This paper optimizes autonomous vehicle controllers using data-driven methods.
problem Designing robust controllers for autonomous vehicles that handle external and internal disturbances.
method Data-driven approach using principal component analysis and time delay neural networks.
result Improved controller performance through a feed-forward compensator.
MTL improves multi-dimensional regression in luminescence sensing.
problem Challenges in modeling multi-dimensional regression problems with classical methods.
method Multi-task learning (MTL) with feed-forward neural networks (FFNNs).
result MTL allows predicting multiple parameters from a single set of measurements.
Perfect tracking control for real-world Euler-Lagrange systems is challenging due to uncertainties in the system model and external disturbances. The magnitude of the tracking error can be reduced either by increasing the feedback gains or improving the model of the system. The latter is clearly preferable as it allows…
The Canonical Regression Quantile method predicts CEO compensation and future performance.
problem Determining fair CEO compensation and its impact on company performance.
method Canonical Regression Quantile method to assess CEO pay and performance.
result The method can predict future CEO performance and distinguish over/underpaid CEOs.
The paper simplifies calculus for semimartingales using multiplicative compensation.
problem Developing a formula for complex-valued semimartingales to simplify stochastic calculus.
method Multiplicative compensation for complex-valued semimartingales.
result The stochastic exponential of complex-valued semimartingales becomes a true martingale after compensation.
Machine learning improves PMD compensation in multiplexed systems.
problem Improving performance in multiplexed systems with PMD.
method Model-based machine learning parameterizing the Manakov-PMD equation.
result Performance close to PMD-free case achieved with hardware-friendly DBP and PMD compensation.
Theoretical analysis of deep neural networks for time series data.
problem Theoretical development for deep neural networks on temporally dependent observations is lacking.
method Established non-asymptotic bounds for prediction error of deep neural networks under mixing-type assumptions.
result Deep neural networks can model non-linear time series data with additional logarithmic factors due to dependence.
New multi-step approach improves fiber nonlinearity compensation efficiency.
problem Fewer steps are traditionally considered better for fiber nonlinearity compensation.
method Carefully designed multi-step machine learning approaches.
result Multi-step approaches lead to better performance-complexity trade-offs.
We propose and study the known-compensation multi-arm bandit (KCMAB) problem, where a system controller offers a set of arms to many short-term players for T steps. In each step, one short-term player arrives to the system. Upon arrival, the player aims to select an arm with the current best average reward and receiv…
Study incentivizes exploration in non-stationary MAB with compensation.
problem Incentivized exploration for non-stationary stochastic bandits with biased feedback.
method Proposed algorithms for abruptly-changing and continuously-changing non-stationary environments.
result Achieves sublinear regret and compensation over time.
New neural network improves MRI reconstruction for non-Cartesian data.
problem Improving MRI reconstruction for non-Cartesian data acquisitions.
method Density-compensated unrolled neural networks.
result Density-compensated unrolled neural networks outperform baselines.
Proposes a new algorithm to reduce communication costs in decentralized training.
problem How to apply error-compensated compression to decentralized training.
method Error-compensated stochastic gradient descent for decentralized training.
result Proposed algorithm outperforms existing methods in communication cost reduction.
The paper analyzes fairness of compensation-based risk-sharing schemes for fund payouts.
problem Fair allocation of payouts in an endowment contingency fund.
method Analyzes two types of administrators and general non-negative loss distributions.
result General conditions for actuarial fairness are provided.
Neural nets trained with linear discriminant initialization converge faster and more accurately.
problem Training feed-forward neural networks efficiently and accurately.
method Initialize first layer weights with linear discriminants.
result Asymptotic higher accuracy and faster convergence.
A machine learning model for PMD compensation in dual-polarization systems.
problem Compensating for polarization-mode dispersion (PMD) in dual-polarization systems.
method Model-based machine learning approach using the split-step Fourier method for the Manakov-PMD equation.
result The model converges to within 1% of peak dB performance after 428 iterations, achieving a 0.30 dB reduction in effective signal-to-noise ratio compared to PMD-free case.
We present a method to compensate statistical errors in the calculation of correlations on asynchronous time series. The method is based on the assumption of an underlying time series. We set up a model and apply it to financial data to examine the decrease of calculated correlations towards smaller return intervals (E…
The study compares feed-forward and attention layers in language models.
problem Understanding the role of feed-forward and attention layers in language models.
method Empirical and theoretical analysis in a synthetic setting.
result Feed-forward layers learn simple distributional associations, while attention layers focus on in-context reasoning.
