Related papers: A Curationary Tale: Logarithmic Regret in DeFi Len…
The rapid progress in generative models has resulted in impressive leaps in generation quality, blurring the lines between synthetic and real data. Web-scale datasets are now prone to the inevitable contamination by synthetic data, directly…
Decentralized finance (DeFi) has the potential to disrupt centralized finance by validating peer-to-peer transactions through tamper-proof smart contracts, thus significantly lowering the transaction cost charged by financial…
Continuous-time adaptive controllers for systems with a matched uncertainty often comprise an online parameter estimator and a corresponding parameterized controller to cancel the uncertainty. However, such methods are often impossible to…
This paper focuses on an online version of the emerging distributed constrained aggregative optimization framework, which is particularly suited for applications arising in cooperative robotics. Agents in a network want to minimize the sum…
Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed what the underlying problems require,…
Distributed programs are hard to get right because they are required to be open, scalable, long-running, and tolerant to faults. In particular, the recent approaches to distributed software based on (micro-)services where different services…
Online learning and model reference adaptive control have many interesting intersections. One area where they differ however is in how the algorithms are analyzed and what objective or metric is used to discriminate "good" algorithms from…
Unsupervised Environment Design (UED) seeks to automatically generate training curricula for reinforcement learning (RL) agents, with the goal of improving generalisation and zero-shot performance. However, designing effective curricula…
Traditional pricing paradigms, once dominated by static models and rule-based heuristics, are increasingly being replaced by dynamic, data-driven approaches powered by machine learning algorithms. Despite their growing sophistication, most…
We study learning control in an online reset-free lifelong learning scenario, where mistakes can compound catastrophically into the future and the underlying dynamics of the environment may change. Traditional model-free policy learning…
Interactive AI systems, such as recommendation engines and virtual assistants, commonly use static user profiles and predefined rules to personalize interactions. However, these methods often fail to capture the dynamic nature of user…
First-price auctions have largely replaced traditional bidding approaches based on Vickrey auctions in programmatic advertising. As far as learning is concerned, first-price auctions are more challenging because the optimal bidding strategy…
Recent work by Foster et al. (2021, 2022, 2023b) and Xu and Zeevi (2023) developed the framework of decision estimation coefficient (DEC) that characterizes the complexity of general online decision making problems and provides a general…
We consider the problem of a firm seeking to use personalized pricing to sell an exogenously given stock of a product over a finite selling horizon to different consumer types. We assume that the type of an arriving consumer can be observed…
We consider the problem of pricing a reusable resource service system. Potential customers arrive according to a Poisson process and purchase the service if their valuation exceeds the current price. If no units are available, customers…
We study a centralized discrete-time dynamic two-way matching model with finitely many agent types. Agents arrive stochastically over time and join their type-dedicated queues waiting to be matched. We focus on availability-based policies…
This paper maps the emerging market for decentralized credit in which ERC 4626 vaults and third-party curators, rather than monolithic lending protocols alone, increasingly determine underwriting and leverage decisions. We show that modular…
Motivated by online advertising auctions, we consider repeated Vickrey auctions where goods of unknown value are sold sequentially and bidders only learn (potentially noisy) information about a good's value once it is purchased. We adopt an…
We study a data pricing problem, where a seller has access to $N$ homogeneous data points (e.g. drawn i.i.d. from some distribution). There are $m$ types of buyers in the market, where buyers of the same type $i$ have the same valuation…
Firms increasingly delegate decisions to learning algorithms in platform markets. Standard algorithms perform well when platform policies are stationary, but firms often face ambiguity about whether policies are stationary or adapt…