A new method matches measures across different spaces using cost-regularized optimal transport.
problem Matching measures in different spaces without aligned data.
method Cost-regularized optimal transport formulation to match measures across two Euclidean spaces.
result Demonstrated applicability to single-cell spatial transcriptomics/multiomics matching tasks.
New interpretation of OT regularization as adversarial ground cost.
problem Optimal transport (OT) regularization for machine learning.
method Using Fenchel duality, interpret convex OT regularization as adversarial ground cost.
result Access to a robust dissimilarity measure on the ground space.
Predictive models are finding an increasing number of applications in many industries. As a result, a practical means for trading-off the cost of deploying a model versus its effectiveness is needed. Our work is motivated by risk prediction problems in healthcare. Cost-structures in domains such as healthcare are quite…
CR-UOT improves matching of heterogeneous single-cell omics profiles.
problem Matching nonnegative finite Radon measures across heterogeneous spaces.
method Cost-regularized unbalanced optimal transport (CR-UOT) framework.
result CR-UOT improves alignment of heterogeneous single-cell omics profiles.
New method synthesizes and analyzes probability measures using entropy-regularized optimal transport.
problem Synthesize and analyze probability measures with entropy-regularized optimal transport.
method Entropy-regularized Wasserstein-2 cost and Sinkhorn divergence for synthesis and analysis.
result Computed barycentric coefficients and their stability for classification of corrupted point cloud data.
Study on regularity of optimal transport maps on convex domains with quadratic cost.
problem Regularity of optimal transport maps between convex domains with quadratic cost.
method Analysis of Cα-densities and C1,α boundary conditions, monotonicity formula for optimal transport maps. result Proves C1,1−ε-regularity for nondegenerate Cα-densities and C2,α-regularity for C1,α boundary. We investigate the use of entropy-regularized optimal transport (EOT) cost in developing generative models to learn implicit distributions. Two generative models are proposed. One uses EOT cost directly in an one-shot optimization problem and the other uses EOT cost iteratively in an adversarial game. The proposed gene…
Enhances neural network regularization with no extra cost.
problem Improving neural network robustness and generalization.
method Train an ensemble of weight matrices with stochastic regularization and explicitly average outputs.
result Consistent improvement on various image classification tasks.
We propose an algorithm for exploring the entire regularization path of asymmetric-cost linear support vector machines. Empirical evidence suggests the predictive power of support vector machines depends on the regularization parameters of the training algorithms. The algorithms exploring the entire regularization path…
FedElasticNet reduces communication costs and handles client drift in FL.
problem Expensive communication costs and client drift issues in federated learning.
method Leverages elastic net regularizers to sparsify local updates and limit client drift.
result FedElasticNet effectively resolves communication cost and client drift problems.
Develops a distributed strategy for Pareto optimization of aggregate costs with smoothed regularizers.
problem Optimizing aggregate costs with non-smooth regularizers in a network of agents.
method Distributed strategy using infimal convolution to smooth regularizers, seeking Pareto optimal solution via diffusion.
result Pareto solution of smoothed problem can be made arbitrarily close to original non-smooth problem.
Study optimal execution in a transient price impact model with multiple traders.
problem Optimal execution among multiple traders with transient price impact.
method Analyzed N-player optimal execution games in an Obizhaeva--Wang model with and without regularization. Derived equilibrium solutions and explained their behavior. result Existence of equilibrium restored with a specific time-dependent cost on block trades, and equilibrium is tractable.
This paper explores how entropic regularization improves Wasserstein estimators' performance.
problem Improving the approximation and estimation properties of Wasserstein estimators.
method Entropic regularization of optimal transport costs to smooth Wasserstein estimators.
result Entropic regularization can achieve comparable statistical performance to un-regularized estimators at lower computational cost.
This work proposes a way to align statistical modeling with decision making. We provide a method that propagates the uncertainty in predictive modeling to the uncertainty in operational cost, where operational cost is the amount spent by the practitioner in solving the problem. The method allows us to explore the range…
This work introduces methods to compute optimal Monge maps and learn elastic costs for efficient data mapping.
problem Efficiently mapping one probability distribution to another using elastic costs.
method Proposes numerical methods to compute optimal Monge maps and a learning loss for parameterized regularizers.
result Proves the optimality of computed Monge maps and learns the parameters of elastic costs.
Study optimal transport for robust optimization, showing how adversary's strategy relates to regularization.
problem Optimizing under uncertain parameters with a fictitious adversary reshaping a reference distribution.
method Introduces optimal transport and regularization to relate robustification to variation and Lipschitz norms.
result Conditions for existence and computability of Nash equilibrium between decision-maker and adversary.
