David M Pennock

Web-based content analysis tasks, such as labeling toxicity, misinformation, or spam often rely on machine learning models to achieve cost and scale efficiencies. As these models impact real human lives, ensuring accuracy and fairness of such models is critical. However, maintaining the performance of these models over time can be challenging due to the temporal shifts in the application context and the sub-populations represented. Furthermore, there is often a delay in obtaining human expert labels for the raw data, which hinders the timely adaptation and safe deployment of the models. To overcome these challenges, we propose a novel approach that anticipates future distributions of data, especially in settings where unlabeled data becomes available earlier than the labels to estimate the future distribution of labels per sub-population and adapt the model preemptively. We evaluate our approach using …

IntroductionLe GM-CSF est un facteur de croissance essentiel pour la maturation des macrophages alvéolaires. Sa signalisation passe par l’activation d’une Janus Kinase 2 et la phosphorylation du facteur de transcription STAT5 mais celle-ci pourrait varier en fonction du microenvironnement et du stade de différenciation cellulaire. Nous avons comparé la signalisation intracellulaire du GM-CSF évaluée par la phosphorylation de STAT5 dans trois types cellulaires: monocytes circulants (MOs), macrophages dérivés des monocytes (MDMs) et macrophages pulmonaires humains (MPs).MéthodesLes MPs étaient obtenus après dissection de pièces d’exérèses chirurgicales puis adhérence au support de culture ou après digestion enzymatique et tri cellulaire par le cytomètre de flux CytoFlex SRT (Beckman Coulter©). Les MOs étaient isolés à partir des cellules mononuclées sanguines de donneurs sains et les MDMs …

IntroductionLes pneumopathies interstitielles diffuses (PID) constituent un groupe hétérogène de pathologies rares dont le pronostic est réservé. Peu d’options thérapeutiques existent pour les patients atteints d’une maladie pulmonaire fibrosante et l’existence d’un biomarqueur fiable et cliniquement pertinent manque dans leur prise en charge. Les polynucléaires éosinophiles de par leurs caractéristiques remarquables et notamment leur implication dans la fibrogenèse pourraient représenter un biomarqueur intéressant. Nous formulons l’hypothèse selon laquelle l’inflammation éosinophile pourrait être un trait traitable dans les PID fibrosantes.MéthodesNous avons réalisé une étude rétrospective monocentrique entre le 1/01/2017 et le 31/12/2022 analysant le taux d’éosinophiles sanguins chez des patients atteints de PID fibrosantes. La description de ce taux dans la population de l’étude a permis de déterminer …

We draw a surprising and direct mathematical equivalence between the class of fair division mechanisms, designed to allocate divisible goods without money, and the class of weakly budget-balanced wagering mechanisms, designed to elicit probabilities. Although this correspondence between fair division and wagering has applications in both settings, we focus on its implications for the design of incentive-compatible fair division mechanisms. In particular, we show that applying the correspondence to competitive scoring rules, a prominent class of wagering mechanisms based on proper scoring rules, yields the first incentive-compatible fair division mechanism that is both fair (proportional and envy-free) and responsive to agent preferences. Moreover, for two agents, we show that competitive scoring rules characterize the whole class of nonwasteful and incentive-compatible fair division mechanisms, subject to …

Participatory democracy aims to make democratic processes more engaging and responsive by giving all citizens the opportunity to participate, and express their preferences, at many stages of decision-making processes beyond electing representatives. Recent years have witnessed an increasing interest in participatory democracy systems, enabled by modern information and communication technology. Participation at scale gives rise to a number of algorithmic challenges. In this seminar, we addressed these challenges by bringing together experts from computational social choice (COMSOC) and related fields. In particular, we studied algorithms for online decision-making platforms and for participatory budgeting processes. We also explored how innovations such as prediction markets, liquid democracy, quadratic voting, and blockchain can be employed to improve participatory decision-making systems. Seminar July 3–8, 2022–http://www. dagstuhl. de/22271 2012 ACM Subject Classification Applied computing→ Law, social and behavioral sciences; Theory of computation→ Algorithmic game theory and mechanism design

IntroductionLe GM-CSF (Granulocyte-Macrophage Colony Stimulating Factor) est un facteur de croissance essentiel pour l’homéostasie pulmonaire et un médiateur de l’inflammation tissulaire. Des stratégies de blocage du GM-CSF sont développées pour traiter certaines pathologies inflammatoires chroniques. Leurs effets sur les cellules pulmonaires sont encore mal évalués. Nous avons étudié et comparé in vitro les effets de traitements ciblant la voie du GM-CSF: anticorps monoclonal (mAb anti GM-CSF) et ruxolitinib (inhibiteur de Janus Kinase 1/2) sur la signalisation intracellulaire évaluée par la phosphorylation de STAT5 (pSTAT5) dans des macrophages pulmonaires humains (MPs), des macrophages dérivés des monocytes (MDMs) et des monocytes circulants (MOs).MéthodesLe tissu pulmonaire est issu de pièces d’exérèses chirurgicales et les MPs sont obtenus après dissection puis adhérence au …

We present a prototype hybrid prediction market and demonstrate the avenue it represents for meaningful human-AI collaboration. We build on prior work proposing artificial prediction markets as a novel machine learning algorithm. In an artificial prediction market, trained AI agents (bot traders) buy and sell outcomes of future events. Classification decisions can be framed as outcomes of future events, and accordingly, the price of an asset corresponding to a given classification outcome can be taken as a proxy for the systems confidence in that decision. By embedding human participants in these markets alongside bot traders, we can bring together insights from both. In this paper, we detail pilot studies with prototype hybrid markets for the prediction of replication study outcomes. We highlight challenges and opportunities, share insights from semi-structured interviews with hybrid market participants, and outline a vision for ongoing and future work.

