labs
news
seminars
-
A bidding game for allocation of indivisible goods
Abstract: We consider allocations of indivisible goods to agents with possibly unequal entitlements, in a setting without payments. We present a fairly natural allocation mechanism, referred to as the bidding game. We ask whether the game has the property that the allocations output by this game (say, in equilibrium), enjoy ex-post fairness properties. To answer this, for various values of 0 <… Continue Reading A bidding game for allocation of indivisible goods
-
Computational and Statistical Limits in Modern Machine Learning – Job Talk
Abstract: Modern machine learning systems operate in regimes that challenge classical learning-theoretic assumptions. Models are highly overparameterized, trained with simple optimization algorithms, and rely critically on how data is collected and curated. Understanding the limits of learning in these settings requires revisiting both the computational and statistical foundations of learning theory. A central question in learning… Continue Reading Computational and Statistical Limits in Modern Machine Learning – Job Talk
-
“Calibeating”: Beating Forecasters at Their Own Game
Joint work with Dean Foster. Abstract: In order to identify expertise, forecasters should not be tested by their calibration score, which can always be made arbitrarily small, but rather by their Brier score. The Brier score is the sum of the calibration score and the refinement score; the latter measures how good the sorting into… Continue Reading “Calibeating”: Beating Forecasters at Their Own Game
-
Comparison of Oracles
Abstract: We analyze incomplete-information games where an oracle publicly shares information with players. One oracle dominates another if, in every game, it can match the set of equilibrium outcomes induced by the latter. Distinct characterizations are provided for deterministic and stochastic signaling functions, based on information matching, partition refinements, and common knowledge components. This study… Continue Reading Comparison of Oracles
-
The Agent Perspective In LLM-Based Strategic Information Retrieval Ecosystems
Abstract: Information retrieval ecosystems are strategic environments in which publishers, mediators, advertisers, and users interact under mechanisms that allocate visibility and revenue. The integration of large language models (LLMs) into search and question answering systems fundamentally reshapes these dynamics, altering ranking incentives and long-term corpus evolution. My dissertation develops a unified strategic perspective on LLM-based… Continue Reading The Agent Perspective In LLM-Based Strategic Information Retrieval Ecosystems
Pages
tracks
-
Data Science
In an era where information is created at a dizzying pace and changes constantly and decisions require the creation of in-depth analysis, the ability to make sense of large quantities of data is a necessary and sought-after power. A master’s degree in Data Science offers tools and knowledge that will enable you to face the great challenges of the 21st century in all areas of life: medicine, social media, finance, urban planning, smart cities and more. Continue Reading Data Science
