New framework for robust uncertainty quantification in strategic settings.
problem Machine learning model predictions can be strategically altered by informed agents.
method Strategic Conformal Prediction framework
result Theoretical guarantees and experimental validation show remarkable effectiveness.
Paper generalizes strategic classification framework and introduces SVC for PAC-learning.
problem Strategic manipulation of testing data to fool classifiers.
method Unified framework for strategic classification, strategic VC-dimension (SVC).
result Characterizes the learnability and computational tractability of linear classifiers.
New algorithm learns optimal policies in strategic MDPs with private types.
problem Optimal policy learning in strategic MDPs with private types and information asymmetry.
method PLAN algorithm using instrumental variable regression and pessimism principle.
result PLAN achieves near-optimal policy with 1 / K 1 / \sqrt{K} 1/ K optimality. Defends against strategic data manipulation in machine learning.
problem Adversaries can tamper with datasets to influence learning outcomes.
method Uses multiple learners and strategic activation to counteract attacks.
result Demonstrates effectiveness of a game-theoretic approach to defense.
New findings show strategic interactions can undermine model expressiveness in machine learning.
problem How strategic interactions affect model performance in machine learning.
method Analyzing model expressiveness and strategic interactions in various machine learning settings.
result Optimizing over less expressive model classes can lead to better equilibrium outcomes in strategic environments.
Algorithm learns optimal coordination for strategic agents in uncertain settings.
problem Optimizing rewards for strategic agents with private types and actions.
method Combines delaying mechanism, reward angle estimation, and LinUCB algorithm.
result Near optimal regret bound of O ~ ( T ) \tilde{O}(\sqrt{T}) O ~ ( T ) for learning optimal policy. Study optimizes auction pricing for strategic bidders in repeated auctions.
problem Optimizing revenue in auctions with multiple strategic bidders.
method Proposes a novel algorithm with strategic regret bound of O(log log T).
result Algorithm learns strategic buyer's valuation with theoretical guarantees.
Study strategic dynamic pricing for buyers with unknown manipulation costs.
problem Strategic buyers manipulate their features to get lower prices, hindering profit maximization.
method Proposes a strategic dynamic pricing policy that incorporates strategic behavior and binary response data.
result Achieves sublinear regret bound of O ( T ) O(\sqrt{T}) O ( T ) compared to linear Ω ( T ) Ω(T) Ω ( T ) regret of non-strategic policies. Study compares employers with and without anticipating strategic labor force responses.
problem Understanding and optimizing strategic interactions in labor markets.
method Formulation of causal strategic classification, theory, and experiments.
result Performatively optimal hiring policies improve employer and labor outcomes, but can also harm labor force utility.
Study allocates resources to strategic agents while balancing cost and incentives.
problem Dynamic allocation of reusable resources to strategic agents with private valuations under long-term cost constraints.
method Incentive-aware framework combining epoch-based lazy updates and randomized exploration rounds.
result Achieves i l d e O ( T ) ilde{\mathcal{O}}(\sqrt{T}) i l d e O ( T ) social welfare regret, satisfies all cost constraints, and ensures incentive alignment. This paper tackles online strategic decision making with asymmetry and knowledge transportability.
problem Strategic decision making with information asymmetry and knowledge transportability challenges.
method Developed a sample-efficient algorithm for online learning under these conditions.
result Proved sample complexity of O ( 1 / ε 2 ) O(1/ε^2) O ( 1/ ε 2 ) for learning an ε ε ε -optimal policy. The paper tackles performative policy learning with strategic agents, improving scalability and generalizability.
problem Strategic agents adjust their features in response to a released policy, causing endogenous distribution shifts.
method Relaxing parametric assumptions, the paper uncovers a low-dimensional structure in distribution shifts and proposes a gradient-based policy optimization algorithm.
result The proposed algorithm achieves high sample efficiency and provides theoretical guarantees for convergence.
Abstract MDPs enable strategic exploration and fast reward transfer in complex environments.
problem Challenging to learn accurate MDPs for high-dimensional states.
method Learn an abstract MDP over low-dimensional coarse states, using an abstraction function.
result Achieves superhuman performance on Pitfall! and higher reward with fewer samples.
No-regret learning with strategic experts, incentivized.
problem Online learning with strategic experts who misreport beliefs.
method Building on wagering mechanisms, we provide algorithms for no-regret and incentive compatibility in both full and partial information settings.
result Our algorithms achieve no regret and incentive compatibility for myopic experts, with comparable regret to classic no-regret algorithms and diminishing regret for forward-looking agents.
Strategic brokers exploit private information in broker-mediated markets, affecting informed traders' performance.
problem Strategic interactions and information leakage in broker-mediated markets.
method Study of strategic trading behavior and information leakage in a broker-mediated market.
result Brokers hold a strategic advantage over informed traders due to information leakage in trading flows.
