Detects spiky corruption in CRMDPs to learn optimal policies.
problem Learning optimal policies in environments with imperfect reward functions.
method Characterized spiky reward corruption, introduced algorithm to detect corrupt states.
result Algorithm can detect corrupt states and learn optimal policies.
Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high variance in learning. Such corruption may be a direct result of goal misspecification, randomness in the reward signal, or correlation of the rew…
No real-world reward function is perfect. Sensory errors and software bugs may result in RL agents observing higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error gives it the maximum reward, but where the true reward is actually small. We formal…
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 ) O((L / L_{\min}) C) O (( L / L m i n ) C ) regret term for an adversary with unknown corruption budget. Robust Q-learning algorithm resists corrupted rewards.
problem Non-ideal environments with corrupted rewards.
method Developed a novel robust Q-learning algorithm using historical data.
result Finite-time convergence rate matches state-of-the-art bounds.
We study a variant of the stochastic multi-armed bandit (MAB) problem in which the rewards are corrupted. In this framework, motivated by privacy preservation in online recommender systems, the goal is to maximize the sum of the (unobserved) rewards, based on the observation of transformation of these rewards through a…
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 i l d e O ( C 2 d ∑ t = 1 T σ t 2 + C 2 R d T ) ilde{O}(C^2d\sqrt{\sum_{t = 1}^T σ_t^2} + C^2R\sqrt{dT}) i l d e O ( C 2 d ∑ t = 1 T σ t 2 + C 2 R d T ) . 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.
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.
CRIMED optimizes regret in bandits with unbounded stochastic corruption.
problem Minimizing regret in bandits with arbitrary unbounded corruptions.
method Introduces CRIMED, an asymptotically-optimal algorithm for Gaussian distributions with known variance.
result Achieves exact lower bound on regret for Gaussian distributions with high corruption probability.
We initiate the study of multi-stage episodic reinforcement learning under adversarial corruptions in both the rewards and the transition probabilities of the underlying system extending recent results for the special case of stochastic bandits. We provide a framework which modifies the aggressive exploration enjoyed b…
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.
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.
A bandit algorithm reduces regret in noisy, communication-constrained feedback.
problem Distributed stochastic multi-armed bandit with noisy, communication-constrained feedback.
method Proposes a multi-phase bandit algorithm, UE-UCB++, that matches an information-theoretic lower bound.
result Matches an information-theoretic lower bound of Ω(√(KT/σ²)) on the minimax regret.
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.
This paper optimizes attacks on stochastic bandits and proposes defenses against them.
problem Optimizing adversarial attacks on stochastic bandit algorithms.
method Designs optimal attack strategies and proposes defense algorithms.
result Optimal attack strategies and defense algorithms achieve near perfect performance.
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…
Recent studies have shown that reinforcement learning (RL) models are vulnerable in various noisy scenarios. For instance, the observed reward channel is often subject to noise in practice (e.g., when rewards are collected through sensors), and is therefore not credible. In addition, for applications such as robotics, …
Study cooperative bandit learning with imperfect communication, achieving near-optimal performance.
problem Real-world distributed decision-making with imperfect communication.
method Proposed decentralized algorithms for three communication scenarios: stochastic networks, random delays, and adversarially corrupted rewards.
result Achieved competitive performance and near-optimal guarantees on group regret.
The paper tackles linear bandits with projections, achieving optimal regret.
problem Learning the best arm in a linear bandit model with unobservable projection rewards.
method Developed strategies for both finite and infinite arms, achieving optimal regret bounds.
result Achieved optimal regret bounds for both finite and infinite arms.
DVRL uses RL to estimate data value for machine learning tasks.
problem Adaptive learning of data value for machine learning tasks.
method Meta learning framework with reinforcement learning for data value estimation.
result DVRL yields superior data value estimates compared to alternative methods.
Algorithm identifies Pareto set in bandits with contaminated feedback.
problem Identifying Pareto set in multi-objective bandits with adversarial contamination.
method Sample median-based multi-objective adaptive elimination algorithm.
result Sample complexity bound that depends on contamination probability.
New predictive bandit model with noise for better decision making.
problem Optimizing decisions with limited information and noise.
method Introduced predictive bandits, derived regret bounds, and developed algorithms.
result Developed algorithms matching theoretical regret bounds.
New algorithms combat adversarial attacks in stochastic linear bandits.
problem Adversarial attacks on stochastic linear bandit rewards.
method Two variants of Robust Phased Elimination algorithms, one knowing C C C and one not. result Near-optimal regret in non-corrupted case and additive terms dependent on C C C . The paper provides robustness guarantees for mode estimation in bandits.
problem Understanding robustness in mode estimation under adversarial data contamination.
method Simple randomization and theoretical analysis of multi-armed bandits.
result Regret guarantees for various modal bandit problems.
New method improves off-policy critic evaluation in reinforcement learning.
problem High variance and instability in off-policy policy evaluation.
method Doubly robust estimators applied to actor-critic algorithms.
result Doubly robust estimation significantly improves performance in continuous control tasks.
