Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

93186278371 · Jun 202019922001200920172026
48 results for entropy robustness

State entropy regularization improves robustness in reinforcement learning, especially under structured perturbations.

problem Structured and spatially correlated perturbations in reinforcement learning.
method State entropy regularization, compared to policy entropy.
result State entropy regularization provides better robustness to structured and spatially correlated perturbations.

Paper introduces robust market making using Wasserstein distance and entropy regularization.

problem Market making robustness under uncertainty.
method Wasserstein distance, entropy regularization, convex optimization, optimal radius selection.
result The robust market making problem can be reformulated as a convex optimization problem.

New method estimates robust multi-period portfolios using entropy.

problem Lack of general agreement on building robust multi-period portfolios.
method Detrended cluster entropy approach to estimate portfolio weights.
result Portfolio weights are estimated reliably from real-world data at varying time horizons.

Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model. Many recent methods have proposed to improve adversarial robustness by utilizing adversarial training or model distillation, which adds additional procedure…

2019-03-23abs ↗pdf ↗

Paper develops a robust HVA measure for dynamic hedging under liquidity stress.

problem Valuation of dynamic hedging under liquidity stress.
method Defines robust HVA as worst-case expected loss over a relative-entropy neighborhood of loss distributions for no-trade bands.
result Wider no-trade bands lower rebalancing costs but increase hedge-error risk.

This work enhances collaborative inference privacy by minimizing conditional entropy and boosting robustness against model inversion attacks.

problem Privacy leakage in collaborative inference systems via model inversion attacks.
method Theoretical proof and derivation of a differentiable measure for bounding conditional entropy, followed by a CEM algorithm to maximize it.
result Theoretical proof and experimental validation show that CEM consistently boosts inversion robustness without compromising feature utility or efficiency.

A new reinforcement learning method reduces action complexity for robust control.

problem Deep reinforcement learning's susceptibility to spurious correlations.
method Minimizing trajectory entropy to encourage simple, predictable actions.
result Trajectory Entropy Reinforcement Learning achieves superior performance and robustness.

In this paper, we propose a general framework to learn a robust large-margin binary classifier when corrupt measurements, called anomalies, caused by sensor failure might be present in the training set. The goal is to minimize the generalization error of the classifier on non-corrupted measurements while controlling th…

2016-10-21abs ↗pdf ↗

EntProp increases entropy of clean samples to generate out-of-distribution data for better DNN performance.

problem Improving deep neural networks' accuracy and robustness to out-of-distribution data.
method High entropy propagation using data augmentation and free adversarial training.
result EntProp achieves higher standard accuracy and robustness with lower training cost.

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

problem Adversarial robustness in multiclass classification with arbitrary loss functions.
method Dual and barycentric reformulations for robust risk minimization.
result Sharp lower bounds for adversarial risks are computed efficiently.

Improves adversarial robustness of DEQ models by regulating neural dynamics.

problem Limited adversarial robustness of DEQ models.
method Interprets DEQs as neural dynamics, uses entropy reduction and random intermediate states.
result Significantly increases adversarial robustness of DEQ models.

Accounting for the non-normality of asset returns remains challenging in robust portfolio optimization. In this article, we tackle this problem by assessing the risk of the portfolio through the "amount of randomness" conveyed by its returns. We achieve this by using an objective function that relies on the exponential…

2017-05-16abs ↗pdf ↗

The minimum error entropy (MEE) criterion has been verified as a powerful approach for non-Gaussian signal processing and robust machine learning. However, the implementation of MEE on robust classification is rather a vacancy in the literature. The original MEE only focuses on minimizing the Renyi's quadratic entropy …

2019-09-06abs ↗pdf ↗

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

problem Training robust deep neural networks requires addressing issues like label noise and low entropy predictions.
method ProSelfLC progressively increases trust in predicted labels over time, considering entropy and learning time.
result ProSelfLC demonstrates improved robustness in both clean and noisy settings through empirical validation.

Theoretical analysis of cross-entropy loss functions and their robustness.

problem Guarantees for using cross-entropy as a surrogate loss function.
method Theoretical analysis of a broad family of loss functions, including cross-entropy.
result First HH-consistency bounds for comp-sum losses and smooth adversarial comp-sum losses.

This paper optimizes trading strategies to minimize risk and maximize profit while accounting for market uncertainty.

problem Optimizing trading strategies to minimize risk and maximize profit while accounting for market uncertainty.
method Relative entropy-regularized robust optimal control problem, modeled as a stochastic differential game.
result Analytical expressions for optimal strategy and trajectory are derived under specific assumptions.

New method prevents entropy collapse in Transformer training, leading to more stable and robust models.

problem Training instability in Transformers, especially in attention layers.
method Spectral normalization with a learned scalar to prevent entropy collapse.
result Prevents entropy collapse, leading to more stable training.

Develops a robust hedging valuation adjustment measure for dynamic hedging under liquidity-demand stress.

problem Dynamic hedging under liquidity-demand stress
method Define robust HVA as the worst-case expected loss over a relative-entropy neighborhood of the loss distribution generated by simulated rebalancing and maturity-unwind trades.
result Distinguishes fixed-radius convention from fixed benchmark-stress convention and shows wider no-trade bands lower rebalancing costs but raise hedge-error risk.