Strategic feature manipulation helps learners identify meaningful variables in online regression settings.
problem Strategic feature manipulation poses a challenge for learners in online regression settings.
method Investigates how strategic feature manipulation by individuals can help learners recover meaningful features.
result Simple learner behavior can help accurately recover meaningful features and incentivize feature improvement.
Study optimal pricing algorithms for strategic buyers in repeated auctions.
problem Optimizing revenue in auctions with strategic buyers over multiple rounds.
method Proposed a novel algorithm that never decreases prices and has a strategic regret bound of Θ(log log T).
result Closed the open research question on no-regret horizon-independent weakly consistent pricing.
Study one-shot strategic classification under unknown costs, improving worst-case accuracy.
problem Learning robust decision rules in strategic settings with unknown user costs.
method Formal study of one-shot strategic classification, framing as a minimax problem, designing efficient algorithms for full-batch and stochastic settings.
result Proves efficient algorithms converge to minimax solution, revealing dual norm regularization's value.
Study optimal treatment assignment policies under strategic agent responses.
problem Learning optimal treatment policies with strategic agents complicates estimation.
method Dynamic model with threshold convergence to mean-field equilibrium, consistent estimator for policy gradient.
result Threshold for treatment assignment converges to mean-field equilibrium threshold under large but finite number of agents.
Look-ahead reasoning helps predict strategic user behavior on learning platforms.
problem Optimization criteria on learning platforms do not reflect users' priorities.
method Formalized level-k thinking and contrasted collective and selfish behavior.
result Coordination benefits users but does not offer higher-level reasoning advantages in the long run.
New research shows strategic classification harms individuals and society.
problem Strategic behavior in decision-making leads to unfair outcomes.
method Introducing a social burden metric, the study quantifies the negative externalities of strategic classification.
result Any increase in institutional utility leads to a corresponding increase in social burden.
New framework reduces strategic manipulation cost for minority groups in fair classification.
problem Strategic manipulation disparities in fair classification.
method Constrained optimization framework that constructs classifiers to reduce strategic manipulation cost for minority groups.
result Empirically, the approach reduces strategic manipulation cost for minority groups over multiple real-world datasets.
New approach learns walk and trot gaits from simulated quadruped using strategic exploration.
problem Learning symmetric gaits (walk and trot) from high-dimensional action spaces.
method Introduced symmetry properties into initial covariance of Gaussian search distribution for strategic exploration. Used episode-based likelihood ratio policy gradient and relative entropy policy search.
result Significant performance enhancement in learning walk and trot gaits compared to random gaits.
Symmetric game analysis shows Nash equilibria in three strategic states.
problem Analyzing Nash equilibria in a symmetric multi-player zero-sum game with two strategic variables.
method Using the minimax theorem by Sion to show equivalence of Nash equilibria.
result Nash equilibria are equivalent in three strategic states.
New approach reduces simulator exploitation by improving strategic robustness.
problem Simulator exploitation leading to reality gap between simulation and real-world performance.
method Formulated as a zero-sum minimax game, providing theoretical guarantees and a convergent active data selection algorithm.
result Proves convergence and reduces prediction error in strategically important regions by 1.5-2.2 times.
New framework shows strategic behavior is actually a form of causal modeling.
problem Designing classifiers that incentivize strategic behavior to improve quality.
method Developed a causal framework to distinguish between gaming and improvement.
result Proved any procedure for designing incentive classifiers must solve a causal inference problem.
New algorithms optimize decision rules in strategic scenarios, minimizing prediction risk and incentivizing better outcomes.
problem Strategic agents manipulate features to improve outcomes, complicating decision-making models.
method Efficient algorithms for learning decision rules that minimize prediction risk, incentivize better outcomes, and estimate true model coefficients.
result Optimal decision rules can be learned through testing and observing agent responses, circumventing hardness results.
The paper addresses fairness in dynamic pricing for strategic buyers.
problem Price disparities among specific groups can lead to unfair perceptions and legal violations.
method Proposes a dynamic pricing policy that achieves fairness and discourages strategic behavior.
result Achieves an upper bound of O ( T + H ( T ) ) O(\sqrt{T}+H(T)) O ( T + H ( T )) regret over T T T time horizons, reducing regret by 35.06% compared to a benchmark policy. Modified Perceptron handles strategic agents with limited position changes.
problem Learning linear classifiers in the presence of strategic agents that can manipulate their positions.
method Developed a modified Perceptron algorithm with bounded mistakes under various manipulation costs.
result The modified Perceptron achieves bounded mistakes even when manipulation costs are unknown.
The paper develops a mathematical model for strategic shifts.
problem Finding optimal moments for strategy changes in market dynamics.
method Explicit strategy formulation using fluctuation theory.
result Analytical results predict optimal strategy shifts.
Adobe research tackles strategic recommendations using reinforcement learning.
problem Optimizing user interactions for long-term objectives in various use-cases.
method Reinforcement learning applied to modeling user behavior and decision-making.
result Practical solutions implemented for various use-cases, addressing fundamental challenges.
