papers

Publications (91)

cs.LG2021

Alternative Microfoundations for Strategic Classification

Meena Jagadeesan, Celestine Mendler-Dünner, Moritz Hardt

When reasoning about strategic behavior in a machine learning context it is tempting to combine standard microfoundations of rational agents with the statistical decision theory un…

cs.SI2021

From Optimizing Engagement to Measuring Value

Smitha Milli, Luca Belli, Moritz Hardt

Most recommendation engines today are based on predicting user engagement, e.g. predicting whether a user will click on an item or not. However, there is potentially a large gap be…

stat.ML2018

Model Reconstruction from Model Explanations

Smitha Milli, Ludwig Schmidt, Anca D. Dragan +1

We show through theory and experiment that gradient-based explanations of a model quickly reveal the model itself. Our results speak to a tension between the desire to keep a propr…

cs.LG2015

Generalization in Adaptive Data Analysis and Holdout Reuse

Cynthia Dwork, Vitaly Feldman, Moritz Hardt +3

Overfitting is the bane of data analysts, even when data are plentiful. Formal approaches to understanding this problem focus on statistical inference and generalization of individ…

cs.CY2023

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…

cs.CL2025

Answer Matching Outperforms Multiple Choice for Language Model Evaluation

Nikhil Chandak, Shashwat Goel, Ameya Prabhu +2

Multiple choice benchmarks have long been the workhorse of language model evaluation because grading multiple choice is objective and easy to automate. However, we show multiple ch…

cs.LG2020

Strategic Classification is Causal Modeling in Disguise

John Miller, Smitha Milli, Moritz Hardt

Consequential decision-making incentivizes individuals to strategically adapt their behavior to the specifics of the decision rule. While a long line of work has viewed strategic a…

cs.GT2026

Leaderboard Incentives: Model Rankings under Strategic Post-Training

Yatong Chen, Guanhua Zhang, Moritz Hardt

Influential benchmarks incentivize competing model developers to strategically allocate post-training resources toward improvements on the leaderboard, a phenomenon dubbed benchmax…

cs.CL2025

Training on the Test Task Confounds Evaluation and Emergence

Ricardo Dominguez-Olmedo, Florian E. Dorner, Moritz Hardt

We study a fundamental problem in the evaluation of large language models that we call training on the test task. Unlike wrongful practices like training on the test data, leakage,…

cs.LG2019

Stable Recurrent Models

John Miller, Moritz Hardt

Stability is a fundamental property of dynamical systems, yet to this date it has had little bearing on the practice of recurrent neural networks. In this work, we conduct a thorou…

cs.LG2024

Algorithmic Collective Action in Machine Learning

Moritz Hardt, Eric Mazumdar, Celestine Mendler-Dünner +1

We initiate a principled study of algorithmic collective action on digital platforms that deploy machine learning algorithms. We propose a simple theoretical model of a collective…

cs.LG2019

The advantages of multiple classes for reducing overfitting from test set reuse

Vitaly Feldman, Roy Frostig, Moritz Hardt

Excessive reuse of holdout data can lead to overfitting. However, there is little concrete evidence of significant overfitting due to holdout reuse in popular multiclass benchmarks…

cs.LG2024

Unprocessing Seven Years of Algorithmic Fairness

André F. Cruz, Moritz Hardt

Seven years ago, researchers proposed a postprocessing method to equalize the error rates of a model across different demographic groups. The work launched hundreds of papers purpo…

cs.LG2016

Preserving Statistical Validity in Adaptive Data Analysis

Cynthia Dwork, Vitaly Feldman, Moritz Hardt +3

A great deal of effort has been devoted to reducing the risk of spurious scientific discoveries, from the use of sophisticated validation techniques, to deep statistical methods fo…

cs.AI2026

Computational Arbitrage in AI Model Markets

Ricardo Olmedo, Bernhard Schölkopf, Moritz Hardt

Consider a market of competing model providers selling query access to models with varying costs and capabilities. Customers submit problem instances and are willing to pay up to a…

