online marketing teams

Abstract: Conversational bandits improve recommendations by actively querying users about key-terms to elicit their item preferences. However, existing methods typically assume homogeneous feedback for items and key-terms, using either absolute rewards or pairwise comparisons. In practice, item feedback often takes the form of clicks or ratings, while comparisons are more natural for key-terms. To address this gap, we study conversational generalized linear bandits with hybrid feedback, combining absolute item rewards and relative key-term comparisons. We propose Conversational UCB with Hybrid Feedback (HyConUCB), which constructs unified confidence bounds from heterogeneous feedback and adaptively selects key-term comparisons by balancing information gain and directional coverage. Through a refined regret analysis that jointly exploits both feedback sources, we establish a regret bound that improves upon reward-only and adapted dueling-only benchmarks. Experiments on synthetic and real-world datasets validate the effectiveness of our algorithm.

Abstract: Agentic recommendation pursues shopper goals through sequences of context-dependent decisions. Developing and evaluating such policies requires faithful recommendation world models that capture both the interactive shopping environment and users' behavioral responses over long interactions. Existing resources rarely provide long-horizon, fine-grained real-user trajectories or support trajectory-level evaluation and offline validation against production A/B results. We introduce UserArena, a real-world e-commerce interactive benchmark containing 64,729 session trajectories from 11,010 users, spanning 566,102 items and 13 action types. UserArena pairs these trajectories with an interactive environment and supports offline validation against outcomes from a controlled production A/B test, enabling five-level evaluation from output validity and local decisions to sequential behavior, personalization, and outcomes. To improve simulator fidelity over these long-horizon interactions, we further propose On-Policy Trajectory Distillation (OPTD), which uses trajectory-level intent to provide dense teacher targets on student-generated rollouts. Experiments show that OPTD achieves the strongest overall fidelity among the evaluated simulators under UserArena's evaluation protocol and most closely reproduces the production policy effect in offline simulation.

Abstract: The explosive growth of short videos has presented significant challenges to content governance. Traditional manual labeling is inefficient, slow to iterate, and costly. Therefore, we explore and develop a multi-stage autopilot labeling framework aimed at progressively increasing the level of automation in short video content annotation. To move beyond the heavy reliance on human expert labeling at the initial L0 stage, we first introduce a discriminative MLLM labeler at the L1 stage, which is fine-tuned with supervised data to directly predict labels for short videos. Advancing to the L2 stage, we shift to a domain-adaptive MLLM pretrained on short video data and use it for zero-shot labeling, enabling flexible generalization without task-specific supervision. In the L3 stage, we propose an agentic annotation workflow, and equip the agent with several key tools, which empower the agent to handle complex, unfamiliar, or vaguely defined cases, significantly reducing the need for human intervention. We conduct extensive experiments across various content issues, and results demonstrate that each stage of the autopilot labeling framework progressively improves labeling accuracy, and has significantly reduced manual labor costs in real-world applications by up to 85%.

Abstract: Many social applications of machine learning exhibit performative effects: population behavior changes in response to deployed models. Performative prediction studies this interaction through a distribution map that relates each model to the population distribution it induces. One of the main results in this framework showed that repeated risk minimization (RRM), which updates models by retraining on the most recent data, can converge to a stable model that minimizes risk on its own induced distribution. However, existing analyses typically assume access to the complete distributions of features and labels after model deployment, ignoring the possibility of selective labels: observing labels only for the accepted subset of the population. In this work, we formalize performative prediction with selective labels and show that retraining only on observed data can misguide the retraining procedure and undermine the guarantees of convergence to a stable solution. We then propose a worst-case objective based on knowledge of a confidence interval on the probability of a positive label. Applying RRM to this objective permits us to remain within a bounded distance to the true stable point. Under a sensitivity assumption on the conditional label distribution, we further show how previously accepted data can tighten these confidence intervals over time. Experiments in a lending application with fairness regularization show that our robust optimization approach closely matches the performance of RRM with complete label access.

