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.
Proposes RNSE for clustering with adaptive similarity matrix learning.
problem Sub-optimal results due to mismatch between stages in Spectral Clustering.
method End-to-end single-stage learning with adaptive similarity matrix and non-negative constraints.
result Superior clustering performance on synthetic and real-world datasets.
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. Study examines auditing fairness in evolving models, identifying strategic updates that preserve audit properties.
problem Auditing fairness in machine learning models that adapt to changing environments.
method Characterizes strategic updates that preserve audit properties, proposes a generic PAC auditing framework.
result Establishes distribution-free auditing bounds for statistical parity using the SP dimension.
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.
We study revenue optimization learning algorithms for repeated second-price auctions with reserve where a seller interacts with multiple strategic bidders each of which holds a fixed private valuation for a good and seeks to maximize his expected future cumulative discounted surplus. We propose a novel algorithm that h…
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.
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.
Modeling dealer competition, internalisation and externalisation impact market dynamics and costs.
problem Understanding and optimizing dealer competition in risky asset markets.
method Variational approach to derive Nash equilibrium for dealer competition.
result Dealers using internalisation are incentivized to increase externalisation, leading to higher hedging costs and wider spreads.
SANE improves exploration of noisy, multimodal functions by finding multiple optima.
problem Finding multiple optima in noisy, non-differentiable functions.
method Strategic Autonomous Non-Smooth Exploration (SANE) with a cost-driven acquisition function and human knowledge gate.
result SANE outperforms classical Bayesian optimization in discovering multiple optima.
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.
A new approach RA improves stochastic optimization by executing multiple steps between subsample updates.
problem Improving the efficiency and effectiveness of stochastic optimization methods.
method Developed Retrospective Approximation (RA) which executes multiple steps between subsample updates using a deterministic solver.
result RA achieves almost sure and L 1 L_1 L 1 consistency under weak conditions and optimizes iteration and oracle complexity. Study on optimizing model updates in performative prediction.
problem Optimizing model updates influenced by model predictions.
method Stochastic optimization with greedy and lazy deploy approaches.
result Rates of convergence for both greedy and lazy deploy methods.
This work explains crises in markets without external news using bounded rational agents.
problem Inability to model out-of-equilibrium dynamics in economic markets.
method Modeling bounded rational strategic reasoning in multi-agent market games.
result Bounded rational strategic reasoning can lead to endogenously emerging crises.
Paper proves multiplicative weight updates can train neural networks without learning rate tuning.
problem Vanishing and exploding gradients in gradient descent for compositional functions.
method Proves descent lemma for compositional functions using multiplicative weight updates and derives Madam optimizer.
result Madam optimizer trains state-of-the-art neural networks without learning rate tuning.
We introduce a new class of context dependent, incomplete information games to serve as structured prediction models for settings with significant strategic interactions. Our games map the input context to outcomes by first condensing the input into private player types that specify the utilities, weighted interactions…
The (stochastic) gradient descent and the multiplicative update method are probably the most popular algorithms in machine learning. We introduce and study a new regularization which provides a unification of the additive and multiplicative updates. This regularization is derived from an hyperbolic analogue of the entr…
New algorithms reduce matching regret by limiting frequent updates.
problem Minimizing regret in stochastic matching with rare optimization updates.
method Batched algorithms that limit matching updates to Θ(log log T) rounds.
result Achieve a regret bound of \(\widetilde{\mathcal{O}}(\sqrt{T})\) with reduced computational cost.
In this letter, we generalize the convolutional NMF by taking the β β β -divergence as the contrast function and present the correct multiplicative updates for its factors in closed form. The new updates unify the β β β -NMF and the convolutional NMF. We state why almost all of the existing updates are inexact and approximat…
Study optimizes resource allocation in noisy systems for better control.
problem Limited attention in stochastic systems with multiplicative noise.
method Analytical and numerical methods for optimal attention allocation.
result Effective resource allocation enhances noise estimation and control decisions.
This paper uses Thompson sampling to optimize portfolio selection.
problem Difficulty in estimating parameters for Markowitz's mean-variance optimization.
method Portfolio bandit strategy using Thompson sampling.
result Optimal investment portfolio can adapt to different investment periods.
