arXiv subjects

Bo Waggoner

Publications and source records attributed to Bo Waggoner.

At least 19 recordsLinked to original sources

arXiv2026

Sample Complexity of Peer Prediction

Peer prediction seeks to incentivize agents to truthfully report an observed signal by rewarding joint sets of reports without observing a ground truth. Following the generalization of information-theoretic mutual information introduced in Kong and Schoenebeck (2019), we call a function of a joint distribution over signals a mutual information when it is non-negative and disincentivizes garbling reports for all information structures. An unbiased estimator for a mutual information takes some number of samples from the distribution and returns rewards for both agents, such that the expected reward is equal to the mutual information. We seek to characterize the set of mutual informations with unbiased estimators for a given number of samples. We show that for three or fewer sampled report pairs, the only mutual information with an unbiased estimator is trivially zero, and for four or five samples with a binary report space, the Determinant Mutual Information (DMI) of Kong (2024) is the unique mutual information (up to a scalar multiple). We further show that DMI ceases to be unique at six samples. We provide an improved estimator of DMI for any given number of samples and characterize its convergence rate. We also examine mutual information estimators that accept a randomized number of samples. First, we show that mutual information estimators on an ex-ante bounded number of samples (termed "stop-short estimators") can achieve a lower variance than an equivalent fixed-sample estimator (for DMI). Second, we introduce the class of scoring-rule-based mutual informations and identify in this family a mutual information that can be estimated with under three samples in expectation.

cs.IT↗

arXiv2026

Adaptive Liquidity in Prediction Markets via Online Learning

Prediction markets rely on liquidity to convert trades into informative prices, yet existing mechanisms fix liquidity ex ante. This restriction enforces a static trade-off between price responsiveness and worst-case loss despite inherently nonstationary trading conditions. We propose a fundamentally different approach that treats liquidity selection itself as an online learning problem. Our mechanism mixes a family of cost-function markets via learnable weights, yielding a single adaptive market that preserves no-arbitrage, bounded worst-case loss, expressiveness, and positive upside. We introduce a hybrid structural risk signal, a per-round objective that quantifies the trade-off between price impact and inventory risk, and show that standard online learning algorithms achieve switching-regret guarantees relative to the best sequence of liquidity regimes in hindsight. Simulations demonstrate that the mechanism adaptively shifts liquidity across regimes in response to both order flow and inventory dynamics. Our results establish a principled framework for adaptive liquidity, connecting prediction market design with online learning.

cs.GT↗

arXiv2025

Robust forecast aggregation via additional queries

We study the problem of robust forecast aggregation: combining expert forecasts with provable accuracy guarantees compared to the best possible aggregation of the underlying information. Prior work shows strong impossibility results, e.g. that even under natural assumptions, no aggregation of the experts' individual forecasts can outperform simply following a random expert (Neyman and Roughgarden, 2022). In this paper, we introduce a more general framework that allows the principal to elicit richer information from experts through structured queries. Our framework ensures that experts will truthfully report their underlying beliefs, and also enables us to define notions of complexity over the difficulty of asking these queries. Under a general model of independent but overlapping expert signals, we show that optimal aggregation is achievable in the worst case with each complexity measure bounded above by the number of agents $n$. We further establish tight tradeoffs between accuracy and query complexity: aggregation error decreases linearly with the number of queries, and vanishes when the "order of reasoning" and number of agents relevant to a query is $\omega(\sqrt{n})$. These results demonstrate that modest extensions to the space of expert queries dramatically strengthen the power of robust forecast aggregation. We therefore expect that our new query framework will open up a fruitful line of research in this area.

cs.GT↗

arXiv2025

Efficiency of Constant Log Utility Market Makers

Automated Market Makers (AMMs) are used to provide liquidity for combinatorial prediction markets that would otherwise be too thinly traded. They offer both buy and sell prices for any of the doubly exponential many possible securities that the market can offer. The problem of setting those prices is known to be #P-hard for the original and most well-known AMM, the logarithmic market scoring rule (LMSR) market maker [Chen et al., 2008]. We focus on another natural AMM, the Constant Log Utility Market Maker (CLUM). Unlike LMSR, whose worst-case loss bound grows with the number of outcomes, CLUM has constant worst-case loss, allowing the market to add outcomes on the fly and even operate over countably infinite many outcomes, among other features. Simpler versions of CLUM underpin several Decentralized Finance (DeFi) mechanisms including the Uniswap protocol that handles billions of dollars of cryptocurrency trades daily. We first establish the computational complexity of the problem: we prove that pricing securities is #P-hard for CLUM, via a reduction from the model counting 2-SAT problem. In order to make CLUM more practically viable, we propose an approximation algorithm for pricing securities that works with high probability. This algorithm assumes access to an oracle capable of determining the maximum shares purchased of any one outcome and the total number of outcomes that has that maximum amount purchased. We then show that this oracle can be implemented in polynomial time when restricted to interval securities, which are used in designing financial options.