User strategization undermines algorithmic trustworthiness.
problem User strategic behavior corrupts algorithmic data and trust.
method Modeling user-platform interactions as a game, analyzing strategic behavior's short-term benefits and long-term harms.
result User strategization can initially benefit platforms but ultimately harms their ability to make accurate decisions.
Models show strategic agents can influence classifier outcomes by investing effort.
problem How strategic agents can influence classifier outcomes.
method Developed a model to characterize strategic effort investment.
result Simple linear mechanisms can incentivize strategic effort effectively.
Paper presents a defense framework against adversarial examples.
problem Vulnerability of deep neural networks to adversarial examples.
method Cross-layer strategic ensemble defense with input and output transformations.
result Strategic ensemble defense achieves high defense success rates and robustness.
Strategic feature selection in high-stakes domains like healthcare.
problem Strategic manipulation of input features in algorithmic predictors.
method Formal study of strategic classification through feature selection and ridge regularization.
result Excluding individual features based on manipulability is generally suboptimal.
The paper analyzes trading strategies in a competitive market with incomplete information.
problem Strategic trading under uncertainty when firms lack full knowledge of competitors' strategies.
method Bayesian games framework to incorporate uncertainty and derive optimal trading strategies.
result Uncertainty significantly impacts trading strategies compared to complete information scenarios.
Ad exchanges use CORP to set reserve prices against strategic buyers.
problem Setting optimal reserve prices in ad exchanges with strategic buyers.
method Proposes CORP policy to learn and set reserve prices robustly.
result Achieves sublinear regret in unknown noise distribution.
Randomised classifiers outperform deterministic ones in strategic classification.
problem Strategic modification of features by agents in classification tasks.
method Theoretical analysis of randomised classifiers in strategic classification.
result Randomised classifiers can achieve better accuracy than deterministic ones under certain conditions.
New approach incentivizes strategic agents to explore, making exploration almost free.
problem Incentivized exploration in multi-armed bandits with long-term strategic agents.
method Simple incentive-provision strategy, best arm identification algorithm, and UCB lower bound.
result Exploration can be (almost) free when there are many learning agents.
LLMs can collude in market divisions, maximizing profits.
problem Strategic collusion of LLM agents in multi-commodity markets.
method Examined LLMs in Cournot competition frameworks, analyzing pricing and resource allocation strategies.
result LLMs can monopolize specific commodities without direct human input or explicit collusion commands.
Strategic traders adjust indicative prices near auctions to achieve nearly diffusive outcomes.
problem Achieving diffusive price behavior in Paris Stock Exchange auctions.
method Analyzing the diffusive properties of indicative auction prices and the strategic behavior of traders.
result Strategic traders adjust their order submission times to achieve nearly diffusive price behavior.
A reinforcement learning framework combining value function and tree search planner for strategic and tactical decisions.
problem Strategic and tactical decision-making in discrete environments.
method Combines value function and tree search planner, using uncertainty modeling and risk measurement.
result Improves performance and learning speed on hard exploration environments.
Study identifies a Strategic Gap in market efficiency due to AI-driven timing and complexity in disclosure.
problem Market inefficiency due to structural influence of disclosure timing and complexity.
method Introduces Autonomous Disclosure Regulator, a multi-node AI framework to audit disclosure complexity and unpredictability.
result Companies use confusing language and unpredictable timing to slow down market learning, creating a 60% Structural Gap.
We study a strategic version of the multi-armed bandit problem, where each arm is an individual strategic agent and we, the principal, pull one arm each round. When pulled, the arm receives some private reward v a v_a v a and can choose an amount x a x_a x a to pass on to the principal (keeping v a − x a v_a-x_a v a − x a for itself). All non-pulle…
COBRA addresses strategic behavior in online platforms by ensuring truthful reporting without monetary incentives.
problem Ensuring truthful reporting from strategic agents in online platforms.
method Proposes COBRA, an algorithm for contextual bandits involving strategic agents that disincentivizes strategic behavior.
result COBRA achieves sub-linear regret guarantee and incentive compatibility without monetary incentives.
The paper analyzes strategic behavior in reinsurance transactions leading to Nash equilibria.
problem Strategic behavior in reinsurance transactions affecting risk aversion and welfare gains.
method Identifying Nash equilibria within a class of risk measures.
result At strictly beneficial Nash equilibria, agents appear homogeneous in risk preferences.
Optimizes decisions under strategic individual behavior.
problem Optimal decision-making in strategic environments.
method Characterizes strategic effort, identifies optimal policies under monotonic cost assumptions, develops iterative search algorithm.
result Demonstrates higher utility of decision policies accounting for strategic behavior.
Market-maker optimizes quotes based on strategic market-takers' behavior.
problem Optimizing market-making strategies in a strategic trading environment.
method Mean-field game approach to model strategic market-takers and derive optimal controls.
result Derivation of optimal controls for market-maker and market-taker.