cs.LG2025

Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning

Jonas Hübotter, Leander Diaz-Bone, Ido Hakimi +2

Humans are good at learning on the job: We learn how to solve the tasks we face as we go along. Can a model do the same? We propose an agent that assembles a task-specific curricul…

cs.LG2017

Understanding deep learning requires rethinking generalization

Chiyuan Zhang, Samy Bengio, Moritz Hardt +2

Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance. Conventional wisdom attribut…

cs.LG2025

ImageNot: A contrast with ImageNet preserves model rankings

Olawale Salaudeen, Moritz Hardt

We introduce ImageNot, a dataset constructed explicitly to be drastically different than ImageNet while matching its scale. ImageNot is designed to test the external validity of de…

cs.DS2012

How Robust are Linear Sketches to Adaptive Inputs?

Moritz Hardt, David P. Woodruff

Linear sketches are powerful algorithmic tools that turn an n-dimensional input into a concise lower-dimensional representation via a linear transformation. Such sketches have seen…

stat.ML2026

Retraining Seeks Stable Signals

Moritz Hardt

Predictive models deployed at scale influence future data, a phenomenon called performativity. And there is always one way to cope: Train the model on new data, deploy it again, an…

cs.LG2019

Gradient Descent Learns Linear Dynamical Systems

Moritz Hardt, Tengyu Ma, Benjamin Recht

We prove that stochastic gradient descent efficiently converges to the global optimizer of the maximum likelihood objective of an unknown linear time-invariant dynamical system fro…

cs.LG2024

Do causal predictors generalize better to new domains?

Vivian Y. Nastl, Moritz Hardt

We study how well machine learning models trained on causal features generalize across domains. We consider 16 prediction tasks on tabular datasets covering applications in health,…

cs.GT2024

Decline Now: A Combinatorial Model for Algorithmic Collective Action

Dorothee Sigg, Moritz Hardt, Celestine Mendler-Dünner

Drivers on food delivery platforms often run a loss on low-paying orders. In response, workers on DoorDash started a campaign, #DeclineNow, to purposefully decline orders below a c…

cs.LG2015

Tight bounds for learning a mixture of two gaussians

Moritz Hardt, Eric Price

We consider the problem of identifying the parameters of an unknown mixture of two arbitrary -dimensional gaussians from a sequence of independent random samples. Our main resul…

cs.DS2012

Beyond Worst-Case Analysis in Private Singular Vector Computation

Moritz Hardt, Aaron Roth

We consider differentially private approximate singular vector computation. Known worst-case lower bounds show that the error of any differentially private algorithm must scale pol…

cs.LG2016

Train faster, generalize better: Stability of stochastic gradient descent

Moritz Hardt, Benjamin Recht, Yoram Singer

We show that parametric models trained by a stochastic gradient method (SGM) with few iterations have vanishing generalization error. We prove our results by arguing that SGM is al…

cs.LG2024

Allocation Requires Prediction Only if Inequality Is Low

Ali Shirali, Rediet Abebe, Moritz Hardt

Algorithmic predictions are emerging as a promising solution concept for efficiently allocating societal resources. Fueling their use is an underlying assumption that such systems…

cs.LG2020

Test-Time Training with Self-Supervision for Generalization under Distribution Shifts

Yu Sun, Xiaolong Wang, Zhuang Liu +3

In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. W…

cs.CC2013

Algorithms and Hardness for Robust Subspace Recovery

Moritz Hardt, Ankur Moitra

We consider a fundamental problem in unsupervised learning called \emph{subspace recovery}: given a collection of points in , if many but not necessarily all of t…

stat.ML2018

Avoiding Discrimination through Causal Reasoning

Niki Kilbertus, Mateo Rojas-Carulla, Giambattista Parascandolo +3

Recent work on fairness in machine learning has focused on various statistical discrimination criteria and how they trade off. Most of these criteria are observational: They depend…