cs.GT↗

arXiv2025

Smooth Quadratic Prediction Markets

When agents trade in a Duality-based Cost Function prediction market, they collectively implement the learning algorithm Follow-The-Regularized-Leader. We ask whether other learning algorithms could be used to inspire the design of prediction markets. By decomposing and modifying the Duality-based Cost Function Market Maker's (DCFMM) pricing mechanism, we propose a new prediction market, called the Smooth Quadratic Prediction Market, the incentivizes agents to collectively implement general steepest gradient descent. Relative to the DCFMM, the Smooth Quadratic Prediction Market has a better worst-case monetary loss for AD securities while preserving axiom guarantees such as the existence of instantaneous price, information incorporation, expressiveness, no arbitrage, and a form of incentive compatibility. To motivate the application of the Smooth Quadratic Prediction Market, we independently examine agents' trading behavior under two realistic constraints: bounded budgets and buy-only securities. Finally, we provide an introductory analysis of an approach to facilitate adaptive liquidity using the Smooth Quadratic Prediction Market. Our results suggest future designs where the price update rule is separate from the fee structure, yet guarantees are preserved.

cs.LG↗

arXiv2025

Combinatorial Markov Search

A decisionmaker faces $n$ alternatives, each of which represents a potential reward. After investing costly resources into investigating the alternatives, the decisionmaker may select one, or more generally a feasible subset, and obtain the associated reward(s). The objective is to maximize the sum of rewards minus total costs invested. We consider this problem under a general model of an alternative as a "Markov Search Process," a type of undiscounted Markov Decision Process on a finite acyclic graph. Even simple cases generalize NP-hard problems such as Pandora's Box with nonobligatory inspection. Despite the apparently adaptive and interactive nature of the problem, we prove optimal prophet inequalities for this problem under a variety of combinatorial constraints. That is, we give approximation algorithms that interact with the alternatives sequentially, where each must be fully explored and either selected or else discarded before the next arrives. In particular, we obtain a computationally efficient $\frac{1}{2}-\epsilon$ prophet inequality for Combinatorial Markov Search subject to any matroid constraint. This result implies incentive-compatible mechanisms with constant Price of Anarchy for serving single-parameter agents when the agents strategically conduct independent, costly search processes to discover their values.

cs.GT↗

arXiv2024

Matching with Nested and Bundled Pandora Boxes

We consider max-weighted matching with costs for learning the weights, modeled as a "Pandora's Box" on each endpoint of an edge. Each vertex has an initially-unknown value for being matched to a neighbor, and an algorithm must pay some cost to observe this value. The goal is to maximize the total matched value minus costs. Our model is inspired by two-sided settings, such as matching employees to employers. Importantly for such settings, we allow for negative values which cause existing approaches to fail. We first prove upper bounds for algorithms in two natural classes. Any algorithm that "bundles" the two Pandora boxes incident to an edge is an $o(1)$-approximation. Likewise, any "vertex-based" algorithm, which uses properties of the separate Pandora's boxes but does not consider the interaction of their value distributions, is an $o(1)$-approximation. Instead, we utilize Pandora's Nested-Box Problem, i.e. multiple stages of inspection. We give a self-contained, fully constructive optimal solution to the nested-boxes problem, which may have structural observations of interest compared to prior work. By interpreting each edge as a nested box, we leverage this solution to obtain a constant-factor approximation algorithm. Finally, we show any "edge-based" algorithm, which considers the interactions of values along an edge but not with the rest of the graph, is also an $o(1)$-approximation.

cs.DS↗

arXiv2024

Public Projects with Preferences and Predictions

When making a decision as a group, there are two primary paradigms: aggregating preferences (e.g. voting, mechanism design) and aggregating information (e.g. discussion, consulting, forecasting). Almost all formally-studied group decisionmaking mechanisms fall under one paradigm or the other, but not both. We consider a public projects problem with the objective of maximizing utilitarian social welfare. Decisionmakers have both preferences, modeled as utility functions over the alternatives; and information, modeled as Bayesian signals relevant to the alternatives' external welfare impact. Aligning incentives is highly challenging because, on the one hand, agents can provide bad information in order to manipulate the mechanism into satisfying their preferences; and on the other hand, they can misreport their preferences to favor selection of an alternative for which their information rewards are high. We propose a two-stage mechanism for this problem. The forecasting stage aggregates information using either a wagering mechanism or a prediction market (the mechanism is modular and compatible with both). The voting stage aggregates preferences, together with the forecasts from the previous stage, and selects an alternative by leveraging the recently-studied Quadratic Transfers Mechanism. We show that, when carefully combined, the entire two-stage mechanism is robust to manipulation of all forms, and under weak assumptions, satisfies Price of Anarchy guarantees. In the case of two alternatives, the Price of Anarchy tends to 1 as natural measures of the "size" of the population grow large. In most cases, the mechanisms achieve a balanced budget as well. We also give the first nonasymptotic Price of Anarchy guarantee for the Quadratic Transfers Mechanism, a result of independent interest.

