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

count % of corpus

48 results for “Adversarial Losses”

Adversarial Weight Perturbation Helps Robust Generalizationcs.LG

AWP improves robustness by flattening weight loss landscape.

problem Improving robustness of deep neural networks against adversarial examples.

method Explicitly regularizes the flatness of weight loss landscape through adversarial weight perturbation.

result AWP forms a double-perturbation mechanism in adversarial training, leading to flatter weight loss landscape.

Adversarial Training Robustness Weight Perturbation Flatness Deep Learning

2020-04-13abs ↗pdf ↗

Adversarial Training Makes Weight Loss Landscape Sharper in Logistic Regressionstat.ML

Adversarial training makes logistic regression weight loss landscapes sharper.

problem Understanding why adversarial training sharpens the weight loss landscape in logistic regression.

method Theoretical analysis of linear logistic regression model with L2 norm constraints, and experiments on ResNet18.

result Adversarial training sharpens the weight loss landscape in linear logistic regression models.

adversarial training logistic regression weight loss landscape sharpness noise alignment

2021-02-05abs ↗pdf ↗

Adversarial Consistency and the Uniqueness of the Adversarial Bayes Classifiercs.LG

Adversarial consistency depends on the uniqueness of adversarial Bayes classifiers.

problem Consistency of adversarial surrogate losses is not guaranteed.

method Connected consistency of adversarial surrogate losses to the uniqueness of adversarial Bayes classifiers.

result A convex surrogate loss is statistically consistent for adversarial learning if and only if the adversarial Bayes classifier is unique.

adversarial learning surrogate losses Bayes classifiers consistency uniqueness

2024-04-26abs ↗pdf ↗

Calibrated Surrogate Losses for Adversarially Robust Classificationstat.ML

This research analyzes the consistency of convex and nonconvex surrogate losses for adversarially robust classification.

problem Ensuring classifiers are robust to adversarial perturbations.

method Analysis of convex and nonconvex surrogate losses through the lens of calibration.

result No convex surrogate loss is calibrated with respect to the adversarial 0-1 loss for linear models, but nonconvex losses can be calibrated under certain conditions.

Adversarial robustness Calibration Surrogate losses Convex optimization Nonconvex optimization

2020-05-28abs ↗pdf ↗

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Themcs.LG

Analyzes adversarial training's impact on loss landscape, proposing PAS to improve model performance.

problem Challenges in optimizing models under adversarial training due to loss landscape properties.

method Analytical studies of adversarial loss functions, numerical analyses, PAS strategy.

result Adversarial training impairs optimization, but PAS strategy improves model performance.

adversarial training loss landscape optimization PAS machine learning

2020-06-15abs ↗pdf ↗

Lower Bounds on Adversarial Robustness for Multiclass Classification with General Loss Functionscs.LG

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.

adversarial robustness multiclass classification arbitrary loss functions lower bounds robust risk minimization

2025-10-02abs ↗pdf ↗

Non-Asymptotic Bounds for Adversarial Excess Risk under Misspecified Modelsstat.ML

Study non-asymptotic bounds for robust estimators under misspecified models.

problem Evaluate performance of robust estimators under adversarial conditions.

method Propose a general approach to adversarial risk analysis, including investigations on generalization and approximation errors.

result Establish non-asymptotic upper bounds for adversarial excess risk under Lipschitz loss functions.

Adversarial Risk Robust Estimation Misspecified Models Generalization Error Approximation Error

2023-09-02abs ↗pdf ↗

On Output Activation Functions for Adversarial Losses: A Theoretical Analysis via Variational Divergence Minimization and An Empirical Study on MNIST Classificationcs.LG

Recent years have seen adversarial losses been applied to many fields. Their applications extend beyond the originally proposed generative modeling to conditional generative and discriminative settings. While prior work has proposed various output activation functions and regularization approaches, some open questions …

2019-01-25abs ↗pdf ↗

Cross-Entropy Loss Functions: Theoretical Analysis and Applicationscs.LG

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

H

-consistency bounds for comp-sum losses and smooth adversarial comp-sum losses.

cross-entropy loss functions theoretical analysis consistency bounds adversarial robustness

2023-04-14abs ↗pdf ↗

On the transferability of adversarial examples between convex and 01 loss modelscs.LG