We initiate the study of incentive-compatible forecasting competitions in which multiple forecasters make predictions about one or more events and compete for a single prize. We have two objectives: (1) to incentivize forecasters to report truthfully and (2) to award the prize to the most accurate forecaster. Proper scoring rules incentivize truthful reporting if all forecasters are paid according to their scores. However, incentives become distorted if only the best-scoring forecaster wins a prize, since forecasters can often increase their probability of having the highest score by reporting more extreme beliefs. In this paper, we introduce two novel forecasting competition mechanisms. Our first mechanism is incentive compatible and guaranteed to select the most accurate forecaster with probability higher than any other forecaster. Moreover, we show that in the standard single-event, two-forecaster setting and under mild …

Participatory democracy aims to make democratic processes more engaging and responsive by giving all citizens the opportunity to participate, and express their preferences, at many stages of decision-making processes beyond electing representatives. Recent years have witnessed an increasing interest in participatory democracy systems, enabled by modern information and communication technology. Participation at scale gives rise to a number of algorithmic challenges. In this seminar, we addressed these challenges by bringing together experts from computational social choice (COMSOC) and related fields. In particular, we studied algorithms for online decision-making platforms and for participatory budgeting processes. We also explored how innovations such as prediction markets, liquid democracy, quadratic voting, and blockchain can be employed to improve participatory decision-making systems.

Introduction GM-CSF (Granulocyte-Macrophage Colony Stimulating Factor) is an essential growth factor for pulmonary homeostasis and a mediator of tissue inflammation. Strategies to block GMCSF are being developed to treat chronic inflammatory diseases. Their effects on lung cells are still poorly evaluated. Objectives We compared in vitro the effects of treatments targeting the GM-CSF pathway: monoclonal antibody (anti GM-CSF mAb) and ruxolitinib (Janus Kinase 1/2 inhibitor) on STAT5 phosphorylation (pSTAT5) in human lung macrophages (LMs), monocyte-derived macrophages (MDMs) and circulating monocytes (MOs). We evaluated their effects on human LMs functions (cytokine production, phagocytosis). Methods Lung tissue was obtained from pieces of lobectomy. LMs were were obtained after dissection and adhesion to the culture medium. MOs were from healthy donors PBMCs and MDMs were …

Optimal auction design is one of the most well-studied and fundamental problems in (algorithmic) mechanism design. In the traditional Myersonian [57] setting, an auctioneer has a single item for sale and there are n interested bidders. Each bidder has a (private) valuation for the item which, intuitively, represents the amount of money they are willing to spend to buy it. The standard Bayesian approach is to assume that the seller has only an incomplete knowledge of these valuations, in the form of a prior joint distribution F. A selling mechanism receives bids from the buyers and then decides to whom the item should be allocated (which, in general, can be a randomized rule) and for what price. The goal is to design a truthful1 selling mechanism that maximizes the auctioneer’s revenue, in expectation over F.Myerson [57] provided a complete and very elegant solution for this problem when bidder valuations are …

EC 2022 Foreword — Rutgers, The State University of New Jersey Skip to main navigation Skip to search Skip to main content Rutgers, The State University of New Jersey Home Rutgers, The State University of New Jersey Logo Help & FAQ Home Profiles Research units Core Facilities Federal Grants Research output Search by expertise, name or affiliation EC 2022 Foreword David M. Pennock, Ilya Segal, Sven Seuken School of Arts and Sciences, Computer Science Research output: Contribution to journal › Editorial › peer-review Overview Original language English (US) Pages (from-to) III-VI Journal EC 2022 - Proceedings of the 23rd ACM Conference on Economics and Computation State Published - Jul 12 2022 Event 23rd ACM Conference on Economics and Computation, EC 2022 - Boulder, United States Duration: Jul 11 2022 → Jul 15 2022 All Science Journal Classification (ASJC) codes Computer Science …

We study the role of information structures in mechanism design problems with limited commitment. In each period, a principal offers a ''spot'' contract to a privately informed agent without committing to future spot contracts, and the agent responds to the contract. In contrast to the classical approach in which the information structure is fixed, we allow for all admissible information structures. We represent the information structure as a fictitious mediator and re-interpret the model as a mechanism design problem by the mediator with commitment. The mediator collects the agent's private information and then, in each period, privately recommends the principal's spot contract and the agent's response in an incentive-compatible manner (both in truth-telling and obedience). We construct several examples to clarify why new equilibrium outcomes can arise once we allow for general information structures. We next develop a durable-good monopoly application. We show that trading outcomes and welfare consequences can substantially differ from those in the classical model with a fixed information structure. In the seller-optimal mechanism, the seller offers a discounted price to the high-valuation buyer only in the initial period, followed by the high, surplus-extracting price until some endogenous deadline, when the buyer's information is revealed and hence fully extracted. As a result, the Coase conjecture fails: even in the limiting case of perfect patience, the seller makes a positive surplus, and the trading outcome is not the first best. We also characterize mediated and unmediated implementation of the seller-optimal outcome.