Matching Markets meet Cumulative Prospect Theory: Towards Optimal and Adversarially Robust Learning
problem Multi-agent multi-armed bandit problem in competitive setup with two-sided matching markets under human-centric decision making model
method Using cumulative prospect theory (CPT) to emulate human preferences
result Improved regret guarantees in adversarial markets with CPT as risk-sensitive measure
Develops a comprehensive theory of corruption in supervised learning.
problem Widespread corruption in data collection affects supervised learning problems.
method Introduces a general theory of corruption using Markov kernels, distinguishing and comparing corruption types.
result Establishes a unified framework for corruption types and develops mitigation strategies.
Thompson Sampling tackles noisy context in stochastic bandits.
problem Designing an action policy for noisy, corrupted contexts in stochastic bandits.
method Introducing a Thompson Sampling algorithm for Gaussian bandits with Gaussian context noise, adopting an information-theoretic analysis.
result Demonstrates the Bayesian regret of the proposed algorithm concerning the oracle's action policy.
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.
Study finds corruption negatively impacts firm performance.
problem The impact of corruption on firm performance is examined.
method Cross-sectional data analysis of a large international dataset.
result Corruption negatively affects corporate performance.
Study shows how repetition affects learning in bandit settings, providing algorithms with sublinear regret.
problem Effect of persistence of engagement on learning in stochastic multi-armed bandit settings.
method Novel algorithms that achieve sublinear regret under temporal constraints.
result Additive effect of priming on regret upper bound, matching popular algorithms in absence of priming.
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.
New algorithm for linear optimization with adaptive corruption.
problem Stochastic linear optimization under adversarial corruption.
method Algorithm uses Löwner-John's ellipsoid for exploration and divides time into epochs.
result Regret increases linearly with corruption amount.
We report quantitative relations between corruption level and economic factors, such as country wealth and foreign investment per capita, which are characterized by a power law spanning multiple scales of wealth and investments per capita. These relations hold for diverse countries, and also remain stable over differen…
CUTS removes corruption from models without clean data, improving utility and security.
problem Removing corruption from models without access to clean training data.
method CUTS uses a proxy set to amplify corruption and subtract it from model weights.
result CUTS recovers a large fraction of lost utility and nearly eliminates attacks with minimal damage.
Study robust estimation under varying corruption probabilities in data.
problem Robust estimation in scenarios with heterogeneous corruption rates.
method Developed estimators for mean and regression under various corruption patterns.
result Optimal estimators can discard corrupted samples beyond a specific threshold.
Network science reveals corruption risk in EU procurement markets.
problem Identifying corruption risk in EU procurement markets.
method Analyzing a large dataset of public procurement contracts using network science.
result Corruption risk is clustered and varies by country, not just by market core or periphery.
Binary classification improves with a small fraction of corrupted labels.
problem Binary classification with corrupted labels.
method Established corruption as a form of regularization and computed upper bounds on estimation error.
result Corruption is beneficial only up to a small fraction of the total sample, scaling with the square root of the sample size.
We study the problem of corrupted sensing, a generalization of compressed sensing in which one aims to recover a signal from a collection of corrupted or unreliable measurements. While an arbitrary signal cannot be recovered in the face of arbitrary corruption, tractable recovery is possible when both signal and corrup…
New algorithm optimizes noisy, potentially corrupted functions.
problem Optimizing unknown functions with noisy bandit feedback, especially when evaluations are corrupted.
method Fast-Slow GP-UCB algorithm, combining robust and non-robust evaluations, enlarged confidence bounds.
result Theoretical analysis upper bounds cumulative regret, showing dependencies on corruption level and kernel.
Study improves binary classification with multiple corrupted samples.
problem Binary classification with multiple corrupted training samples.
method Minimizes weighted combination of corruption-corrected empirical risks.
result Optimal weights are functions of sample sizes and corruption degrees.
Picket guards against corrupted data in machine learning models.
problem Data corruption biases models and invalidates predictions.
method PicketNet detects corrupted data using self-supervised deep learning; flags corrupted queries online.
result Picket consistently protects models from corrupted data during training and deployment.
New setting combines state evolution and corrupted context for better decision-making.
problem Decision-making in a changing state with unreliable context.
method Proposes a new algorithm using a referee to dynamically combine contextual bandit and multi-armed bandit policies.
result Improved empirical performance compared to existing algorithms.
New method for contextual bandits with corrupted context.
problem Contextual bandits with corrupted context in online settings.
method Combining contextual bandit and multi-armed bandit approaches.
result Improved learning from all iterations, including corrupted ones.
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.
The main purpose of this paper is to formalize the modelling process, analysis and mathematical definition of corruption when entering into a contract between principal agent and producers. The formulation of the problem and the definition of concepts for the general case are considered. For definiteness, all calculati…
New algorithm robustly trains deep neural networks under corrupted supervision.
problem Training deep neural networks with corrupted supervision data.
method Unified framework for classification and regression, focusing on collective impact of data points on average gradient.
result Achieves strong guarantees without assuming the type of corruption, robust under various types of corruption.