25 citations · 110 across the 18 of their papers we have counts for
21 papers
Stabilizing Performative Feedback Loops with Minimal Model Deployments
Gabriele Farina, Juan Carlos Perdomo
When algorithmic predictions inform people's decisions, the models we deploy are performative and actively shape the data we see. This feedback loop between algorithms and their br…
An Efficient Black-Box Reduction from Online Learning to Multicalibration, and a New Route to -Regret Minimization
Gabriele Farina, Juan Carlos Perdomo
We give a Gordon-Greenwald-Marks (GGM) style black-box reduction from online learning to online multicalibration. Concretely, we show that to achieve high-dimensional multicalibrat…
Defensive Generation
Gabriele Farina, Juan Carlos Perdomo
We study the problem of efficiently producing, in an online fashion, generative models of scalar, multiclass, and vector-valued outcomes that cannot be falsified on the basis of th…
The Stability of Online Algorithms in Performative Prediction
Gabriele Farina, Juan Carlos Perdomo
The use of algorithmic predictions in decision-making leads to a feedback loop where the models we deploy actively influence the data distributions we see, and later use to retrain…
In Defense of Defensive Forecasting
Juan Carlos Perdomo, Benjamin Recht
This tutorial provides a survey of algorithms for Defensive Forecasting, where predictions are derived not by prognostication but by correcting past mistakes. Pioneered by Vovk, De…
Inducing Efficient and Equitable Professional Networks through Link Recommendations
Cynthia Dwork, Chris Hays, Lunjia Hu +2
Professional networks are a key determinant of individuals' labor market outcomes. They may also play a role in either exacerbating or ameliorating inequality of opportunity across…
Revisiting the Predictability of Performative, Social Events
Juan C. Perdomo
Social predictions do not passively describe the future; they actively shape it. They inform actions and change individual expectations in ways that influence the likelihood of the…
The Value of Prediction in Identifying the Worst-Off
Unai Fischer-Abaigar, Christoph Kern, Juan Carlos Perdomo
Machine learning is increasingly used in government programs to identify and support the most vulnerable individuals, prioritizing assistance for those at greatest risk over optimi…
From Fairness to Infinity: Outcome-Indistinguishable (Omni)Prediction in Evolving Graphs
Cynthia Dwork, Chris Hays, Nicole Immorlica +2
Professional networks provide invaluable entree to opportunity through referrals and introductions. A rich literature shows they also serve to entrench and even exacerbate a status…
Large Scale Transfer Learning for Tabular Data via Language Modeling
Josh Gardner, Juan C. Perdomo, Ludwig Schmidt
Tabular data -- structured, heterogeneous, spreadsheet-style data with rows and columns -- is widely used in practice across many domains. However, while recent foundation models h…
The Relative Value of Prediction in Algorithmic Decision Making
Juan Carlos Perdomo
Algorithmic predictions are increasingly used to inform the allocations of goods and interventions in the public sphere. In these domains, predictions serve as a means to an end. T…
Difficult Lessons on Social Prediction from Wisconsin Public Schools
Juan C. Perdomo, Tolani Britton, Moritz Hardt +1
Early warning systems (EWS) are predictive tools at the center of recent efforts to improve graduation rates in public schools across the United States. These systems assist in tar…
Making Decisions under Outcome Performativity
Michael P. Kim, Juan C. Perdomo
Decision-makers often act in response to data-driven predictions, with the goal of achieving favorable outcomes. In such settings, predictions don't passively forecast the future;…
A Complete Characterization of Linear Estimators for Offline Policy Evaluation
Juan C. Perdomo, Akshay Krishnamurthy, Peter Bartlett +1
Offline policy evaluation is a fundamental statistical problem in reinforcement learning that involves estimating the value function of some decision-making policy given data colle…
Globally Convergent Policy Search over Dynamic Filters for Output Estimation
Jack Umenberger, Max Simchowitz, Juan C. Perdomo +2
We introduce the first direct policy search algorithm which provably converges to the globally optimal filter for the classical problem of predicting the outputs…
Stabilizing Dynamical Systems via Policy Gradient Methods
Juan C. Perdomo, Jack Umenberger, Max Simchowitz
Stabilizing an unknown control system is one of the most fundamental problems in control systems engineering. In this paper, we provide a simple, model-free algorithm for stabilizi…
Towards a Dimension-Free Understanding of Adaptive Linear Control
Juan C. Perdomo, Max Simchowitz, Alekh Agarwal +1
We study the problem of adaptive control of the linear quadratic regulator for systems in very high, or even infinite dimension. We demonstrate that while sublinear regret requires…
Outside the Echo Chamber: Optimizing the Performative Risk
John Miller, Juan C. Perdomo, Tijana Zrnic
In performative prediction, predictions guide decision-making and hence can influence the distribution of future data. To date, work on performative prediction has focused on findi…
Stochastic Optimization for Performative Prediction
Celestine Mendler-Dünner, Juan C. Perdomo, Tijana Zrnic +1
In performative prediction, the choice of a model influences the distribution of future data, typically through actions taken based on the model's predictions. We initiate the stud…
Performative Prediction
Juan C. Perdomo, Tijana Zrnic, Celestine Mendler-Dünner +1
When predictions support decisions they may influence the outcome they aim to predict. We call such predictions performative; the prediction influences the target. Performativity i…
Robust Attacks against Multiple Classifiers
Juan C. Perdomo, Yaron Singer
We address the challenge of designing optimal adversarial noise algorithms for settings where a learner has access to multiple classifiers. We demonstrate how this problem can be f…