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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “Adversarial corruption”

Multi-Agent Stochastic Bandits Robust to Adversarial Corruptionscs.LG

Algorithm maximizes total reward in multi-agent bandits with adversarial corruptions.

problem Maximizing total reward in multi-agent bandits with adversarial corruptions.

method Proposes a cooperative learning algorithm robust to adversarial corruptions.

result Demonstrates an additive

O((L / L_{\min}) C)

regret term for an adversary with unknown corruption budget.

multi-agent stochastic bandits adversarial corruptions cooperative learning regret minimization

2024-11-12abs ↗pdf ↗

On the effectiveness of adversarial training against common corruptionscs.LG

Adversarial training improves robustness against common corruptions.

problem Improving robustness of models against common corruptions.

method Adversarial training with

\ell_p

perturbation and learned perceptual similarity.

result Our approach leads to state-of-the-art performance on common corruptions.

adversarial training robustness corruptions CIFAR-10 ImageNet-100

2021-03-03abs ↗pdf ↗

Robust Lipschitz Bandits to Adversarial Corruptionscs.LG

New algorithm tackles adversarial corruption in Lipschitz bandits with sub-linear regret.

problem Adversarial corruption in Lipschitz bandits.

method Developed robust Lipschitz bandit algorithms for weak and strong adversaries.

result Achieved sub-linear regret under both weak and strong adversaries.

Lipschitz bandits adversarial corruption sub-linear regret robust algorithms

2023-05-29abs ↗pdf ↗

Stochastic Linear Optimization with Adversarial Corruptioncs.LG

We extend the model of stochastic bandits with adversarial corruption (Lykouriset al., 2018) to the stochastic linear optimization problem (Dani et al., 2008). Our algorithm is agnostic to the amount of corruption chosen by the adaptive adversary. The regret of the algorithm only increases linearly in the amount of cor…

2019-09-04abs ↗pdf ↗

Learning with Monotone Adversarial Corruptionscs.LG

Monotone adversarial corruptions degrade optimal learning algorithms.

problem Optimal learning algorithms' reliance on exchangeability and independence is challenged.

method Introduces a monotone adversarial corruption model where an adversary adds monotone corruptions to a clean dataset.

result Optimal learning algorithms achieve suboptimal expected error on new test points.

monotone corruptions adversarial attacks machine learning binary classification exchangeability

2026-01-05abs ↗pdf ↗

Adversarial Sign-Corrupted Isotonic Regressionmath.ST

New method tackles adversarial sign-corrupted isotonic regression, estimating monotonic signals under heavy dependence.

problem Estimating monotonic signals when responses are sign-corrupted and adversarially designed to violate monotonicity.

method Developed ASCIFIT, a three-step estimation procedure using PAVA with pre- and post-processing corrections.

result Theoretical guarantees of sharp high probability upper bounds and minimax lower bounds for ASCIFIT.

Adversarial Sign-Corruption Isotonic Regression Monotonic Estimation Minimax Lower Bounds PAVA

2022-07-14abs ↗pdf ↗

Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptionscs.LG

New algorithm reduces linear contextual bandit regret with adversarial corruption.

problem Linear contextual bandit with adversarial reward corruption.

method Optimism in the face of uncertainty principle, weighted ridge regression.

result Achieves nearly optimal regret for both corrupted and uncorrupted cases.

linear contextual bandits adversarial corruption optimism ridge regression regret minimization

2022-05-13abs ↗pdf ↗

On Biased Random Walks, Corrupted Intervals, and Learning Under Adversarial Designcs.LG

Analyzes biased random walks and corrupted intervals in adversarial settings.

problem Learning thresholds and intervals in adversarial conditions.

method Analyzes biased random walks and corrupted intervals under adversarial design.

result Analyzes the expected behavior of biased random walks and corrupted intervals.

biased random walks corrupted intervals adversarial design learning thresholds learning intervals