Abstract: Generative AI has dramatically accelerated the rate at which new treatments---from novel pharmaceuticals to online marketing campaigns---can be conceived and deployed. As a result, modern experimentation platforms often run continuously, with treatments added as they are ready and removed when they underperform. We formalize this "Always-On" experimental setting, in which treatments can be dynamically generated, added to, and removed from a running experiment, and study the statistical problem of deciding whether to accept or reject each treatment while controlling for the false discovery rate. We develop sequential tests that achieve time-uniform Type-I error control under arbitrary stopping times and "predictable" treatment schedules. Our approach builds on the testing-by-betting framework: we construct test supermartingales for testing the average treatment effect of each treatment, and show that the construction of these test supermartingales is growth-rate optimal in an almost-sure sense.

Abstract: We study multi-armed bandits (MAB) with multiple optimal arms, motivated by the fact that many practical decision making problems admit multiple correct answers. For $K$-armed bandits with $A$ optimal arms, we first provide a sharper analysis of previous sub-sampling algorithms (De Heide et al., 2021; Zhu and Nowak, 2020), establishing a $\tilde{O}\Big(\frac{K-A}{\sqrt{KA}}\sqrt{T} \Big)$ minimax regret, where $T$ is the total number of interactions and $\tilde O(\cdot)$ drops all constant and logarithmic factors, improving the previous $\tilde{O}(\sqrt{KT/A})$ regret. We then provide a matching lower bound up to logarithmic factors, indicating that our established rate is nearly minimax-optimal. We further show that the knowledge of $A$ up to $\tilde{O}(1)$ factors is necessary to achieve near-optimal regret, as near-optimal algorithms for one number of optimal arms must incur substantially larger regret than optimal regret for a smaller number. Overall, our results provide a comprehensive minimax characterization of $K$-armed bandits with $A$ over the entire range of $1 \leq A \leq K-1$.

Abstract: Collective attention is a finite shared resource, and social media posts compete for limited opportunities to be seen. On X, users can undo a repost and repost it again. By repeating this cycle, a user can put the same post back into followers' timelines any number of times without making new content. We call this procedure repeat reposting, and we read it as placing repeated demand on this shared resource (Attentional DoS). We formalize this idea and explore repeat reposting in a large-scale dataset of cascades with at least 1,000 reactions, originating from posts classified as Japanese on X, covering April 2025 to March 2026. Repeat reposts are rare, appearing in a small share of all (user, post) pairs. Even so, close to a million posts have at least one repeater, and most repeats come from a small group of habitual accounts. The central result is that subsequent audience growth is associated less with the number of repeats than with the estimated reach of the repeating accounts. Through the lens of seriality, how habitually the same groups of accounts repeat reposts across many posts, a distinct distributed form emerges: several serial amplifiers converge on the same post (Attentional DDoS). Its synchrony, how closely their actions are timed together, forms a continuum from bursts on the scale of minutes to a daily clock. A check of the content of 99.7% of amplified posts shows that most ADDoS repeat events are directed at Chinese-script content, which our vocabulary matching and sample inspection indicate is predominantly commercial spam. Repeat reposting thus lets a post re-enter the competition for visibility. The observed pattern is better characterized as repeated temporal coverage of an existing audience and the self-reinforcement of posts that are already growing, rather than as evidence that repeat reposting takes reach from other content.

Abstract: Information cascades on social media are conventionally conceptualized as directed, feedforward branching processes. However, real-world diffusion pathways frequently deviate from pure hierarchical trees due to localized clustering, reciprocal commentary, and multi-wave temporal surges. In this work, we quantify the directional asymmetry and hierarchical structure of empirical information cascades on X (formerly Twitter) using spectral non-normality via Henrici's departure from normality. Analyzing approximately 58,000 cascade networks across diverse topics (including politics, entertainment, natural disasters, etc.), we investigate (1) how non-normality relates to temporal dynamics such as endogenous-like versus exogenous-like patterns and burstiness, (2) whether non-normality is correlated with the peak concentration or overall size of a cascade, (3) whether the overall non-normality of a cascade's network structure can be predicted from its early stages. We find that non-normality strongly aligns with peak concentration (peak/N) rather than overall cascade size, characterizing cascades governed by rapid, asymmetric forwarding. Furthermore, while early-stage structural forecasting (<= 30% of nodes observed) exhibits expected baseline uncertainty (51%-72% accuracy at a +/- 20% error tolerance), predictability consolidates rapidly during intermediate growth, exceeding 80% across all dynamic clusters once 50%-60% of the network is observed. By identifying the topological and dynamic correlates of cascade structures, this study advances our understanding of information flow and establishes a quantifiable benchmark for forecasting directional diffusion architectures.