cs.LG2017

Climbing a shaky ladder: Better adaptive risk estimation

Moritz Hardt

We revisit the \emph{leaderboard problem} introduced by Blum and Hardt (2015) in an effort to reduce overfitting in machine learning benchmarks. We show that a randomized version o…

cs.CL2024

Questioning the Survey Responses of Large Language Models

Ricardo Dominguez-Olmedo, Moritz Hardt, Celestine Mendler-Dünner

Surveys have recently gained popularity as a tool to study large language models. By comparing survey responses of models to those of human reference populations, researchers aim t…

cs.LG2015

Strategic Classification

Moritz Hardt, Nimrod Megiddo, Christos Papadimitriou +1

Machine learning relies on the assumption that unseen test instances of a classification problem follow the same distribution as observed training data. However, this principle can…

cs.LG2021

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…

cs.LG2021

Patterns, predictions, and actions: A story about machine learning

Moritz Hardt, Benjamin Recht

This graduate textbook on machine learning tells a story of how patterns in data support predictions and consequential actions. Starting with the foundations of decision making, we…

cs.LG2014

Preventing False Discovery in Interactive Data Analysis is Hard

Moritz Hardt, Jonathan Ullman

We show that, under a standard hardness assumption, there is no computationally efficient algorithm that given samples from an unknown distribution can give valid answers to $n…

cs.LG2018

The Social Cost of Strategic Classification

Smitha Milli, John Miller, Anca D. Dragan +1

Consequential decision-making typically incentivizes individuals to behave strategically, tailoring their behavior to the specifics of the decision rule. A long line of work has th…

cs.CC2010

Subsampling Mathematical Relaxations and Average-case Complexity

Boaz Barak, Moritz Hardt, Thomas Holenstein +1

We initiate a study of when the value of mathematical relaxations such as linear and semidefinite programs for constraint satisfaction problems (CSPs) is approximately preserved wh…

cs.LG2026

Good Allocations from Bad Estimates

Sílvia Casacuberta, Moritz Hardt

Conditional average treatment effect (CATE) estimation is the de facto gold standard for targeting a treatment to a heterogeneous population. The method estimates treatment effects…

cs.CL2025

Lawma: The Power of Specialization for Legal Annotation

Ricardo Dominguez-Olmedo, Vedant Nanda, Rediet Abebe +6

Annotation and classification of legal text are central components of empirical legal research. Traditionally, these tasks are often delegated to trained research assistants. Motiv…

cs.LG2019

The implicit fairness criterion of unconstrained learning

Lydia T. Liu, Max Simchowitz, Moritz Hardt

We clarify what fairness guarantees we can and cannot expect to follow from unconstrained machine learning. Specifically, we characterize when unconstrained learning on its own imp…

cs.DS2011

Beating Randomized Response on Incoherent Matrices

Moritz Hardt, Aaron Roth

Computing accurate low rank approximations of large matrices is a fundamental data mining task. In many applications however the matrix contains sensitive information about individ…

cs.LG2025

Train-before-Test Harmonizes Language Model Rankings

Guanhua Zhang, Ricardo Dominguez-Olmedo, Moritz Hardt

Existing language model benchmarks provide contradictory model rankings, even for benchmarks that aim to capture similar skills. This dilemma of conflicting rankings hampers model…

cs.LG2025

Performative Prediction: Past and Future

Moritz Hardt, Celestine Mendler-Dünner

Predictions in the social world generally influence the target of prediction, a phenomenon known as performativity. Self-fulfilling and self-negating predictions are examples of pe…

cs.CY2024

An engine not a camera: Measuring performative power of online search

Celestine Mendler-Dünner, Gabriele Carovano, Moritz Hardt

The power of digital platforms is at the center of major ongoing policy and regulatory efforts. To advance existing debates, we designed and executed an experiment to measure the p…

cs.LG2020

A System for Massively Parallel Hyperparameter Tuning

Liam Li, Kevin Jamieson, Afshin Rostamizadeh +4

Modern learning models are characterized by large hyperparameter spaces and long training times. These properties, coupled with the rise of parallel computing and the growing deman…