2020-03-30abs ↗pdf ↗

Better Algorithms for Stochastic Bandits with Adversarial Corruptionscs.LG

We study the stochastic multi-armed bandits problem in the presence of adversarial corruption. We present a new algorithm for this problem whose regret is nearly optimal, substantially improving upon previous work. Our algorithm is agnostic to the level of adversarial contamination and can tolerate a significant amount…

2019-02-22abs ↗pdf ↗

Robust Iterative Learning Hidden Quantum Markov Modelscs.LG

RILA learns HQMMs robustly against adversarial corruption.

problem Robustness of HQMM learning algorithms under adversarial perturbations.

method Adversarially Corrupted HQMM (AC-HQMM) and Robust Iterative Learning Algorithm (RILA).

result RILA outperforms existing algorithms in convergence stability, corruption resilience, and physical validity.

HQMM Robustness Adversarial Corruption Iterative Learning Quantum Markov Models

2025-10-27abs ↗pdf ↗

Stochastic gradient descent for streaming linear and rectified linear systems with adversarial corruptionscs.LG

Improved SGD for robust linear and ReLU regression with adversarial corruptions.

problem Robust regression with adversarial corruptions in streaming data.

method Stochastic gradient descent (SGD-exp) with exponentially decaying step size.

result Nearly linear convergence to true parameter with up to 50% Massart corruption rate.

stochastic gradient descent linear regression ReLU regression adversarial corruptions streaming data

2024-03-02abs ↗pdf ↗

A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptionscs.LG

A new algorithm reduces regret in bandit problems with adversarial corruptions.

problem Optimizing decision-making in bandit problems with variable uncertainties and adversarial interference.

method Proposes HCW-GLB-OMD, an OMD-based estimator with Hessian-based confidence weights for robustness.

result Achieves instance-wise minimax optimality with a

κ

-factor in the corruption term.

bandit problems heteroskedastic GLBs adversarial corruptions online mirror descent regret minimization

2026-02-11abs ↗pdf ↗

Active Learning on Adversarially Corrupted Graphscs.LG

New algorithm finds corrupted vertices in graphs with few queries.

problem Adversarial tampering of graph edges and vertices.

method Active learning algorithm with polynomial query complexity.

result Efficiently recovers corrupted vertices with small query complexity.

active learning adversarial attacks graph theory vertex expansion sum-of-squares algorithms

2026-07-06abs ↗pdf ↗

Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruptionstat.ML

This study tackles adversarial corruption in model-based reinforcement learning.

problem Adversarial corruption in model-based reinforcement learning.

method Maximum likelihood estimation (MLE) approach for learning transition model in both online and offline settings.

result Proves a regret of

ilde{\mathcal{O}}(\sqrt{T} + C)

for CR-OMLE and a suboptimality of

\mathcal{O}(C/n)

for CR-PMLE.

reinforcement learning model-based adversarial corruption maximum likelihood estimation regret analysis

2024-02-14abs ↗pdf ↗

On Optimal Robustness to Adversarial Corruption in Online Decision Problemsstat.ML

The paper shows optimal robustness against adversarial corruption in sequential decision-making problems.

problem Optimal robustness to adversarial corruption in online decision-making problems.

method Investigates prediction with expert advice and multi-armed bandit problems, focusing on algorithms with decreasing learning rates and second-order regret bounds.

result Optimal robustness can be expressed by a square-root dependency on the amount of corruption, achieving

O(\frac{\log N}{\Delta} + \sqrt{\frac{C \log N}{\Delta}})

-regret.

Adversarial Corruption Sequential Decision Making Prediction with Expert Advice Multi-Armed Bandit Regret Bounds

2021-09-22abs ↗pdf ↗

A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Banditsstat.ML

Robust algorithm optimizes corrupted Gaussian process bandits.

problem Sequential optimization of corrupted, expensive reward functions.

method Robust GP Phased Elimination (RGP-PE) algorithm.

result Algorithm balances robustness to corruptions with exploration and exploitation.

