Yiding Feng

Reducing food waste while preserving profit is an important operational problem for retailers of perishable products. We study a finite-horizon inventory allocation problem with a regular channel and an opaque surprise-bag channel. Before observing each period's regular demand, the retailer chooses product display quantities and surprise-bag offers. Each offered bag sells and creates a noncancellable commitment that must be fulfilled from inventory remaining at the horizon. The model incorporates waste costs and linear constraints on the expected aggregate composition of bag allocations, while allowing arbitrary correlation in regular demand across products and periods. Under productwise regular-channel profitability, an LP-based reservation policy achieves the optimal competitive ratio 1/(2 + κ) against a clairvoyant benchmark, where κ = w/s is the waste-cost-to-bag-reward ratio. An adaptive reservation policy weakly dominates the static policy in expected profit on every instance and inherits its guarantee. We also identify sufficient conditions under which deferred product assignment strictly improves optimal expected profit over immediate assignment, and extend the static guarantee to fixed multi-unit bags. In simulations calibrated from cafeteria sales data, the adaptive policy improves mean profit over the static policy by 6.2%-9.2% across the tested quality-floor settings.

We study non-clairvoyant scheduling for batched Large Language Model (LLM) inference under a hard Key-Value (KV) cache memory budget. Each request has a known prompt length but an unknown response length, and its memory footprint comprises a fixed prompt component together with a response component that grows with each decoded token. At each decoding round, the scheduler chooses a feasible batch of active requests; evicting a request discards its accumulated cache states, wasting prior computation. The goal is to minimize total completion time against the optimal clairvoyant schedule that knows all response lengths. We present the first O(1)-competitive algorithm for arbitrary prompt lengths and arbitrary response lengths with no additional assumptions. Rather than relying on a single universal scheduling policy, our algorithm is built on a novel regime-aware routing framework. Specialized sub-schedulers handle different memory-growth geometries, while a meta-scheduler time-shares the memory budget across them and dynamically routes each job as its execution progressively reveals its behavior. This framework also yields constant-competitive guarantees for makespan and for total completion time under online arrivals.

No-Regret Bayesian Recommendation to Homogeneous Users We introduce and study the online Bayesian recommendation problem for a recommender system platform. The platform has the privilege to privately observe a utility-relevant state of a product at each round and uses this information to make online recommendations to a stream of myopic users. This paradigm is common in a wide range of scenarios in the current internet economy. The platform commits to an online recommendation policy that utilizes its information advantage on the product state to persuade self-interested users to follow the recommendation. Because the platform does not know users’ preferences or beliefs in advance, we study the platform’s online learning problem of designing an adaptive recommendation policy to persuade users while gradually learning users’ preferences and beliefs en route. Specifically, we aim to design online learning policies with no Stackelberg regret for the platform, that is, against the optimal benchmark policy in hindsight under the assumption that users will correspondingly adapt their responses to the benchmark policy. Our first result is an online policy that achieves double logarithmic regret dependence on the number of rounds. We also present an information-theoretic lower bound showing that no adaptive online policy can achieve regret with better dependency on the number of rounds. Finally, by formulating the platform’s problem as optimizing a linear program with membership oracle access, we present our second online recommendation policy that achieves regret with polynomial dependence on the number of states but logarithmic dependence on the number of rounds.

In many real-world applications, a model provider provides probabilistic forecasts to downstream decision-makers who use them to make decisions under diverse payoff objectives. The provider may have access to multiple predictive models, each potentially miscalibrated, and must choose which model to deploy in order to maximize the usefulness of predictions for downstream decisions. A central challenge arises: how can the provider meaningfully compare two predictors when neither is guaranteed to be well-calibrated, and when the relevant decision tasks may differ across users and contexts? To answer this, our first contribution introduces the notion of the informativeness gap between any two predictors, defined as the maximum normalized payoff advantage one predictor offers over the other across all decision-making tasks. Our framework strictly generalizes several existing notions: it subsumes U-Calibration [Kleinberg et al., 2023] and Calibration Decision Loss [Hu and Wu, 2024], which compare a miscalibrated predictor to its calibrated counterpart, and it recovers Blackwell informativeness [Blackwell, 1951, 1953] as a special case when both predictors are perfectly calibrated. Our second contribution is a dual characterization of the informativeness gap, which gives rise to a natural informativeness measure that can be viewed as a relaxed variant of the earth mover's distance (EMD) between two prediction distributions. We show that this measure satisfies natural desiderata: it is complete and sound, and it can be estimated sample-efficiently in the prediction-only access setting. Along the way, we also obtain novel combinatorial structural results when applying this measure to perfectly calibrated predictors. We complement our theory with experiments on LLM-based forecasters in real-world weather and Bitcoin prediction tasks, showing that the informativeness gap offers a more decision-relevant alternative to traditional metrics like the Brier score/ECE, and provides a principled lens for evaluating how ad hoc calibration post-processing affects downstream decision usefulness.