The paper explores transferability of adversarial examples between convex and 01 loss models, finding non-transferability due to different decision boundaries caused by outliers.

problem Transferability of adversarial examples between convex and 01 loss models.

method Empirical study of transferability between linear 01 loss and convex (hinge) loss models, and between neural networks with different activation functions.

result Adversarial examples are non-transferable between convex and 01 loss models due to different decision boundaries caused by outliers.

adversarial examples transferability convex loss 01 loss outliers

2020-06-14abs ↗pdf ↗

Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustnesscs.LG

Proposes using mode connectivity to improve adversarial robustness of neural networks.

problem Improving adversarial robustness of deep neural networks.

method Employing mode connectivity in loss landscapes to study adversarial robustness and propose methods for improvement.

result Path connection learned using limited bonafide data can effectively mitigate adversarial effects while maintaining original accuracy.

mode connectivity loss landscapes adversarial robustness deep neural networks adversarial attacks

2020-04-30abs ↗pdf ↗

Bridging Adversarial Robustness and Gradient Interpretabilitycs.LG

Adversarial training is a training scheme designed to counter adversarial attacks by augmenting the training dataset with adversarial examples. Surprisingly, several studies have observed that loss gradients from adversarially trained DNNs are visually more interpretable than those from standard DNNs. Although this phe…

2019-03-27abs ↗pdf ↗

Smoothness Analysis of Adversarial Trainingcs.LG

Smoothness analysis of adversarial training reveals $L_\infty$ constraints cause more non-smoothness.

problem Non-smoothness of adversarial training loss function.

method Analyzed the smoothness of adversarial training loss function using optimal attacks for model parameters.

result The

L_\infty

constraint causes more non-smoothness than

L_2

constraint.

adversarial training smoothness non-smoothness Lipschitz continuity EntropySGD

2021-03-02abs ↗pdf ↗

Towards adversarial robustness with 01 loss neural networkscs.LG

01 loss neural network improves adversarial robustness on CIFAR10.

problem Improving machine learning models' resistance to adversarial attacks.

method Proposes a single hidden layer 01 loss neural network trained with stochastic coordinate descent.

result 01 loss network has the largest adversarial distortion compared to other models.

adversarial robustness 01 loss neural networks CIFAR10 adversarial attacks

2020-08-20abs ↗pdf ↗

No-Regret Online Reinforcement Learning with Adversarial Losses and Transitionscs.LG

New algorithms achieve no-regret learning even with adversarial transitions and losses.

problem No-regret learning impossible with adversarial transitions and losses.

method Developed algorithms for adversarial Markov Decision Processes with smooth regret increase.

result Achieved

\widetilde{O}(\sqrt{T} + C^{ extsf{P}})

regret, with

C^{ extsf{P}}

measuring adversarial transition function.

Reinforcement Learning Online Learning Adversarial Markov Decision Processes No-Regret Adversarial Losses

2023-05-27abs ↗pdf ↗

Improved Algorithms for Adversarial Bandits with Unbounded Lossesstat.ML

Two new algorithms improve performance in adversarial bandits with unbounded losses.

problem Adversarial Multi-Armed Bandits with unbounded losses.

method Developed UMAB-NN and UMAB-G for non-negative and general unbounded losses respectively.

result UMAB-NN achieves the first adaptive and scale-free regret bound for non-negative unbounded losses.

Adversarial Bandits Unbounded Losses Regret Bound Non-negative Losses General Losses

2023-10-03abs ↗pdf ↗

Calibration and Consistency of Adversarial Surrogate Lossescs.LG

Study on calibration and consistency of adversarial surrogate losses.

problem Designing robust classifiers with theoretical guarantees.

method Extensive analysis of H-calibration and H-consistency of adversarial surrogate losses.

result Some convex loss functions and supremum-based convex losses are not H-calibrated for important hypothesis sets.