Robust optimization Gaussian process Bandit learning Adversarial corruption Phased elimination

2022-02-03abs ↗pdf ↗

Corruption-tolerant Algorithms for Generalized Linear Modelscs.LG

Unified framework SVAM learns GLMs robustly to adversarial label corruption.

problem Learning GLMs under adversarial label corruption.

method SVAM framework based on variance reduction technique.

result Provable model recovery guarantees superior to state-of-the-art.

SVAM Generalized Linear Models Adversarial Corruption Robust Regression Variance Reduction

2022-12-11abs ↗pdf ↗

Corruption Robust Active Learningcs.LG

New algorithm robust to label corruptions in active learning.

problem Active learning under unknown adversarial label corruptions.

method Proposed a new active learning algorithm that is provably correct without assumptions on corruptions.

result Achieves minimax label complexity in non-corrupted setting and only requires additional labels to achieve desired accuracy in corrupted setting.

active learning label corruptions minimax label complexity streaming-based adversarial

2021-06-21abs ↗pdf ↗

Stochastic bandits robust to adversarial corruptionscs.LG

We introduce a new model of stochastic bandits with adversarial corruptions which aims to capture settings where most of the input follows a stochastic pattern but some fraction of it can be adversarially changed to trick the algorithm, e.g., click fraud, fake reviews and email spam. The goal of this model is to encour…

2018-03-25abs ↗pdf ↗

Linear Regression under Missing or Corrupted Coordinatescs.DS

Study linear regression with missing or corrupted data, showing error bounds.

problem Linear regression under missing or corrupted data.

method Information-theoretic lower bounds and efficient algorithms.

result Error bounds match in missing and corruption settings.

linear regression missing data corruption information theory algorithm efficiency

2025-09-23abs ↗pdf ↗

Improved Analysis of the Tsallis-INF Algorithm in Stochastically Constrained Adversarial Bandits and Stochastic Bandits with Adversarial Corruptionscs.LG

Improved regret bounds for Tsallis-INF in adversarial bandits and corruptions.

problem Adversarial bandits and corruptions in multiarmed bandit problems.

method Improved regret bounds for Tsallis-INF algorithm.

result Achieves $\mathcal{O}\left(\left(\sum_{i eq i^*} \frac{1}{Δ_i} ight)\log_+\left(\frac{(K-1)T}{\left(\sum_{i eq i^*} \frac{1}{Δ_i} ight)^2} ight)+\sqrt{C\left(\sum_{i eq i^*}\frac{1}{Δ_i} ight)\log_+\left(\frac{(K-1)T}{C\sum_{i eq i^*}\frac{1}{Δ_i}} ight)} ight)$ regret bound.

Tsallis-INF regret bounds adversarial bandits stochastic corruptions multiarmed bandits

2021-03-23abs ↗pdf ↗

Linear Contextual Bandits with Adversarial Corruptionscs.LG

New algorithm resists corruption in linear contextual bandits.

problem Adversarial corruption in linear contextual bandits.

method Variance-aware algorithm with multi-level partition and adaptive confidence sets.

result Regret bound of

ilde{O}(C^2d\sqrt{\sum_{t = 1}^T σ_t^2} + C^2R\sqrt{dT})

contextual bandits adversarial corruption variance-aware regret bound multi-level partition

2021-10-25abs ↗pdf ↗

Trimmed Maximum Likelihood Estimation for Robust Learning in Generalized Linear Modelscs.LG

Estimates GLMs robustly against label corruptions.

problem Learning GLMs under adversarial label corruptions.

method Iterative trimmed maximum likelihood estimator.

result Achieves minimax near-optimal risk.