This work improves adversarial robustness by boosting model ensembles with margin maximization.

problem Single models are insufficient for defending against adversarial attacks.
method Margin-boosting approach to learn ensembles with maximum margin.
result Our algorithm outperforms existing ensembling techniques and large models trained end-to-end.

In this paper, we develop the notion of entropy for uniform hypergraphs via tensor theory. We employ the probability distribution of the generalized singular values, calculated from the higher-order singular value decomposition of the Laplacian tensors, to fit into the Shannon entropy formula. We show that this tensor …

2019-12-20abs ↗pdf ↗

We consider the problem of robust optimization within the well-established Bayesian optimization (BO) framework. While BO is intrinsically robust to noisy evaluations of the objective function, standard approaches do not consider the case of uncertainty about the input parameters. In this paper, we propose Noisy-Input …

2020-02-07abs ↗pdf ↗

We introduce Implicit Policy, a general class of expressive policies that can flexibly represent complex action distributions in reinforcement learning, with efficient algorithms to compute entropy regularized policy gradients. We empirically show that, despite its simplicity in implementation, entropy regularization c…

2018-06-10abs ↗pdf ↗

We present the Tamed Cross Entropy (TCE) loss function, a robust derivative of the standard Cross Entropy (CE) loss used in deep learning for classification tasks. However, unlike other robust losses, the TCE loss is designed to exhibit the same training properties than the CE loss in noiseless scenarios. Therefore, th…

2018-10-11abs ↗pdf ↗

The paper shows how policy regularization acts like an adversary to improve robustness.

problem Improving robustness of learned policies in reinforcement learning.
method Using convex duality, the paper characterizes adversarial reward perturbations and provides generalization guarantees.
result Policy regularization acts as an adversary to improve robustness against worst-case reward perturbations.

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

problem Entropy Martingale Optimal Transport problem and its associated optimization problem.
method Combines Entropy Optimal Transport and Martingale Optimal Transport theories, with novel penalization terms and constraints.
result Establishes a nonlinear robust pricing-hedging duality, covering various known robust results.

In this paper, we propose a general framework to learn a robust large-margin binary classifier when corrupt measurements, called anomalies, caused by sensor failure might be present in the training set. The goal is to minimize the generalization error of the classifier on non-corrupted measurements while controlling th…

2015-07-16abs ↗pdf ↗

Entropy Search (ES) and Predictive Entropy Search (PES) are popular and empirically successful Bayesian Optimization techniques. Both rely on a compelling information-theoretic motivation, and maximize the information gained about the argmax\arg\max of the unknown function; yet, both are plagued by the expensive computatio…

2017-03-06abs ↗pdf ↗

New algorithm reduces performance loss in IRL with mismatched transition dynamics.

problem Performance degradation in inverse reinforcement learning due to mismatched transition dynamics.
method Proposed a robust Maximum Causal Entropy (MCE) IRL algorithm leveraging robust reinforcement learning insights.
result Empirically demonstrated stable performance improvement under transition dynamics mismatches.

New research shows flat minima in robust loss landscapes correlate with good adversarial robustness.

problem Adversarial training leads to robust overfitting, poor robust generalization.
method Average- and worst-case metrics to measure flatness in robust loss landscapes.
result Flatness in robust loss landscapes correlates with good adversarial robustness.

MEC improves efficiency and robustness in semi-supervised inference.

problem Efficient inference with limited labeled data and robust uncertainty quantification.
method Machine-Learning-Assisted Generalized Entropy Calibration (MEC) using cross-fitted, calibration-weighted PPI.
result MEC achieves semiparametric efficiency bounds under weaker assumptions and provides near-nominal coverage.

Proposes SOVR loss to improve adversarial robustness by increasing logit margins.

problem Adversarial training's difficulty in robustness against sophisticated attacks.
method Introduces SOVR loss function that switches from cross-entropy to one-vs-the-rest loss for important samples.
result SOVR loss increases logit margins of important samples, improving robustness against Auto-Attack.

Paper finds a new principle for optimizing consumption and wealth using Tsallis entropy.

problem Optimal consumption-investment problem with recursive utility.
method Established connection to quadratic BSDE, derived stochastic maximum principle.
result Proved existence of optimal strategy and analyzed coupled system.

Previous work shows that adversarially robust generalization requires larger sample complexity, and the same dataset, e.g., CIFAR-10, which enables good standard accuracy may not suffice to train robust models. Since collecting new training data could be costly, we focus on better utilizing the given data by inducing t…

2019-05-25abs ↗pdf ↗

We present a new statistical learning paradigm for Boltzmann machines based on a new inference principle we have proposed: the latent maximum entropy principle (LME). LME is different both from Jaynes maximum entropy principle and from standard maximum likelihood estimation.We demonstrate the LME principle BY deriving …

2012-10-19abs ↗pdf ↗

This paper improves test-time adaptation for distribution shifts using confidence maximization and input transformation.

problem Improving deep networks' performance on data shifted from the training distribution.
method Proposes a novel loss function combining confidence maximization and batch-wise entropy maximization with an input transformation module.
result Significantly improves robustness of pretrained networks to corruptions on benchmarks like ImageNet-C.

Training accurate deep neural networks (DNNs) in the presence of noisy labels is an important and challenging task. Though a number of approaches have been proposed for learning with noisy labels, many open issues remain. In this paper, we show that DNN learning with Cross Entropy (CE) exhibits overfitting to noisy lab…

2019-08-16abs ↗pdf ↗