Explainably estimating confidence in published scholarly work offers opportunity for faster and more robust scientific progress. We develop a synthetic prediction market to assess the credibility of published claims in the social and behavioral sciences literature. We demonstrate our system and detail our findings using a collection of known replication projects. We suggest that this work lays the foundation for a research agenda that creatively uses AI for peer review.

Despite high-profile successes in the field of Artificial Intelligence, machine-driven technologies still suffer important limitations, particularly for complex tasks where creativity, planning, common sense, intuition, or learning from limited data is required. These limitations motivate effective methods for human-machine collaboration. Our work makes two primary contributions. We thoroughly experiment with an artificial prediction market model to understand the effects of market parameters on model performance for benchmark classification tasks. We then demonstrate, through simulation, the impact of exogenous agents in the market, where these exogenous agents represent primitive human behaviors. This work lays the foundation for a novel set of hybrid human-AI machine learning algorithms.

The idealization of a static machine-learned model, trained once and deployed forever, is not practical. As input distributions change over time, the model will not only lose accuracy, any constraints to reduce bias against a protected class may fail to work as intended. Thus, researchers have begun to explore ways to maintain algorithmic fairness over time. One line of work focuses on dynamic learning: retraining after each batch, and the other on robust learning which tries to make algorithms robust against all possible future changes. Dynamic learning seeks to reduce biases soon after they have occurred and robust learning often yields (overly) conservative models. We propose an anticipatory dynamic learning approach for correcting the algorithm to mitigate bias before it occurs. Specifically, we make use of anticipations regarding the relative distributions of population subgroups (e.g., relative ratios of male and …

Financial options are contracts that specify the right to buy or sell an underlying asset at a strike price by an expiration date. Standard exchanges offer options of predetermined strike values and trade options of different strikes independently, even for those written on the same underlying asset. Such independent market design can introduce arbitrage opportunities and lead to the thin market problem. The paper first proposes a mechanism that consolidates and matches orders on standard options related to the same underlying asset, while providing agents the flexibility to specify any custom strike value. The mechanism generalizes the classic double auction, runs in time polynomial to the number of orders, and poses no risk to the exchange, regardless of the value of the underlying asset at expiration. Empirical analysis on real-market options data shows that the mechanism can find new matches for options of …

Introduction to the Special Issue on WINE'18: Part 2 — Rutgers, The State University of New Jersey Skip to main navigation Skip to search Skip to main content Rutgers, The State University of New Jersey Home Rutgers, The State University of New Jersey Logo Help & FAQ Home Profiles Research units Core Facilities Federal Grants Research output Search by expertise, name or affiliation Introduction to the Special Issue on WINE'18: Part 2 David Pennock, Ilya Segal Research output: Contribution to journal › Editorial › peer-review Overview Original language English (US) Article number 9 Journal ACM Transactions on Economics and Computation Volume 9 Issue number 2 DOIs https://doi.org/10.1145/3447512 State Published - May 2021 Externally published Yes All Science Journal Classification (ASJC) codes Computer Science (miscellaneous) Statistics and Probability Economics and Econometrics Marketing …

We design a prediction market to recover a complete and fully general probability distribution over a random variable. Traders buy and sell interval securities that pay \$1 if the outcome falls into an interval and \$0 otherwise. Our market takes the form of a central automated market maker and allows traders to express interval endpoints of arbitrary precision. We present two designs in both of which market operations take time logarithmic in the number of intervals (that traders distinguish), providing the first computationally efficient market for a continuous variable. Our first design replicates the popular logarithmic market scoring rule (LMSR), but operates exponentially faster than a standard LMSR by exploiting its modularity properties to construct a balanced binary tree and decompose computations along the tree nodes. The second design consists of two or more parallel LMSR market makers that mediate submarkets of increasingly fine-grained outcome partitions. This design remains computationally efficient for all operations, including arbitrage removal across submarkets. It adds two additional benefits for the market designer: (1) the ability to express utility for information at various resolutions by assigning different liquidity values, and (2) the ability to guarantee a true constant bounded loss by appropriately decreasing the liquidity in each submarket.

Prediction markets are a way to yield probabilistic predictions about future events, theoretically incorporating all available information. In this paper, we focus on the confidence that we should place in the prediction of a market. When should we believe that the market probability meaningfully reflects underlying uncertainty, and when should we not? We discuss two notions of confidence. The first is based on the expected profit that a trader could make from correcting the market if it were wrong, and the second is based on expected market volatility in the future. Our paper is a stepping stone to future work in this area, and we conclude by discussing some key challenges.