Extends compactness theory to variable-coefficient pseudo-differential operators on manifolds.
problem Compensated compactness for pseudodifferential operators on vector bundles.
method Establishes a theorem for weakly convergent sequences of sections under a pseudo-differential operator.
result Quadratic form converges in distributional sense under certain conditions.
A new IC-Connection improves disentanglement in conditional GANs.
problem Poor disentanglement of latent variables in conditional GANs.
method Information Compensation Connection (IC-Connection) for disentanglement.
result Our method achieves better disentanglement than state-of-the-art GANs.
This work optimizes reservoir computing models by linking recurrence and non-linear dynamics.
problem Understanding how recurrence and non-linear dynamics in cortical networks contribute to their function.
method Transformed time-continuous, recurrent dynamics into an effective feed-forward structure of linear and non-linear temporal kernels.
result Optimal time-series classifiers can be built from random reservoir networks, demonstrating significant performance gains.
We discuss the pricing of defaultable assets in an incomplete information model where the default time is given by a first hitting time of an unobservable process. We show that in a fairly general Markov setting, the indicator function of the default has an absolutely continuous compensator. Given this compensator we t…
Proposes DC-S3GD for efficient large-scale decentralized neural network training.
problem Training large-scale decentralized neural networks efficiently.
method Decentralized stale-synchronous version of DC-ASGD with gradient correction.
result Achieves state-of-the-art results in training Convolutional Neural Networks.
UDVD uses deep learning to denoise videos without supervision.
problem Lack of clean video data for training deep learning models.
method UDVD is a CNN trained solely on noisy video data, adapting to local motion.
result UDVD performs as well as supervised methods, even with limited training data.
ForecastNet uses a time-variant deep feed-forward neural network for better multi-step-ahead time series forecasting.
problem Time-invariant architectures limit multi-step-ahead forecasting.
method ForecastNet employs a deep feed-forward architecture with time-variant parameters and interleaved outputs.
result ForecastNet outperforms other models on multi-step-ahead time series forecasting tasks.
We present two statistical causes for the distortion of correlations on high-frequency financial data. We demonstrate that the asynchrony of trades as well as the decimalization of stock prices has a large impact on the decline of the correlation coefficients towards smaller return intervals (Epps effect). These distor…
New method adapts without backprop, faster and better.
problem Efficient domain adaptation without source data.
method Computing class prototypes from pre-trained model.
result Significant accuracy improvements over pre-trained model.
Extends weak continuity of Yang-Mills connections to a broader class.
problem Weak compactness of Ω-Yang-Mills connections. method Compensation compactness argument applied to Yang-Mills fields.
result Weak continuity result extended to Ω-Yang-Mills connections. A new method reduces communication in Federated Learning by pulling less often.
problem Reducing communication overhead in Federated Learning.
method Pulling Reduction with Local Compensation (PRLC) for SGD.
result PRLC achieves lower pulling frequency and maintains the same convergence rate as synchronous SGD.
A second order self-adjoint operator Δ=S∂2+U is uniquely defined by its principal symbol S and potential U if it acts on half-densities. We analyse the potential U as a compensating field (gauge field) in the sense that it compensates the action of coordinate transformations on the second derivatives in…
This paper proposed a bias-compensated normalized maximum correntropy criterion (BCNMCC) algorithm charactered by its low steady-state misalignment for system identification with noisy input in an impulsive output noise environment. The normalized maximum correntropy criterion (NMCC) is derived from a correntropy based…
The study proves a theorem on Riemannian manifolds for wedge products of weakly convergent differential forms.
problem Analyzing the limiting behavior of wedge products of weakly convergent differential forms on Riemannian manifolds.
method Formulating and proving compensated compactness theorems for wedge products of differential forms on closed Riemannian manifolds.
result The theorem generalizes the div-curl lemma for vectorfields and applies to critical regularity exponents.
Paper characterizes and constructs universal approximators for neural networks.
problem Limited understanding of universal approximation in neural networks.
method Characterization, representation, construction method, existence result for any universal approximator.
result Improved capabilities of feed-forward architecture to approximate continuous functions.