cs.GT↗

arXiv2024

Trading off Consistency and Dimensionality of Convex Surrogates for the Mode

In multiclass classification over $n$ outcomes, the outcomes must be embedded into the reals with dimension at least $n-1$ in order to design a consistent surrogate loss that leads to the "correct" classification, regardless of the data distribution. For large $n$, such as in information retrieval and structured prediction tasks, optimizing a surrogate in $n-1$ dimensions is often intractable. We investigate ways to trade off surrogate loss dimension, the number of problem instances, and restricting the region of consistency in the simplex for multiclass classification. Following past work, we examine an intuitive embedding procedure that maps outcomes into the vertices of convex polytopes in a low-dimensional surrogate space. We show that full-dimensional subsets of the simplex exist around each point mass distribution for which consistency holds, but also, with less than $n-1$ dimensions, there exist distributions for which a phenomenon called hallucination occurs, which is when the optimal report under the surrogate loss is an outcome with zero probability. Looking towards application, we derive a result to check if consistency holds under a given polytope embedding and low-noise assumption, providing insight into when to use a particular embedding. We provide examples of embedding $n = 2^{d}$ outcomes into the $d$-dimensional unit cube and $n = d!$ outcomes into the $d$-dimensional permutahedron under low-noise assumptions. Finally, we demonstrate that with multiple problem instances, we can learn the mode with $\frac{n}{2}$ dimensions over the whole simplex.

cs.LG↗

arXiv2023

Forecasting Competitions with Correlated Events

Beginning with Witkowski et al. [2022], recent work on forecasting competitions has addressed incentive problems with the common winner-take-all mechanism. Frongillo et al. [2021] propose a competition mechanism based on follow-the-regularized-leader (FTRL), an online learning framework. They show that their mechanism selects an $\epsilon$-optimal forecaster with high probability using only $O(\log(n)/\epsilon^2)$ events. These works, together with all prior work on this problem thus far, assume that events are independent. We initiate the study of forecasting competitions for correlated events. To quantify correlation, we introduce a notion of block correlation, which allows each event to be strongly correlated with up to $b$ others. We show that under distributions with this correlation, the FTRL mechanism retains its $\epsilon$-optimal guarantee using $O(b^2 \log(n)/\epsilon^2)$ events. Our proof involves a novel concentration bound for correlated random variables which may be of broader interest.

cs.LG↗

arXiv2023

An Axiomatic Characterization of CFMMs and Equivalence to Prediction Markets

Constant-function market makers (CFMMs), such as Uniswap, are automated exchanges offering trades among a set of assets. We study their technical relationship to another class of automated market makers, cost-function prediction markets. We first introduce axioms for market makers and show that CFMMs with concave potential functions characterize "good" market makers according to these axioms. We then show that every such CFMM on $n$ assets is equivalent to a cost-function prediction market for events with $n$ outcomes. Our construction directly converts a CFMM into a prediction market and vice versa. Conceptually, our results show that desirable market-making axioms are equivalent to desirable information-elicitation axioms, i.e., markets are good at facilitating trade if and only if they are good at revealing beliefs. For example, we show that every CFMM implicitly defines a proper scoring rule for eliciting beliefs; the scoring rule for Uniswap is unusual, but known. From a technical standpoint, our results show how tools for prediction markets and CFMMs can interoperate. We illustrate this interoperability by showing how liquidity strategies from both literatures transfer to the other, yielding new market designs.

cs.GT↗

arXiv2022

Proper losses for discrete generative models

We initiate the study of proper losses for evaluating generative models in the discrete setting. Unlike traditional proper losses, we treat both the generative model and the target distribution as black-boxes, only assuming ability to draw i.i.d. samples. We define a loss to be black-box proper if the generative distribution that minimizes expected loss is equal to the target distribution. Using techniques from statistical estimation theory, we give a general construction and characterization of black-box proper losses: they must take a polynomial form, and the number of draws from the model and target distribution must exceed the degree of the polynomial. The characterization rules out a loss whose expectation is the cross-entropy between the target distribution and the model. By extending the construction to arbitrary sampling schemes such as Poisson sampling, however, we show that one can construct such a loss.

cs.LG↗

arXiv2022

An Embedding Framework for the Design and Analysis of Consistent Polyhedral Surrogates