Abstract: Online conformal prediction can fail when predictions shape actions and actions determine which outcomes enter calibration. Standard adaptive methods may retain marginal coverage while systematically miscovering the counterfactual outcomes of rarely selected actions. This paper formalizes the failure through counterfactual coverage and introduces Propensity-Weighted Online Conformal Prediction, an inverse-propensity-weighted recursion that debiases calibration. A doubly robust variant further reduces nuisance bias to the product of outcome-model and propensity errors. Under positivity, the resulting coverage rate matches an information-theoretic lower bound up to logarithmic factors. Experiments on synthetic decision tasks, open bandit data, and financial rebalancing show that PW-OCP and DR-OCP improve counterfactual coverage and downstream regret without sacrificing prediction-set sharpness.

Abstract: Characterizing temporal interactions in social systems is challenging because social behavior can be bursty and non-stationary, violating the stationarity assumptions of many methods used to measure temporal dependence. The cross-correlogram, an existing technique used to profile neural excitations and inhibitions, offers an interpretable alternative to methods such as Granger causality or co-occurrence, as it produces a full profile of lagged dependence directly from event times rather than a single summary statistic. We adapt the cross-correlogram by integrating functional models of behavior with data-driven temporal response profiling. By characterizing how periodic structure biases traditional cross-correlograms, we propose a correction based on smooth intensity functions, specified from a known functional form or estimated empirically. This approach provides a robust, interpretable estimator of temporal dependency profiles even when collective rhythms operate on timescales that overlap those of the interactions of interest. We demonstrate theoretically and through simulation that the proposed method recovers temporal dependencies in periodic regimes, outperforming interval-jitter and Granger causality methods. Finally, we apply the method to 3.1 million event times from X (formerly Twitter) collected between 2019 and 2020, demonstrating how cross-correlograms reveal delayed temporal relationships in collective online behavior that are missed by co-occurrence measures. For a subset of television-related hashtags, recovered delays align with known broadcast schedules, providing evidence that the proposed method captures genuine temporal structure rather than artifacts of shared attention cycles.

Abstract: AI-generated summaries increasingly mediate how people interpret information across platforms, including product reviews on e-commerce sites. Using Amazon's AI summaries as a case study, we conducted a preregistered, randomized experiment (N = 278) comparing how AI summaries and user reviews shaped product perceptions, and how their influence varied with valence and presentation order. We found that both AI summaries and user reviews influenced participants' opinions, with negative summaries having a larger effect than positive ones. Presentation order was the most important factor: the first source anchored judgment and only user reviews could displace an existing anchor. Although participants reported preferring user reviews, they often underestimated the influence of AI summaries on their judgments. Our findings show how the placement of AI summaries shapes user perception and highlight opportunities to design interfaces that support more deliberate judgments about when to rely on summaries and when to examine the underlying content directly.

Abstract: In online A/B tests for real-time bidding (RTB), control and treatment models are typically trained on a shared serving log that includes data generated by the counterpart model. This shared-log training biases each model's training data through two channels: the counterpart model may have selected a different ad from the ad-candidate pool (ad-ranking disagreement) and may have bid a different price (bid-pricing disagreement), potentially distorting the A/B test outcome. Log-splitting eliminates the bias but sacrifices training data; log-sharing retains all data but leaves the bias unaddressed. We formalize the Bid-Aware Filter Family (BAFF), a class of (k,l)-parameterized hard filters that controls tolerance to each channel independently, providing a structured search space between these two extremes. We further propose a three-stage online measurement protocol that enables evaluating data-sharing strategies by their deviation from an interference-free reference model in production. In offline simulation, a (k,l) sweep surfaces operating points with smaller deviation from the interference-free reference model than both log-sharing and log-splitting. In a live RTB deployment on a demand-side platform (DSP), filter-based variants preserve the reference model's business metrics (e.g., CPC, CTR) more closely than both baselines. The best operating point is setting-dependent, underscoring the practical value of the search space itself.