Generalized Linear Models Adversarial Corruptions Robust Estimation Iterative Trimmed Maximum Likelihood

2022-06-09abs ↗pdf ↗

Reaching Kesten-Stigum Threshold in the Stochastic Block Model under Node Corruptionscs.LG

New algorithm detects communities even with corrupted data, reaching Kesten-Stigum threshold.

problem Robust community detection in stochastic block model with node corruptions.

method Polynomial-time algorithm using Grothendieck norm of principal submatrices.

result First algorithm to achieve weak recovery at Kesten-Stigum threshold with node corruptions.

community detection stochastic block model node corruptions Kesten-Stigum threshold Grothendieck norm

2023-05-17abs ↗pdf ↗

Subspace Methods That Are Resistant to a Limited Number of Features Corrupted by an Adversarycs.LG

In this paper, we consider batch supervised learning where an adversary is allowed to corrupt instances with arbitrarily large noise. The adversary is allowed to corrupt any $l$ features in each instance and the adversary can change their values in any way. This noise is introduced on test instances and the algorithm r…

2019-02-19abs ↗pdf ↗

Investigating the Corruption Robustness of Image Classifiers with Random Lp-norm Corruptionscs.LG

Study improves image classifier robustness to random p-norm corruptions.

problem Improving robustness of image classifiers to real-world imperceptible corruptions.

method Training and testing with random p-norm corruptions, evaluating robustness against different p-norms.

result Training with a combination of p-norm corruptions significantly improves robustness.

image classifiers robustness random corruptions p-norm adversarial robustness

2023-05-09abs ↗pdf ↗

Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecificationcs.LG

Unified framework for corruption-robust linear bandits with optimal gap-dependent misspecification bounds.

problem Effective learning in linear bandits with corrupted rewards across different corruption models.

method Unified framework for analyzing strong and weak corruption, connection to gap-dependent misspecification, and specialized algorithm.

result Optimal bounds for gap-dependent misspecification in linear bandits.

corruption-robust learning minimax regret gap-dependent misspecification stochastic linear bandits adversarial linear bandits

2024-10-10abs ↗pdf ↗

Robust Mean Estimation under Quantizationstat.ML

Robustly estimates mean with quantized data and corruption.

problem Mean estimation under quantization and adversarial corruption.

method Constructs multivariate robust estimators in two settings.

result Optimal estimators up to logarithmic factors.

mean estimation quantization robustness adversarial corruption

2026-01-11abs ↗pdf ↗

Adversarial Examples Are a Natural Consequence of Test Error in Noisecs.LG

Over the last few years, the phenomenon of adversarial examples --- maliciously constructed inputs that fool trained machine learning models --- has captured the attention of the research community, especially when the adversary is restricted to small modifications of a correctly handled input. Less surprisingly, image…

2019-01-29abs ↗pdf ↗

MimicGAN: Corruption-Mimicking for Blind Image Recovery & Adversarial Defensecs.CV

Solving inverse problems continues to be a central challenge in computer vision. Existing techniques either explicitly construct an inverse mapping using prior knowledge about the corruption, or learn the inverse directly using a large collection of examples. However, in practice, the nature of corruption may be unknow…

2018-11-20abs ↗pdf ↗

Geometry-Aware Instrumental Variable Regressioncs.LG

Proposes a robust IV estimator using optimal transport for corrupted or adversarial data.

problem Lack of robustness in traditional IV estimators for corrupted or adversarial data.

method Integrates data-derivative information through optimal transport to address geometric aspects of data.

result Improves robustness against data corruption and adversarial attacks.

Instrumental Variable Optimal Transport Robustness Adversarial Attacks Data Corruption

2024-05-19abs ↗pdf ↗

Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noisecs.LG

SGD-trained neural networks generalize well even with adversarial label noise.

problem Generalization of neural networks trained on adversarial label noise.

method Training a one-hidden-layer neural network with SGD on arbitrary width networks.

result SGD-trained networks achieve classification accuracy competitive with the best halfspace over adversarial label noise.