We formalize and study the natural approach of designing convex surrogate loss functions via embeddings, for problems such as classification, ranking, or structured prediction. In this approach, one embeds each of the finitely many predictions (e.g. rankings) as a point in $R^d$, assigns the original loss values to these points, and "convexifies" the loss in some way to obtain a surrogate. We establish a strong connection between this approach and polyhedral (piecewise-linear convex) surrogate losses: every discrete loss is embedded by some polyhedral loss, and every polyhedral loss embeds some discrete loss. Moreover, an embedding gives rise to a consistent link function as well as linear surrogate regret bounds. Our results are constructive, as we illustrate with several examples. In particular, our framework gives succinct proofs of consistency or inconsistency for various polyhedral surrogates in the literature, and for inconsistent surrogates, it further reveals the discrete losses for which these surrogates are consistent. We go on to show additional structure of embeddings, such as the equivalence of embedding and matching Bayes risks, and the equivalence of various notions of non-redudancy. Using these results, we establish that indirect elicitation, a necessary condition for consistency, is also sufficient when working with polyhedral surrogates.

cs.LG↗

arXiv2022

Balls and Bins -- Simple Concentration Bounds

Concentration bounds are given for throwing balls into bins independently according to a distribution $p$. The probability of a $k$-loaded bin after $m$ balls is shown to be controlled on both sides by $\rho_{m,k} := m \|p\|_k / k$. This gives concentration inequalities for the maximum load as well as for the waiting time until a $k$-loaded bin.

math.PR↗

arXiv2022

Contracts with Information Acquisition, via Scoring Rules

We consider a principal-agent problem where the agent may privately choose to acquire relevant information prior to taking a hidden action. This model generalizes two special cases: a classic moral hazard setting, and a more recently studied problem of incentivizing information acquisition (IA). We show that all of these problems can be reduced to the design of a proper scoring rule. Under a limited liability condition, we consider the special cases separately and then the general problem. We give novel results for the special case of IA, giving a closed form "pointed polyhedral cone" solution for the general multidimensional problem. We also describe a geometric, scoring-rules based solution to the case of the classic contracts problem. Finally, we give an efficient algorithm for the general problem of Contracts with Information Acquisition.

cs.GT↗

arXiv2022

High Welfare Matching Markets via Descending Price

We consider design of monetary mechanisms for two-sided matching. Mechanisms in the tradition of the deferred acceptance algorithm, even in variants incorporating money, tend to focus on the criterion of stability. Instead, in this work we seek a simple auction-inspired mechanism with social welfare guarantees. We consider a descending-price mechanism called the Marshallian Match, proposed (but not analyzed) by Waggoner and Weyl (2019). When all values for potential matches are positive, we show the Marshallian Match with a "rebate" payment rule achieves constant price of anarchy. This result extends to models with costs for acquiring information about one's values, and also to matching on hypergraphs. With possibly-negative valuations, which capture e.g. job markets, the problem becomes harder. We introduce notions of approximate stability and show that they have beneficial welfare implications. However, the main problem of proving constant factor welfare guarantees in "ex ante stable equilibrium" remains open.

cs.GT↗

arXiv2021

Agreement Implies Accuracy for Substitutable Signals

Inspired by Aumann's agreement theorem, Scott Aaronson studied the amount of communication necessary for two Bayesian experts to approximately agree on the expectation of a random variable. Aaronson showed that, remarkably, the number of bits does not depend on the amount of information available to each expert. However, in general the agreed-upon estimate may be inaccurate: far from the estimate they would settle on if they were to share all of their information. We show that if the experts' signals are \emph{substitutes} -- meaning the experts' information has diminishing marginal returns -- then it is the case that if the experts are close to agreement then they are close to the truth. We prove this result for a broad class of agreement and accuracy measures that includes squared distance and KL divergence. Additionally, we show that although these measures capture fundamentally different kinds of agreement, Aaronson's agreement result generalizes to them as well.

cs.GT↗

arXiv2021

Surrogate Regret Bounds for Polyhedral Losses

Surrogate risk minimization is an ubiquitous paradigm in supervised machine learning, wherein a target problem is solved by minimizing a surrogate loss on a dataset. Surrogate regret bounds, also called excess risk bounds, are a common tool to prove generalization rates for surrogate risk minimization. While surrogate regret bounds have been developed for certain classes of loss functions, such as proper losses, general results are relatively sparse. We provide two general results. The first gives a linear surrogate regret bound for any polyhedral (piecewise-linear and convex) surrogate, meaning that surrogate generalization rates translate directly to target rates. The second shows that for sufficiently non-polyhedral surrogates, the regret bound is a square root, meaning fast surrogate generalization rates translate to slow rates for the target. Together, these results suggest polyhedral surrogates are optimal in many cases.

cs.LG↗