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.
We study incentivized exploration for the multi-armed bandit (MAB) problem where the players receive compensation for exploring arms other than the greedy choice and may provide biased feedback on reward. We seek to understand the impact of this drifted reward feedback by analyzing the performance of three instantiatio…
We propose a contextual bandit based model to capture the learning and social welfare goals of a web platform in the presence of myopic users. By using payments to incentivize these agents to explore different items/recommendations, we show how the platform can learn the inherent attributes of items and achieve a subli…
We study platforms in the sharing economy and discuss the need for incentivizing users to explore options that otherwise would not be chosen. For instance, rental platforms such as Airbnb typically rely on customer reviews to provide users with relevant information about different options. Yet, often a large fraction o…
As researchers and practitioners of applied machine learning, we are given a set of requirements on the problem to be solved, the plausibly obtainable data, and the computational resources available. We aim to find (within those bounds) reliably useful combinations of problem, data, and algorithm. An emphasis on algori…
Game theory models incentivizes honesty in collaborative learning among competitors.
problem Incentivizing honest updates among competitors in collaborative learning schemes.
method Formulated a game to model interactions, studied two learning tasks, proposed mechanisms to incentivize honest communication.
result Rational clients are incentivized to manipulate their updates, preventing learning; proposed mechanisms ensure comparable learning quality to full cooperation.
An algorithmic decision-maker incentivizes people to act in certain ways to receive better decisions. These incentives can dramatically influence subjects' behaviors and lives, and it is important that both decision-makers and decision-recipients have clarity on which actions are incentivized by the chosen model. While…
Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and simulation. However, most of these formulations either get stuck in environments with stochastic dynamics or are too inefficient to be scalable t…
Achieving efficient and scalable exploration in complex domains poses a major challenge in reinforcement learning. While Bayesian and PAC-MDP approaches to the exploration problem offer strong formal guarantees, they are often impractical in higher dimensions due to their reliance on enumerating the state-action space.…
Consequential decision-making incentivizes individuals to strategically adapt their behavior to the specifics of the decision rule. While a long line of work has viewed strategic adaptation as gaming and attempted to mitigate its effects, recent work has instead sought to design classifiers that incentivize individuals…
In this paper we introduce a simple approach for exploration in reinforcement learning (RL) that allows us to develop theoretically justified algorithms in the tabular case but that is also extendable to settings where function approximation is required. Our approach is based on the successor representation (SR), which…
The paper proposes incentivizing human annotators with 'golden questions' to improve data quality.
problem Ensuring high-quality human annotations for training large language models.
method A principal-agent model is used to incentivize annotators with bonuses based on the maximum likelihood estimators (MLE) of their annotations. Hypothesis testing is applied to monitor the annotators' performance.
result The hypothesis testing rate for the principal-agent model is of Θ(1/nlogn), highlighting the importance of 'golden questions' for monitoring annotators.
Corporate venture capital is in the midst of a renaissance. The end of 2015 marked all-time highs both in the number of corporate firms participating in VC deals and in the amount of capital being deployed by corporate VCs. This paper explores, rather than defines, how these firms find success in the wake of this sudde…
We present an adversarial active exploration for inverse dynamics model learning, a simple yet effective learning scheme that incentivizes exploration in an environment without any human intervention. Our framework consists of a deep reinforcement learning (DRL) agent and an inverse dynamics model contesting with each …
User engagement in social networks depends critically on the number of online actions their users take in the network. Can we design an algorithm that finds when to incentivize users to take actions to maximize the overall activity in a social network? In this paper, we model the number of online actions over time usin…
We study an online multi-task learning setting, in which instances of related tasks arrive sequentially, and are handled by task-specific online learners. We consider an algorithmic framework to model the relationship of these tasks via a set of convex constraints. To exploit this relationship, we design a novel algori…
Prior work on training generative Visual Dialog models with reinforcement learning(Das et al.) has explored a Qbot-Abot image-guessing game and shown that this 'self-talk' approach can lead to improved performance at the downstream dialog-conditioned image-guessing task. However, this improvement saturates and starts d…
This work models GHG offset credit markets to find optimal strategies for market participants.
problem Optimizing GHG offset credit markets to reduce emissions and penalize excess emissions.
method Characterized optimal behavior in single-player and two-player GHG offset credit markets using optimal stopping and control problems, and mixed-Nash equilibria.
result Market participants benefit from optimal OC trading and generation, highlighting the importance of acting optimally.
This paper addresses reward estimation and incentive design for agents with hidden rewards.
problem Estimating and incentivizing agents with unknown rewards in a learning setting.
method Repeated adverse selection game with a self-interested learning agent and a learning principal. Introduces an estimator for consistent reward estimation and a data-driven incentive policy.
result Finite-sample consistency of the estimator and a rigorous regret bound for the principal.
Paper explores how to design federated learning protocols that benefit all participants while maintaining privacy.
problem Privacy concerns undermine the accuracy benefits of federated learning in privacy-sensitive domains.
method The paper provides conditions for mutually beneficial federated learning protocols and designs protocols that maximize total utility and accuracy.
result The paper demonstrates that federated learning can be designed to be mutually beneficial, striking a balance between privacy and model accuracy.
We propose and study the known-compensation multi-arm bandit (KCMAB) problem, where a system controller offers a set of arms to many short-term players for T steps. In each step, one short-term player arrives to the system. Upon arrival, the player aims to select an arm with the current best average reward and receiv…
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.
SREC markets are a relatively novel market-based system to incentivize the production of energy from solar means. A regulator imposes a floor on the amount of energy each regulated firm must generate from solar power in a given period and provides them with certificates for each generated MWh. Firms offset these certif…
We consider a fundamental dynamic allocation problem motivated by the problem of securities lending in financial markets, the mechanism underlying the short selling of stocks. A lender would like to distribute a finite number of identical copies of some scarce resource to n clients, each of whom has a priv…
Classification-as-a-Service (CaaS) is widely deployed today in machine intelligence stacks for a vastly diverse set of applications including anything from medical prognosis to computer vision tasks to natural language processing to identity fraud detection. The computing power required for training complex models on l…