SGD neural networks generalization adversarial noise label corruption

2021-01-04abs ↗pdf ↗

Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscs.LG

In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Then we propose a new dataset called ImageNet-P which enables researc…

2019-03-28abs ↗pdf ↗

On the relationship between class selectivity, dimensionality, and robustnesscs.LG

Class selectivity affects robustness to corruptions but not to adversarial attacks.

problem Understanding the relationship between class selectivity and robustness in neural networks.

method Investigated the impact of class selectivity on robustness to natural corruptions and adversarial attacks using Tiny ImageNetC and CIFAR10C datasets.

result Decreasing class selectivity increases robustness to both natural corruptions and adversarial attacks.

class selectivity robustness natural corruptions adversarial attacks dimensionality

2020-07-08abs ↗pdf ↗

Minimax Rates for Robust Community Detectioncs.DS

Efficient algorithm detects communities in noisy graphs with robustness.

problem Community detection in stochastic block models with adversarial corruptions.

method Efficient algorithm using semidefinite programming for robust clustering.

result Achieves error

O(ε) + e^{-\frac{C}{2} (1 \pm o(1))}

for

ε

-fraction of corruptions.

community detection stochastic block model robustness semidefinite programming adversarial corruptions

2022-07-25abs ↗pdf ↗

Adversarially-Robust Inference on Trees via Belief Propagationcs.DS

Adversarial inference on tree models is possible with limited corruption, improving on Kesten-Stigum threshold.

problem Posterior inference on tree-structured graphical models in the presence of adversarial corruption.

method Dynamic programming via belief propagation, constrained adversarial corruption.

result Belief propagation can perform accurate inference with limited adversarial corruption.

adversarial inference tree models belief propagation posterior inference graphical models

2024-03-31abs ↗pdf ↗

Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processesstat.ML

New algorithm reduces regret in RL with adversarial corruption.

problem Adversarial corruption in reinforcement learning.

method Uncertainty-weighted least-squares regression and weighted uncertainty estimator.

result Achieves regret of

ilde{O}(\sqrt{T} + ζ)

for contextual bandits.

reinforcement learning contextual bandits uncertainty weighting adversarial corruption regret bound

2022-12-12abs ↗pdf ↗

On the Robustness of Epoch-Greedy in Multi-Agent Contextual Bandit Mechanismscs.LG

Improved $ε$ -greedy handles strategic bidding in PPC auctions.

problem Strategic bidding in PPC auctions with personalization and corruptions.

method Extended

ε

-greedy to handle strategic arms in contextual multi-arm bandit.

result

ε

-greedy is robust to adversarial corruptions and degrades linearly with corruption.

PPC auctions contextual bandit strategic bidding ε-greedy adversarial corruptions

2023-07-15abs ↗pdf ↗

Certified Robust Neural Networks: Generalization and Corruption Resistancestat.ML

New method improves neural network robustness without sacrificing generalization.

problem Robustness and generalization are often at odds in neural networks.

method Distributionally robust loss function bridging robustness and generalization.

result Certified robustness against data evasion and poisoning attacks with guaranteed generalization.

neural networks robustness generalization adversarial training corruption resistance

2023-03-03abs ↗pdf ↗

Fairness-Aware PAC Learning from Corrupted Datacs.LG

New study shows how adversaries can bias fair machine learning models even with corrupted data.

problem Fairness concerns in machine learning models under data corruption.

method Study of fairness-aware learning algorithms under worst-case data manipulations.

result Natural learning algorithms optimizing for both accuracy and fairness are order-optimal in terms of corruption ratio and protected groups frequencies.

fairness machine learning data corruption adversarial attacks accuracy

2021-02-11abs ↗pdf ↗

Robust Group Synchronization via Cycle-Edge Message Passingstat.ML

We propose a general framework for solving the group synchronization problem, where we focus on the setting of adversarial or uniform corruption and sufficiently small noise. Specifically, we apply a novel message passing procedure that uses cycle consistency information in order to estimate the corruption levels of gr…