cs.CY2026

Policy Design in Long-Run Welfare Dynamics

Jiduan Wu, Rediet Abebe, Moritz Hardt +1

Improving social welfare is a complex challenge requiring policymakers to optimize objectives across multiple time horizons. Evaluating the impact of such policies presents a funda…

cs.CL2024

Test-Time Training on Nearest Neighbors for Large Language Models

Moritz Hardt, Yu Sun

Many recent efforts augment language models with retrieval, by adding retrieved data to the input context. For this approach to succeed, the retrieved data must be added at both tr…

cs.LG2023

A Theory of Dynamic Benchmarks

Ali Shirali, Rediet Abebe, Moritz Hardt

Dynamic benchmarks interweave model fitting and data collection in an attempt to mitigate the limitations of static benchmarks. In contrast to an extensive theoretical and empirica…

cs.GT2024

Causal Inference from Competing Treatments

Ana-Andreea Stoica, Vivian Y. Nastl, Moritz Hardt

Many applications of RCTs involve the presence of multiple treatment administrators -- from field experiments to online advertising -- that compete for the subjects' attention. In…

cs.LG2018

Delayed Impact of Fair Machine Learning

Lydia T. Liu, Sarah Dean, Esther Rolf +2

Fairness in machine learning has predominantly been studied in static classification settings without concern for how decisions change the underlying population over time. Conventi…

cs.LG2015

The Ladder: A Reliable Leaderboard for Machine Learning Competitions

Avrim Blum, Moritz Hardt

The organizer of a machine learning competition faces the problem of maintaining an accurate leaderboard that faithfully represents the quality of the best submission of each compe…

cs.HC2026

Stochastic wage suppression on gig platforms and how to organize against it

Ana-Andreea Stoica, Celestine Mendler-Duenner, Moritz Hardt

Digital labor platforms are increasingly used to procure human input, ranging from annotating data and red-teaming AI models, to ride-sharing and food delivery. A central concern i…

cs.LG2014

Understanding Alternating Minimization for Matrix Completion

Moritz Hardt

Alternating Minimization is a widely used and empirically successful heuristic for matrix completion and related low-rank optimization problems. Theoretical guarantees for Alternat…

cs.LG2022

Causal Inference Struggles with Agency on Online Platforms

Smitha Milli, Luca Belli, Moritz Hardt

Online platforms regularly conduct randomized experiments to understand how changes to the platform causally affect various outcomes of interest. However, experimentation on online…

cs.LG2020

Revisiting Design Choices in Proximal Policy Optimization

Chloe Ching-Yun Hsu, Celestine Mendler-Dünner, Moritz Hardt

Proximal Policy Optimization (PPO) is a popular deep policy gradient algorithm. In standard implementations, PPO regularizes policy updates with clipped probability ratios, and par…

cs.CY2021

Algorithmic Amplification of Politics on Twitter

Ferenc Huszár, Sofia Ira Ktena, Conor O'Brien +3

Content on Twitter's home timeline is selected and ordered by personalization algorithms. By consistently ranking certain content higher, these algorithms may amplify some messages…

cs.CV2020

Sanity Checks for Saliency Maps

Julius Adebayo, Justin Gilmer, Michael Muelly +3

Saliency methods have emerged as a popular tool to highlight features in an input deemed relevant for the prediction of a learned model. Several saliency methods have been proposed…

cs.LG2019

Natural Analysts in Adaptive Data Analysis

Tijana Zrnic, Moritz Hardt

Adaptive data analysis is frequently criticized for its pessimistic generalization guarantees. The source of these pessimistic bounds is a model that permits arbitrary, possibly ad…

cs.DS2015

The Noisy Power Method: A Meta Algorithm with Applications

Moritz Hardt, Eric Price

We provide a new robust convergence analysis of the well-known power method for computing the dominant singular vectors of a matrix that we call the noisy power method. Our result…