Adversarial robustness Surrogate losses H-calibration H-consistency Generalized linear models

2021-04-19abs ↗pdf ↗

Consistent Robust Adversarial Prediction for General Multiclass Classificationstat.ML

We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case conditional label distributions (the adversarial distributions) that (approximately) m…

2018-12-18abs ↗pdf ↗

On Achieving Optimal Adversarial Test Errorcs.LG

Adversarial training achieves optimal test error for shallow networks.

problem Achieving optimal adversarial test error for general data distributions.

method Applying new Rademacher complexity bounds and properties of optimal adversarial predictors.

result Adversarial training can achieve optimal adversarial test error for general data distributions.

adversarial training optimal test error shallow networks Rademacher complexity optimal adversarial predictors

2023-06-13abs ↗pdf ↗

Adversarially Robust Learning via Entropic Regularizationcs.LG

New algorithm ATENT improves adversarial robustness in neural networks.

problem Improving neural network robustness against adversarial attacks.

method Proposes a new loss function with entropic regularization for training robust neural networks.

result ATENT achieves competitive robust classification accuracy on benchmark datasets.

adversarial robustness deep learning entropic regularization neural networks robustness

2020-08-27abs ↗pdf ↗

Relating Adversarially Robust Generalization to Flat Minimacs.LG

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.

Adversarial Training Robust Generalization Flat Minima Robust Loss Landscape Overfitting

2021-04-09abs ↗pdf ↗

Hellinger loss function for Generative Adversarial Networksstat.ML

Proposes new loss functions for GANs to improve estimation accuracy and robustness.

problem Improving the training of GANs to achieve more accurate and robust models.

method Introduces Hellinger-type loss functions and analyzes their statistical properties.

result Demonstrates improved estimation accuracy and robustness of the proposed loss functions.

Generative Adversarial Networks Hellinger distance Loss functions Robustness Estimation accuracy

2025-12-13abs ↗pdf ↗

Perturbation Analysis of Gradient-based Adversarial Attackscs.LG

This paper analyzes adversarial attacks methods and their effectiveness.

problem Understanding the effectiveness and theoretical properties of adversarial attacks.

method Comparative and formal analysis of loss functions of three adversarial attack methods.

result The Iterative Fast Gradient Sign attack is the slowest in creating adversarial examples.

adversarial attacks loss functions L-BFGS attack Iterative Fast Gradient Sign attack Carlini & Wagner's attack

2020-06-02abs ↗pdf ↗

Nonparametric Density Estimation under Adversarial Lossesmath.ST

We study minimax convergence rates of nonparametric density estimation under a large class of loss functions called "adversarial losses", which, besides classical $\mathcal{L}^p$ losses, includes maximum mean discrepancy (MMD), Wasserstein distance, and total variation distance. These losses are closely related to the …

2018-05-22abs ↗pdf ↗

Understanding Adversarial Robustness Through Loss Landscape Geometriescs.LG

The pursuit of explaining and improving generalization in deep learning has elicited efforts both in regularization techniques as well as visualization techniques of the loss surface geometry. The latter is related to the intuition prevalent in the community that flatter local optima leads to lower generalization error…

2019-07-22abs ↗pdf ↗

Expressive Losses for Verified Robustness via Convex Combinationscs.LG

New expressive losses improve adversarial robustness without sacrificing accuracy.

problem Training networks for robustness at the expense of accuracy.

method Formalizing expressivity, using convex combinations of adversarial attacks and IBP bounds.

result Trivial expressive losses yield state-of-the-art results in various settings.

adversarial robustness expressive losses convex combinations worst-case loss robustness-accuracy trade-offs

2023-05-23abs ↗pdf ↗

Towards Calibrated Losses for Adversarial Robust Reject Option Classificationcs.LG

This paper characterizes and designs loss functions for robust classification with abstention.

problem Ensuring robustness against adversarial attacks and knowing when to abstain from prediction.

method Proposes adversarial robust reject option loss and characterizes surrogates for calibration.

result Shifted Double Ramp Loss and Shifted Double Sigmoid Loss satisfy the calibration conditions.