We propose an inference method to estimate sparse interactions and biases according to Boltzmann machine learning. The basis of this method is L1 regularization, which is often used in compressed sensing, a technique for reconstructing sparse input signals from undersampled outputs. L1 regularization impedes the …
Reducing ICD-10 code granularity improves cost model accuracy and stability.
problem High-dimensional regression with ICD-10 codes leads to unstable coefficient estimates.
method Log-linear analytics approach to cost model regularization through diagnostic code merging.
result Reducing ICD-10 code granularity from 7 characters to 6 or fewer improves model interpretability and consistency.
New method for training deep neural networks with regularization, converging to better generalization.
problem Improving generalization of deep neural networks through explicit regularization.
method Regularizer Mirror Descent (RMD) method, inspired by convergence properties of stochastic mirror descent (SMD).
result RMD converges to a point close to the minimizer of the cost function, leading to better generalization performance.
We consider so-called regular invertible Gaussian Volterra processes and derive a formula for their prediction laws. Examples of such processes include the fractional Brownian motions and the mixed fractional Brownian motions. As an application, we consider conditional-mean hedging under transaction costs in Black-Scho…
Optimal ridge regularization computed iteratively from generative parameters.
problem Finding the optimal ridge regularization strength for linear regression.
method Iterative procedure to compute optimal regularization strength numerically.
result The proposed procedure attains near-optimal generalization across various conditions.
Designs a neural network to reduce training cost by mapping to higher dimensions.
problem High training cost in neural networks.
method Maps feature vectors to higher dimensional space, designs weight matrices to reduce cost, uses convex constraints.
result Reduces training cost as the number of layers increases, without cross-validation.
We consider the problem of selecting the best estimator among a family of Tikhonov regularized estimators, or, alternatively, to select a linear combination of these regularizers that is as good as the best regularizer in the family. Our theory reveals that if the Tikhonov regularizers share the same penalty matrix wit…
Optimizes neural networks with blackbox solvers using Time-cost Regularization.
problem Improving neural network performance by integrating efficient solvers for complex problems.
method Optimizes both the primary loss function and the performance of the blackbox solver using Time-cost Regularization. Introduces a hyper-blackbox concept to learn blackbox parameters.
result Significant improvement in neural network performance through optimization of blackbox solvers.
New algorithm reduces online hyperparameter optimization costs.
problem High cost of evaluating validation examples in online HPO.
method Modeling online HPO as a time-varying Bayesian optimization problem, proposing a costly feedback setting.
result Cost-efficient GP-UCB algorithm reaches human expert-level performance.
Study optimal transport on globally hyperbolic spacetimes, focusing on weak Kantorovich potentials' regularity.
problem Investigate regularity of weak Kantorovich potentials on globally hyperbolic spacetimes.
method Apply insights from Riemannian and Lorentzian cases to study π-solutions. result Conclude existence, uniqueness, and structure of optimal transport maps.
We give sufficient conditions on initial and target measures supported on the sphere §n to ensure the solution to the optimal transport problem with the cost ∣x−y∣2/2 is a diffeomorphism.
Researchers analyze inverse optimal transport, deriving theoretical and empirical insights.
problem Understanding the inverse problem of inferring cost matrices from optimal couplings.
method Formalized and analyzed using entropy-regularized optimal transport, with theoretical and empirical contributions.
result Characterization of the manifold of cross-ratio equivalent costs and derivation of an MCMC sampler.
In this paper the regularity of optimal transportation potentials defined on round spheres is investigated. Specifically, this research generalises the calculations done by Loeper, where he showed that the strong (A3) condition of Trudinger and Wang is satisfied on the round sphere, when the cost-function is the geodes…
Pruning filters in neural networks improves performance and reduces costs.
problem Large neural networks have high inference costs and limited resource usage.
method Batch Bridgeout for efficient pruning of convolutional filters.
result Batch Bridgeout trained networks achieve higher accuracy across various pruning intensities.
A new ICA method adds L1-regularization for better interpretability of fMRI data.
problem Improving interpretability of ICA features in high-dimensional fMRI data.
method L1-regularization added to ICA cost function, solved by DCA.
result Validated on synthetic and real fMRI data, improving feature interpretability.
Study on convergence rates for optimal transport with regularization.
problem Convergence analysis of divergence-regularized optimal transport.
method Novel methodology using quantization and martingale couplings.
result Sharp rates for various divergences and transport costs.