cs.CY2022

Adversarial Scrutiny of Evidentiary Statistical Software

Rediet Abebe, Moritz Hardt, Angela Jin +3

The U.S. criminal legal system increasingly relies on software output to convict and incarcerate people. In a large number of cases each year, the government makes these consequent…

cs.LG2024

Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks

Guanhua Zhang, Moritz Hardt

We examine multi-task benchmarks in machine learning through the lens of social choice theory. We draw an analogy between benchmarks and electoral systems, where models are candida…

cs.LG2021

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…

stat.ML2020

Identity Crisis: Memorization and Generalization under Extreme Overparameterization

Chiyuan Zhang, Samy Bengio, Moritz Hardt +2

We study the interplay between memorization and generalization of overparameterized networks in the extreme case of a single training example and an identity-mapping task. We exami…

cs.CC2014

Computational Limits for Matrix Completion

Moritz Hardt, Raghu Meka, Prasad Raghavendra +1

Matrix Completion is the problem of recovering an unknown real-valued low-rank matrix from a subsample of its entries. Important recent results show that the problem can be solved…

cs.AI2026

Correct Looks Better: Pairwise Comparisons Reveal Accuracy Rankings

Mina Remeli, Moritz Hardt

Pairwise comparisons combined with aggregation methods like Elo have become central to evaluating generative models, yet concerns remain that they reward superficial stylistic cues…

cs.LG2025

How Benchmark Prediction from Fewer Data Misses the Mark

Guanhua Zhang, Florian E. Dorner, Moritz Hardt

Large language model (LLM) evaluation is increasingly costly, prompting interest in methods that speed up evaluation by shrinking benchmark datasets. Benchmark prediction (also cal…

cs.LG2016

Equality of Opportunity in Supervised Learning

Moritz Hardt, Eric Price, Nathan Srebro

We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features. Assu…

cs.DS2012

A simple and practical algorithm for differentially private data release

Moritz Hardt, Katrina Ligett, Frank McSherry

We present new theoretical results on differentially private data release useful with respect to any target class of counting queries, coupled with experimental results on a variet…

cs.LG2026

Don't Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget

Florian E. Dorner, Moritz Hardt

We study how to best spend a budget of noisy labels to compare the accuracy of two binary classifiers. It's common practice to collect and aggregate multiple noisy labels for a giv…

cs.LG2020

Linear Dynamics: Clustering without identification

Chloe Ching-Yun Hsu, Michaela Hardt, Moritz Hardt

Linear dynamical systems are a fundamental and powerful parametric model class. However, identifying the parameters of a linear dynamical system is a venerable task, permitting pro…

cs.CL2026

Limits to Predicting Online Speech Using Large Language Models

Mina Remeli, Moritz Hardt, Robert C. Williamson

Our paper studies the predictability of online speech -- that is, how well language models learn to model the distribution of user generated content on X (previously Twitter). We d…

cs.CC2011

Private Data Release via Learning Thresholds

Moritz Hardt, Guy N. Rothblum, Rocco A. Servedio

This work considers computationally efficient privacy-preserving data release. We study the task of analyzing a database containing sensitive information about individual participa…

cs.CC2009

On the Geometry of Differential Privacy

Moritz Hardt, Kunal Talwar

We consider the noise complexity of differentially private mechanisms in the setting where the user asks linear queries $f\colon\Rn\to\Re$ non-adaptively. Here, the database is…

cs.LG2026

Scaling Open-Ended Reasoning to Predict the Future

Nikhil Chandak, Shashwat Goel, Ameya Prabhu +2

High-stakes decision making involves reasoning under uncertainty about the future. In this work, we train language models to make predictions on open-ended forecasting questions. T…

cs.LG2024

Evaluating language models as risk scores

André F. Cruz, Moritz Hardt, Celestine Mendler-Dünner

Current question-answering benchmarks predominantly focus on accuracy in realizable prediction tasks. Conditioned on a question and answer-key, does the most likely token match the…