2019-12-24abs ↗pdf ↗

A Model Selection Approach for Corruption Robust Reinforcement Learningcs.LG

New model selects robustly in adversarial reinforcement learning with unknown corruption.

problem Adversarial corruption in reinforcement learning with unknown total corruption amount.

method Model selection approach for finite-horizon tabular and linear MDPs.

result First worst-case optimal bound without knowledge of total corruption.

reinforcement learning corruption robustness model selection adversarial tabular MDPs

2021-10-07abs ↗pdf ↗

Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruptioncs.LG

Study on measuring vulnerability of neural network parameters via corruption.

problem Understanding the robustness and generalization of deep neural networks.

method Proposes an indicator to measure parameter robustness via parameter corruption and provides a gradient-based estimation.

result Demonstrates the effectiveness of the proposed indicator and training method in improving parameter robustness and accuracy.

Deep Neural Networks Parameter Robustness Vulnerability Gradient Estimation Adversarial Corruption

2020-06-10abs ↗pdf ↗

Robust Bayesian Optimisation with Unbounded Corruptionsstat.ML

New algorithm robust to outliers in Bayesian Optimization.

problem Vulnerability of Bayesian Optimization to extreme outliers.

method Introduces a new adversary with a frequency-bounded corruption budget and derives RCGP-UCB algorithm.

result Achieves sublinear regret in the presence of up to

O(T^{1/4})

and

O(T^{1/7})

corruptions with possibly infinite magnitude.

Bayesian Optimization Robustness Outliers Adversary Regret

2025-11-19abs ↗pdf ↗

Robust Distribution Learning with Local and Global Adversarial Corruptionscs.LG

Efficiently learns distributions corrupted by both global and local adversarial modifications.

problem Learning distributions with both global and local adversarial corruptions.

method Develops an efficient algorithm to minimize Wasserstein distance with orthogonal projections.

result Achieves optimal risk bounds with error

\sqrt{\varepsilon k} + ρ+ ilde{O}(d\sqrt{k}n^{-1/(k \lor 2)})

Adversarial Corruption Distribution Learning Wasserstein Distance Orthogonal Projections Trace Norm Approximation

2024-06-10abs ↗pdf ↗

A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustnesscs.LG

Boosting framework improves adversarial robustness in deep learning.

problem Adversarial robustness of deep neural networks.

method Multiclass boosting framework with theoretical guarantees.

result Multiclass boosting achieves adversarial robustness faster than state-of-the-art methods.

adversarial robustness deep learning boosting stochastic gradient descent minimax guarantee

2021-03-01abs ↗pdf ↗

PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Maskingcs.CV

PatchGuard defends against localized adversarial patches with provable robustness.

problem Localized adversarial patches induce misclassification in machine learning models.

method PatchGuard uses CNNs with small receptive fields and robust masking to detect and mask corrupted features.

result PatchGuard achieves state-of-the-art provable robust accuracy and clean accuracy.

adversarial patches provably robust masking CNNs receptive fields

2020-05-17abs ↗pdf ↗

Best-of-Both-Worlds Linear Contextual Banditscs.LG

Develops a strategy to minimize loss in both stochastic and adversarial environments for linear contextual bandits.

problem Linear contextual bandits with adversarial corruption.

method Proposes a novel strategy called Best-of-Both-Worlds (BoBW) RealFTRL, extending RealLinExp3 and FTRL.

result Regret upper bound of $O\left(\min\left\{\frac{(\log(T))^3}{Δ_{*}} + \sqrt{\frac{C(\log(T))^3}{Δ_{*}}},\ \ \sqrt{T}(\log(T))^2 ight\} ight)$, showing effectiveness in both stochastic and adversarial environments.

linear contextual bandits adversarial corruption stochastic environments adversarial environments FTRL

2023-12-27abs ↗pdf ↗