Adversarial Robustness Reject Option Calibration Loss Functions Robust Classification

2024-10-14abs ↗pdf ↗

Improving the Robustness of Deep Neural Networks via Adversarial Training with Triplet Losscs.LG

Recent studies have highlighted that deep neural networks (DNNs) are vulnerable to adversarial examples. In this paper, we improve the robustness of DNNs by utilizing techniques of Distance Metric Learning. Specifically, we incorporate Triplet Loss, one of the most popular Distance Metric Learning methods, into the fra…

2019-05-28abs ↗pdf ↗

One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Trainingcs.LG

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.

adversarial training robustness logit margins one-vs-the-rest loss Auto-Attack

2022-07-21abs ↗pdf ↗

Boosting Adversarial Robustness From The Perspective of Effective Margin Regularizationcs.LG

The paper proposes effective margin regularization to improve adversarial robustness in deep neural networks.

problem Adversarial vulnerability of deep neural networks (DNNs).

method Regularization of effective weight norm during training to maximize effective margins.

result Effective margin regularization (EMR) boosts adversarial robustness in both standard and adversarial training.

Adversarial robustness Deep neural networks Effective margin Regularization Margin maximization

2022-10-11abs ↗pdf ↗

Building Robust Ensembles via Margin Boostingcs.LG

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.

adversarial robustness margin-boosting ensemble learning cross-entropy loss state-of-the-art techniques

2022-06-07abs ↗pdf ↗

A Likelihood-Based Generative Approach for Spatially Consistent Precipitation Downscalingphysics.ao-ph

New approach combines likelihood and adversarial losses for better precipitation predictions.

problem Spatially inconsistent precipitation projections from likelihood-based models.

method Fuses likelihood-based and adversarial losses for generative models.

result Improves spatial consistency in precipitation downscaling.

precipitation downscaling likelihood-based adversarial losses generative models

2024-06-26abs ↗pdf ↗

Adversarial Risk via Optimal Transport and Optimal Couplingscs.LG

Modern machine learning algorithms perform poorly on adversarially manipulated data. Adversarial risk quantifies the error of classifiers in adversarial settings; adversarial classifiers minimize adversarial risk. In this paper, we analyze adversarial risk and adversarial classifiers from an optimal transport perspecti…

2019-12-05abs ↗pdf ↗

ATRO: Adversarial Training with a Rejection Optioncs.LG

Framework to mitigate adversarial attacks by allowing classifiers to abstain.

problem Vulnerability of classifiers to adversarial examples.

method Adversarial training with a rejection option.

result ATRO framework improves classifier reliability against adversarial attacks.

adversarial training rejection option adversarial attacks machine learning classification

2020-10-24abs ↗pdf ↗

Improved robustness to adversarial examples using Lipschitz regularization of the losscs.LG

We augment adversarial training (AT) with worst case adversarial training (WCAT) which improves adversarial robustness by 11% over the current state-of-the-art result in the $\ell_2$ norm on CIFAR-10. We obtain verifiable average case and worst case robustness guarantees, based on the expected and maximum values of the…

2018-10-01abs ↗pdf ↗

Adversarially robust generalization theory via Jacobian regularization for deep neural networksstat.ML

This study connects Jacobian regularization to adversarial robustness and improves generalization.

problem Adversarial attacks make deep neural networks vulnerable.

method Developed a connection between Jacobian regularization and adversarial training, and established robust generalization gaps.

result Jacobian norms are related to both standard and robust generalization.

adversarial robustness deep learning jacobian regularization generalization adversarial attacks

2024-12-17abs ↗pdf ↗

Robust Upper Bounds for Adversarial Trainingcs.LG

New method improves adversarial training robustness.

problem Lack of tight upper bounds for adversarial training.

method Holistic expansion of the network for upper bound minimization.

result RUB and aRUB methods are more robust than state-of-the-art methods.

adversarial training robust optimization deep learning security guarantees upper bounds

2021-12-17abs ↗pdf ↗

A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Predictionscs.CR

Adversarial tweets can fool stock prediction models, causing financial loss.

problem Vulnerability of stock prediction models to adversarial attacks on social media.

method Solving combinatorial optimization problems with semantic and budget constraints to generate adversarial tweets.

result Adversarial tweets can fool stock prediction models and cause significant financial loss.

stock prediction adversarial attack social media sentiment analysis financial loss

2022-05-01abs ↗pdf ↗

Between Stochastic and Adversarial Online Convex Optimization: Improved Regret Bounds via Smoothnesscs.LG

Improved online convex optimization bounds between stochastic and adversarial settings.

problem Understanding optimization tasks that are neither i.i.d. nor fully adversarial.

