arXiv research

Insider trading is reduced when penalized, affecting expected penalties in a non-monotone way.

In an incomplete Brownian-motion market setting, we propose a convex monotonic pricing functional for nonattainable bounded contingent claims which is compatible with prices for attainable claims. The pricing functional is defined as the convex conjugate of a generalized entropy penalty functional and an interpretation…

A new model CDTM improves text classification by concentrating document topics.

This paper reformulates $F_β$ for better model performance and interpretation.

ProSelfLC improves robustness of deep neural networks by automatically deciding trust in predictions.

New scalable algorithm for non-negative linear regression with entropy-regularized OT loss.

New method detects changes by maximizing cross-entropy, outperforming existing techniques.

Study risk-sensitive market making with entropy regularization for better quote control.

Study optimal reinsurance pricing under model uncertainty for multiple insurers.

Generative AI connects to Schrödinger bridge problems with soft constraints for stability.

Recent contributions have framed linear system identification as a nonparametric regularized inverse problem. Relying on $\ell_2$-type regularization which accounts for the stability and smoothness of the impulse response to be estimated, these approaches have been shown to be competitive w.r.t classical parametric met…

Tree-AMP simplifies inference in complex tree-structured models.

This paper introduces a method to incorporate risk sensitivity in RL using quadratic variation penalties.

A new copula, the checkerboard copula, maximizes entropy and preserves dependence.

A single algebraic identity unifies information-theoretic variational results.

We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to a reparameterization. This space is equipped with a learned probability model, which is used to impose an entropy penalty on the parameter r…

Maximum likelihood estimation of energy-based models is a challenging problem due to the intractability of the log-likelihood gradient. In this work, we propose learning both the energy function and an amortized approximate sampling mechanism using a neural generator network, which provides an efficient approximation o…

The paper sets lower bounds for adversarial robustness in multiclass classification.

Paper introduces ENZ to measure significant coefficients in sparse recovery, improving over classical methods.

Develops a new duality between entropy martingale optimal transport and nonlinear pricing-hedging.

Tree tensor networks balance model complexity and empirical risk for high-dimensional function approximation.

Through the direct study of the analysis estimator we derive oracle inequalities with fast and slow rates by adapting the arguments involving projections by Dalalyan, Hebiri and Lederer (2017). We then extend the theory to the square root analysis estimator. Finally, we focus on (square root) total variation regularize…

We develop a technique based on Malliavin-Bismut calculus ideas, for asymptotic expansion of dual control problems arising in connection with exponential indifference valuation of claims, and with minimisation of relative entropy, in incomplete markets. The problems involve optimisation of a functional of Brownian path…

Detecting and recovering labels in binomial logistic mixtures is challenging due to an information gap.

Learning robot controllers by minimizing a black-box objective cost using Bayesian optimization (BO) can be time-consuming and challenging. It is very often the case that some roll-outs result in failure behaviors, causing premature experiment detention. In such cases, the designer is forced to decide on heuristic cost…

Unsupervised learning with generative adversarial networks (GANs) has proven to be hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to the vanishing gradients problem during the learning process…

There has been a growing interest in mutual information measures due to their wide range of applications in Machine Learning and Computer Vision. In this paper, we present a generalized structured regression framework based on Shama-Mittal divergence, a relative entropy measure, which is introduced to the Machine Learn…

Regularization methods are often employed in deep learning neural networks (DNNs) to prevent overfitting. For penalty based DNN regularization methods, convex penalties are typically considered because of their optimization guarantees. Recent theoretical work have shown that nonconvex penalties that satisfy certain reg…

Paper introduces a new method for risk-sensitive investment management using RL.

We present a coupled Variational Auto-Encoder (VAE) method that improves the accuracy and robustness of the probabilistic inferences on represented data. The new method models the dependency between input feature vectors (images) and weighs the outliers with a higher penalty by generalizing the original loss function t…

Causal inference improves heterophilic graph learning.

One-bit measurements widely exist in the real world, and they can be used to recover sparse signals. This task is known as the problem of learning halfspaces in learning theory and one-bit compressive sensing (1bit-CS) in signal processing. In this paper, we propose novel algorithms based on both convex and nonconvex s…

The paper studies robust risk measures with linear penalties under uncertain distributions.

The use of machine-learning in neuroimaging offers new perspectives in early diagnosis and prognosis of brain diseases. Although such multivariate methods can capture complex relationships in the data, traditional approaches provide irregular (l2 penalty) or scattered (l1 penalty) predictive pattern with a very limited…

New sparse penalty improves biclustering for gene expression data.

New approach avoids excess empirical risk in domain generalization.

We study the problem of estimating high-dimensional regression models regularized by a structured sparsity-inducing penalty that encodes prior structural information on either the input or output variables. We consider two widely adopted types of penalties of this kind as motivating examples: (1) the general overlappin…

A popular heuristic for improved performance in Generative adversarial networks (GANs) is to use some form of gradient penalty on the discriminator. This gradient penalty was originally motivated by a Wasserstein distance formulation. However, the use of gradient penalty in other GAN formulations is not well motivated.…

Curvature penalties improve interpretability of KANs without sacrificing accuracy.

New method reduces bias in sparse Bayesian learning.

We consider a one-period Kyle (1985) framework where the insider can be subject to a penalty if she trades. We establish existence and uniqueness of equilibrium for virtually any penalty function when noise is uniform. In equilibrium, the demand of the insider and the price functions are in general non-linear and remai…

New nonconvex penalty smooths at origin for deep learning.

We study the problem of learning high dimensional regression models regularized by a structured-sparsity-inducing penalty that encodes prior structural information on either input or output sides. We consider two widely adopted types of such penalties as our motivating examples: 1) overlapping group lasso penalty, base…

This work extends entropic optimal transport to non-product reference couplings, focusing on Gaussian cases.

Wasserstein GAN(WGAN) is a model that minimizes the Wasserstein distance between a data distribution and sample distribution. Recent studies have proposed stabilizing the training process for the WGAN and implementing the Lipschitz constraint. In this study, we prove the local stability of optimizing the simple gradien…

UCPO improves diversity in reinforcement learning models, maintaining high accuracy.

Multi-group learners suffer a penalty in transductive learning.

Global minima found for multidimensional scaling with penalties.