cs.LG2022

Performative Power

Moritz Hardt, Meena Jagadeesan, Celestine Mendler-Dünner

We introduce the notion of performative power, which measures the ability of a firm operating an algorithmic system, such as a digital content recommendation platform, to cause cha…

cs.LG2026

Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data

Florian E. Dorner, Vivian Y. Nastl, Moritz Hardt

High quality annotations are increasingly a bottleneck in the explosively growing machine learning ecosystem. Scalable evaluation methods that avoid costly annotation have therefor…

cs.DS2011

Privately Releasing Conjunctions and the Statistical Query Barrier

Anupam Gupta, Moritz Hardt, Aaron Roth +1

Suppose we would like to know all answers to a set of statistical queries C on a data set up to small error, but we can only access the data itself using statistical queries. A tri…

cs.LG2019

Explaining an increase in predicted risk for clinical alerts

Michaela Hardt, Alvin Rajkomar, Gerardo Flores +5

Much work aims to explain a model's prediction on a static input. We consider explanations in a temporal setting where a stateful dynamical model produces a sequence of risk estima…

cs.LG2026

FutureSim: Replaying World Events to Evaluate Adaptive Agents

Shashwat Goel, Nikhil Chandak, Arvindh Arun +5

AI agents are being increasingly deployed in dynamic, open-ended environments that require adapting to new information as it arrives. To efficiently measure this capability for rea…

cs.LG2014

Fast matrix completion without the condition number

Moritz Hardt, Mary Wootters

We give the first algorithm for Matrix Completion whose running time and sample complexity is polynomial in the rank of the unknown target matrix, linear in the dimension of the ma…

cs.SI2023

County-level Algorithmic Audit of Racial Bias in Twitter's Home Timeline

Luca Belli, Kyra Yee, Uthaipon Tantipongpipat +3

We report on the outcome of an audit of Twitter's Home Timeline ranking system. The goal of the audit was to determine if authors from some racial groups experience systematically…

cs.LG2024

What Makes ImageNet Look Unlike LAION

Ali Shirali, Moritz Hardt

ImageNet was famously created from Flickr image search results. What if we recreated ImageNet instead by searching the massive LAION dataset based on image captions alone? In this…

cs.LG2022

Retiring Adult: New Datasets for Fair Machine Learning

Frances Ding, Moritz Hardt, John Miller +1

Although the fairness community has recognized the importance of data, researchers in the area primarily rely on UCI Adult when it comes to tabular data. Derived from a 1994 US Cen…

cs.LG2024

Is your model predicting the past?

Moritz Hardt, Michael P. Kim

When does a machine learning model predict the future of individuals and when does it recite patterns that predate the individuals? In this work, we propose a distinction between t…

cs.LG2020

Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning

Esther Rolf, Max Simchowitz, Sarah Dean +4

While real-world decisions involve many competing objectives, algorithmic decisions are often evaluated with a single objective function. In this paper, we study algorithmic polici…

cs.CC2011

Fairness Through Awareness

Cynthia Dwork, Moritz Hardt, Toniann Pitassi +2

We study fairness in classification, where individuals are classified, e.g., admitted to a university, and the goal is to prevent discrimination against individuals based on their…

cs.LG2023

Causal Inference out of Control: Estimating the Steerability of Consumption

Gary Cheng, Moritz Hardt, Celestine Mendler-Dünner

Regulators and academics are increasingly interested in the causal effect that algorithmic actions of a digital platform have on consumption. We introduce a general causal inferenc…

cs.LG2018

Identity Matters in Deep Learning

Moritz Hardt, Tengyu Ma

An emerging design principle in deep learning is that each layer of a deep artificial neural network should be able to easily express the identity transformation. This idea not onl…

cs.LG2019

Model Similarity Mitigates Test Set Overuse

Horia Mania, John Miller, Ludwig Schmidt +2

Excessive reuse of test data has become commonplace in today's machine learning workflows. Popular benchmarks, competitions, industrial scale tuning, among other applications, all…