method Establishing novel regret bounds exploiting smoothness of expected losses.

result Regret bounds improve on previous results by reducing dependence on maximum gradient length to variance of gradients.

online convex optimization stochastic adversarial regret bounds smoothness

2022-02-15abs ↗pdf ↗

Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningstat.ML

We propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the conditional label distribution given input. Virtual adversarial loss is defined as the robustness of the conditional label distribution around each input data point against local perturbation. Unlike adver…

2017-04-13abs ↗pdf ↗

Accelerated Rates between Stochastic and Adversarial Online Convex Optimizationcs.LG

New bounds for online convex optimization between stochastic and adversarial settings.

problem Understanding optimization tasks that are neither i.i.d. nor fully adversarial.

method Establishing novel regret bounds exploiting smoothness of expected losses.

result Regret bounds match expected rates in the fully i.i.d. case and gracefully deteriorate in the fully adversarial case.

online convex optimization stochastic adversarial regret bounds smoothness

2023-03-06abs ↗pdf ↗

Localized Adversarial Training for Increased Accuracy and Robustness in Image Classificationcs.LG

Today's state-of-the-art image classifiers fail to correctly classify carefully manipulated adversarial images. In this work, we develop a new, localized adversarial attack that generates adversarial examples by imperceptibly altering the backgrounds of normal images. We first use this attack to highlight the unnecessa…

2019-09-10abs ↗pdf ↗

Bounded Memory Adversarial Bandits with Composite Anonymous Delayed Feedbackcs.LG

Study non-oblivious adversarial bandits with delayed feedback and propose algorithms with improved regret bounds.

problem Adversarial bandit problem with delayed, composite anonymous feedback.

method Propose wrapper algorithm for non-oblivious delay setting, achieving

o(T)

policy regret.

result Achieve

o(T)

policy regret for many adversarial bandit problems with bounded memory loss sequences.

adversarial bandits delayed feedback composite anonymous bounded memory non-oblivious delay

2022-04-27abs ↗pdf ↗

H

-Consistency Guarantees for Regressioncs.LG

Study improves $H$ -consistency bounds for regression analysis.

problem Improving

H

-consistency bounds for regression analysis.

method Generalized theorems and novel

H

-consistency bounds for various surrogate loss functions.

result Derives principled surrogate losses for adversarial regression.

$H$-consistency regression surrogate loss adversarial regression Huber loss

2024-03-28abs ↗pdf ↗

SAT: Improving Adversarial Training via Curriculum-Based Loss Smoothingcs.LG

SAT improves adversarial training by smoothing the loss landscape through curriculum learning.

problem Adversarial training sacrifices clean accuracy for robustness and suffers from large generalization error.

method SAT uses curriculum learning to smooth the adversarial loss landscape, improving both clean and robust accuracy.

result SAT models improve clean and robust accuracy significantly compared to adversarial training and other baselines.

adversarial training curriculum learning loss smoothing robustness clean accuracy

2020-03-18abs ↗pdf ↗

Interpreting Adversarial Robustness: A View from Decision Surface in Input Spacecs.LG

One popular hypothesis of neural network generalization is that the flat local minima of loss surface in parameter space leads to good generalization. However, we demonstrate that loss surface in parameter space has no obvious relationship with generalization, especially under adversarial settings. Through visualizing …

2018-09-29abs ↗pdf ↗

On Proper Learnability between Average- and Worst-case Robustnesscs.LG

Study on proper learning under relaxed worst-case robust loss for VC classes.

problem Proper adversarially robust PAC learning under relaxed worst-case robust loss.

method Introduced a family of robust loss relaxations and showed their effectiveness for proper learnability.

result VC classes are properly PAC learnable with sample complexity close to standard PAC learning setup.

proper learning adversarial robustness VC dimension sample complexity robust loss relaxations

2022-11-10abs ↗pdf ↗

An Approximate Dynamic Programming Approach to Adversarial Online Learningcs.GT

We describe an approximate dynamic programming (ADP) approach to compute approximations of the optimal strategies and of the minimal losses that can be guaranteed in discounted repeated games with vector-valued losses. Such games prominently arise in the analysis of regret in repeated decision-making in adversarial env…

2016-03-16abs ↗pdf ↗