Integrated gradients are widely employed to evaluate the contribution of input features in classification models because it satisfies the axioms for attribution of prediction. This method, however, requires an appropriate baseline for reliable determination of the contributions. We propose a compensated integrated grad…
Proposes a compensation mechanism for improving individual forecast confidence.
problem Difficult to assess the quality of individual probabilistic forecasts and their utilities.
method Compensation mechanism based on fair bets and online learning.
result The proposed mechanism cannot be exploited and ensures forecasted utility matches actual utility.
In this paper the method of compensated compactness is applied to the problem of isometric immersion of a two dimensional Riemannian manifold with negative Gauss curvature into three dimensional Euclidean space. Previous applications of the method to this problem have required decay of order t−4 in the Gauss curva…
This paper explores how enforcing equivariance constraints limits neural network expressivity and proposes compensatory model size increases.
problem The impact of enforcing equivariance constraints on the expressive power of neural networks.
method Examined 2-layer ReLU networks, analyzed boundary hyperplanes and channel vectors, and constructed upper bounds on model size required for compensation.
result Enforcing equivariance constraints reduces the expressive power of neural networks, but this can be compensated by increasing model size.
A CNN-based method improves DTI of the human heart, compensating for motion.
problem Signal loss due to heart motion in DTI.
method Invertible Wavelet Scattering using CNN.
result Effective motion compensation and improved fiber structures.
New model adds persistent memory to self-attention layers for improved performance.
problem Improving transformer performance by removing feed-forward layers.
method Augmenting self-attention layers with persistent memory vectors.
result The model outperforms standard transformers on language modeling benchmarks.
Efficient neural network optimization reduces costs and improves model performance.
problem High computational costs in optimizing neural networks, especially at scale.
method Introduces self-attentive feed-forward neural units (SAFFU) for efficient optimization.
result Explicit solutions outperform models optimized by backpropagation alone, and further training with backpropagation leads to better optima from smaller data sets.
Edge devices adapt pre-trained models to local data without backpropagation.
problem Adapting pre-trained models to edge devices' local data distributions.
method Feed-forward latent domain adaptation using cross-attention.
result Consistent improvements over ERM baselines and domain-supervised adaptation.
Paper uses neural networks to analyze oil price impact on Iranian stock and industry indices.
problem Impact of oil price volatility on Tehran stock and industry indices.
method Feed-forward neural networks analysis of two periods: sanctions and post-sanctions.
result Neural networks predict stock and industry indices well, showing significant oil price volatility impact.
Paper introduces non-linear discounting models for default compensation and climate valuation.
problem Valuation of non-replicable value and damage under default risk.
method Develops two models: one for risk-neutralising discounting and another for survival probability dependent discounting.
result Non-decaying discount factors (negative discount rates) are possible under certain scenarios.
We present a compensated compactness theorem in Banach spaces established recently, whose formulation is originally motivated by the weak rigidity problem for isometric immersions of manifolds with lower regularity. As a corollary, a geometrically intrinsic div-curl lemma for tensor fields on Riemannian manifolds is ob…
Survey on recent developments in isometric immersions using PDE techniques.
problem Analyzing isometric immersions with low Sobolev regularity.
method Compensated compactness and Coulomb-Uhlenbeck gauges.
result Weak continuity and stability of Gauss-Codazzi-Ricci equations.
Basic binary relations such as equality and inequality are fundamental to relational data structures. Neural networks should learn such relations and generalise to new unseen data. We show in this study, however, that this generalisation fails with standard feed-forward networks on binary vectors. Even when trained wit…
The paper proves weak continuity of Cartan structural system on semi-Riemannian manifolds with lower regularity.
problem Weak continuity of the Cartan structural system on semi-Riemannian manifolds with lower regularity.
method Formulated and proved a geometric compensated compactness theorem, deduced Lp weak continuity of the Cartan structural system. result Weak continuity of the Cartan structural system and Gauss-Codazzi-Ricci system on semi-Riemannian manifolds with lower regularity.
Study proposes framework for cyber bonds to compensate cyber attack losses.
problem Cyber risk treatment in finance industry.
method Developed a framework, used publicly available data to determine loss distribution parameters, numerically simulated bond price and characteristics, considered two coupon calculation approaches.
result Numerical simulations of cyber bond price, yield, and characteristics.
Compensation methods correct overestimation of adversarial robustness in neural networks.
problem Overestimation of adversarial robustness using first-order attack methods.
method Proposed compensation methods address inaccurate gradient computation and reduce backpropagations.
result Empirical evaluation of adversarial robustness is improved with these methods.