Study non-Gaussian measures' concentration properties in metric spaces.
problem Concentration properties for non-linear Gaussian functionals with non-Gaussian tails.
method Prove generalised Transportation-Cost Inequalities (TCIs) for specific functionals.
result Extended TCIs for rough volatility and Parabolic Anderson Model.
Study statistical guarantees for DRO with OT and OT-regularized divergences.
problem Enhancing adversarial robustness in machine learning models.
method Derive concentration inequalities for supervised learning via DRO-based adversarial training.
result First to cover soft-constraint costs and reweighting mechanisms in adversarial training.
Study one-shot strategic classification under unknown costs, improving worst-case accuracy.
problem Learning robust decision rules in strategic settings with unknown user costs.
method Formal study of one-shot strategic classification, framing as a minimax problem, designing efficient algorithms for full-batch and stochastic settings.
result Proves efficient algorithms converge to minimax solution, revealing dual norm regularization's value.
Artificial neural networks (ANNs) may not be worth their computational/memory costs when used in mobile phones or embedded devices. Parameter-pruning algorithms combat these costs, with some algorithms capable of removing over 90% of an ANN's weights without harming the ANN's performance. Removing weights from an ANN i…
We theoretically and empirically study portfolio optimization under transaction costs and establish a link between turnover penalization and covariance shrinkage with the penalization governed by transaction costs. We show how the ex ante incorporation of transaction costs shifts optimal portfolios towards regularized …
In-network distributed estimation of sparse parameter vectors via diffusion LMS strategies has been studied and investigated in recent years. In all the existing works, some convex regularization approach has been used at each node of the network in order to achieve an overall network performance superior to that of th…
A l1-norm penalized orthogonal forward regression (l1-POFR) algorithm is proposed based on the concept of leaveone- out mean square error (LOOMSE). Firstly, a new l1-norm penalized cost function is defined in the constructed orthogonal space, and each orthogonal basis is associated with an individually tunable regulari…
Extends super-replication theorem with dynamic strategies and transaction costs.
problem Dynamic super-replication under proportional transaction costs.
method Generalizes admissible strategies and defines a well-defined super-replication price process.
result Well-defined super-replication price process in dynamic setting.
SOS programming verifies MTW tensor non-negativity for optimal transport maps.
problem Verifying MTW tensor non-negativity for general cost functions is difficult.
method Sum-of-Squares (SOS) programming for verifying and approximating MTW non-negativity.
result SOS programming provides certificates and approximations of MTW non-negativity.
The paper optimizes portfolios with transaction costs in a large asset universe.
problem Optimizing portfolios with transaction costs in a large asset universe.
method Mean-variance optimization with nonconvex penalty for proportional and quadratic transaction costs.
result The proposed models show satisfactory performance and highlight the importance of transaction costs.
QMME balances cost and speed in convex optimization.
problem Slow convergence of first-order methods and high cost of second-order methods.
method Minimizing quadratic majorants with fixed curvature at each iteration.
result QMME framework achieves sequential convergence under standard assumptions.
Consider transportation of one distribution of mass onto another, chosen to optimize the total expected cost, where cost per unit mass transported from x to y is given by a smooth function c(x,y). If the source density f^+(x) is bounded away from zero and infinity in an open region U' \subset R^n, and the target densit…
We obtain a constructive criterion for robust no-arbitrage in discrete-time market models with transaction costs. This criterion is expressed in terms of the supports of the regular conditional upper distributions of the solvency cones. We also consider the model with a bank account. A method for construction of arbitr…
We consider an investor with constant absolute risk aversion who trades a risky asset with general Ito dynamics, in the presence of small proportional transaction costs. Kallsen and Muhle-Karbe (2012) formally derived the leading-order optimal trading policy and the associated welfare impact of transaction costs. In th…
This article addresses regularity of optimal transport maps for cost="squared distance" on Riemannian manifolds that are products of arbitrarily many round spheres with arbitrary sizes and dimensions. Such manifolds are known to be non-negatively cross-curved [KM2]. Under boundedness and non-vanishing assumptions on th…
The paper compares traditional regression with modern neural network methods for financial hedging and risk compression.
problem Finding optimal hedge ratios and managing portfolio risk using traditional regression methods has limitations.
method The paper introduces regularization techniques and common factor analyses using neural networks to improve upon regression methods.
result Neural network methods provide better performance in hedge ratio estimation and risk compression compared to traditional regression.