This paper explores the economic interactions within modern crowdsourcing markets. In these markets, employers issue requests for tasks, platforms facilitate the recruitment of crowd workers, and workers complete tasks for monetary rewards. Recognizing that these roles serve distinct functions within the ecosystem, we introduce a three-party model that distinguishes among the principal (the requester), the intermediary (the platform), and the pool of agents (the workers). The principal, unable to directly engage with agents, relies on the intermediary to recruit and incentivize them. This interaction unfolds in two stages: first, the principal designs a profit-sharing contract with the intermediary; second, the intermediary implements a mechanism to select an agent to complete the delegated task. We analyze the proposed model as an extensive-form Stackelberg game. Our contributions are threefold: First, we fully characterize the subgame perfect equilibrium of our model. In particular, the principal’s contract design problem can be represented as virtual value pricing, a novel auction-theoretic formulation. We identify the optimality of linear contracts, even when the task has multiple outcomes and agents' cost distributions are asymmetric. Second, to quantify the principal's utility loss from delegation and information asymmetry, we introduce the price of double marginalization (PoDM) and the classical price of anarchy (PoA). We derive tight or nearly tight bounds on both ratios under regular and monotone hazard rate distributions. Finally, we extend our analysis to two natural variants of the base model: (i) the intermediary is restricted to anonymous pricing mechanisms, and (ii) the principal lacks precise information about the market size.

Quality information on online platforms is often conveyed through simple, percentile-based badges and tiers that remain stable across different market environments. Motivated by this empirical evidence, we study robust quality disclosure in a market where a platform commits to a public disclosure policy mapping the seller's product quality into a signal, and the seller subsequently sets a downstream monopoly price. Buyers have heterogeneous private types and valuations that are linear in quality. We evaluate a disclosure policy via a minimax competitive ratio: its worst-case revenue relative to the Bayesian-optimal disclosure-and-pricing benchmark, uniformly over all prior quality distributions, type distributions, and admissible valuations. Our main results provide a sharp theoretical justification for quantile-partition disclosure. For K-quantile partition policies, we fully characterize the robust optimum: the optimal worstcase ratio is pinned down by a one-dimensional fixed-point equation and the optimal thresholds follow a backward recursion. We also give an explicit formula for the robust ratio of any quantile partition as a simple "max-over-bins" expression, which explains why the robust-optimal partition allocates finer resolution to upper quantiles and yields tight guarantees such as 1 + 1/K for uniform percentile buckets. In contrast, we show a robustness limit for finite-signal monotone (quality-threshold) partitions, which cannot beat a factor-2 approximation. Technically, our analysis reduces the robust quality disclosure to a robust disclosure design program by establishing a tight functional characterization of all feasible indirect revenue functions.

Large Language Model (LLM) inference presents a unique scheduling challenge due to the Key-Value (KV) cache, where a job's memory footprint grows linearly with the number of decoded tokens. This growth couples scheduling decisions with feasibility: a scheduler must minimize latency under a hard memory budget, yet the response lengths of requests are inherently unknown. While recent works have explored this problem either assuming clairvoyance-exact knowledge of response lengths-or relying on machine-learned predictions, obtaining robust performance guarantees without any prior knowledge of job sizes remains a theoretically fundamental and practically important open problem. In this work, we propose the Geometric Slicing Algorithm (GSA), the non-clairvoyant policy to achieve the first constant competitive ratio for this problem in the offline batch setting. GSA manages uncertainty through a geometric phase structure that periodically restarts jobs to bound memory exposure, combined with a staggered pipeline mechanism that enables high concurrency by smoothing aggregate memory consumption. We prove that GSA achieves a competitive ratio of at most 61.92 for general instances, improving to 32 in the large-memory regime. Our algorithmic framework also yields a clairvoyant counterpart, the Geometric Batching Algorithm (GBA), which achieves an approximation ratio of 10.67 for general instances and 6.75 in the largememory regime-significantly improving upon the best previously known bound of over 9000. Numerical experiments on real request traces demonstrate that our algorithms perform robustly while preserving these worst-case guarantees.