and RKHS.
Study on LMMSE estimation with model mismatch, quantifying MSE trade-offs.
problem Model mismatch in LMMSE estimation with undermodeling.
method Analyzing the average MSE of LMMSE estimation with random regressors.
result Performance improvement depends on sufficient samples and model complexity.
A fast method for LOOCV in k-NN regression reduces computation time.
problem Efficient computation of LOOCV for k-NN regression.
method Identical LOOCV estimate to (k+1)-NN MSE on training data.
result LOOCV computation can be done with (k+1)-NN regression once.
Kernel adaptive filters (KAF) are a class of powerful nonlinear filters developed in Reproducing Kernel Hilbert Space (RKHS). The Gaussian kernel is usually the default kernel in KAF algorithms, but selecting the proper kernel size (bandwidth) is still an open important issue especially for learning with small sample s…
New theory shows large learning rates prevent overfitting in neural networks.
problem Generalization of two-layer ReLU neural networks in noisy regression problems.
method Gradient descent with constant learning rate converges to stable minima.
result Gradient descent with large learning rates finds smooth, sparse fits.
New methods for estimating complex causal effects in econometrics.
problem Estimating causal parameters in short panel data models using nested nonparametric instrumental variable regression.
method Introducing techniques to limit ill-posedness in nested NPIV, providing explicit mean square rates and efficient inference.
result Explicit mean square rates for nested NPIV and efficient inference for causal parameters.