A new pricing strategy minimizes regret by controlling strategic buyer behavior.
problem Designing a pricing policy for strategic buyers with limited seller information.
method Phased-structure policy with randomized isolation periods.
result Regret of T T T -period O ~ ( T ) \widetilde{\mathcal{O}}(\sqrt{T}) O ( T ) against a benchmark policy. 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.
In this paper, we extend the β β β -CNMF to two dimensions and derive exact multiplicative updates for its factors. The new updates generalize and correct the nonnegative matrix factor deconvolution previously proposed by Schmidt and Mørup. We show by simulation that the updates lead to a monotonically decreasing β β β -dive…
Fewer data weight updates lead to faster convergence in machine learning models.
problem Improving robustness of machine learning models through data mixing.
method Analyzing convergence behavior of data mixing with a finite number of inner steps.
result The optimal number of inner steps scales with the budget and type of gradients used.
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.
MpFL models clients as strategic players to reach equilibrium with less communication.
problem Real-world clients act independently with individual objectives, not aligned with a shared global model.
method MpFL uses game-theoretic modeling and PEARL-SGD algorithm for local updates and communication.
result PEARL-SGD reaches an equilibrium with less communication than non-local updates in stochastic setup.
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.
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.
New algorithm for online optimization over symmetric cones, unifying previous methods.
problem Online convex optimization over symmetric cones.
method Symmetric-Cone Multiplicative Weights Update (SCMWU) algorithm.
result SCMWU is a no-regret algorithm.
DefogGAN predicts hidden RTS game information to aid strategic decision-making.
problem Predicting hidden information in real-time strategy games like StarCraft.
method Conditional Generative Adversarial Network (GAN) with pyramidal reconstruction loss.
result DefogGAN predicts enemy buildings and combat units as accurately as professional players.
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.
We consider the problem of Probably Approximate Correct (PAC) learning of a binary classifier from noisy labeled examples acquired from multiple annotators (each characterized by a respective classification noise rate). First, we consider the complete information scenario, where the learner knows the noise rates of all…
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. DMLE improves active learning by correcting MLE for sample dependencies.
problem Dependencies among samples in active learning affect model parameter estimation.
method Dependency-aware Maximum Likelihood Estimation (DMLE).
result DMLE achieves superior performance across multiple benchmark datasets.
Study strategic competition in commodity markets using impulse-switching controls.
problem Strategic competition between upstream and downstream firms in commodity markets.
method Non-zero-sum stochastic differential game with mixed impulse/switching controls.
result Multiple Nash equilibria found, depending on the number of switches by the downstream firm.
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.
Consequential decision-making typically incentivizes individuals to behave strategically, tailoring their behavior to the specifics of the decision rule. A long line of work has therefore sought to counteract strategic behavior by designing more conservative decision boundaries in an effort to increase robustness to th…
LD-SGD improves communication in decentralized SGD.
problem Efficiently combining local updates and decentralized communication.
method Proposes LD-SGD integrating local updates and decentralized SGD, with a convergence analysis.
result LD-SGD converges to a critical point for non-convex objectives with non-identically distributed data.
Calibrated models can lead to miscalibrated aggregations in strategic interactions.
problem Miscalibration in aggregated predictions from multiple calibrated models.
method Analysis of strategic interactions between calibrated predictors, proving conditions for miscalibration and comparing VCG and Brier-score aggregation methods.
result VCG aggregation method outperforms Brier-score in strategic settings, providing robustness and comparable accuracy.
Study explores optimal strategies in games with multiple players and mean-field interactions.
problem Optimal strategies in games with multiple players and mean-field interactions.
method Exploration of three different notions of optimality, including mean-field control solution, mean-field coarse correlated equilibria, and mean-field Nash equilibria.
result Approximation of cooperative and competitive equilibria in large N N N -player games by mean-field control and mean-field equilibria. 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.
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. 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.
This paper optimizes brokerage contracts for multiple clients trading a single asset.
problem Optimizing brokerage contracts for multiple clients trading a single asset.
method Endogenously determines clients' reservation values and strategically chooses clients. Characterizes optimal portfolios computationally.
result Characterizes optimal portfolios of clients and their profits, showing dependence on price impact coefficients.
Online learning makes sequence of decisions with partial data arrival where next movement of data is unknown. In this paper, we have presented a new technique as multiple times weight updating that update the weight iteratively forsame instance. The proposed technique analyzed with popular state-of-art algorithms from …