Moritz Hardt

papers

818

total citations

papers (11)

Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the data

ICLR 2025

citations

Unprocessing Seven Years of Algorithmic Fairness

ICLR 2024arXiv

citations

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

ICML 2024arXiv

citations

Allocation Requires Prediction Only if Inequality Is Low

ICML 2024arXiv

citations

How Benchmark Prediction from Fewer Data Misses the Mark

NEURIPS 2025arXiv

citations

Causal Inference from Competing Treatments

ICML 2024arXiv

citations

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

ICML 2024

citations

Causal Inference out of Control: Estimating Performativity without Treatment Randomization

ICML 2024

citations

Moritz Hardt

papers (11)

Retiring Adult: New Datasets for Fair Machine Learning

Stochastic Optimization for Performative Prediction

Performative Power

Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the data

Unprocessing Seven Years of Algorithmic Fairness

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

Allocation Requires Prediction Only if Inequality Is Low

How Benchmark Prediction from Fewer Data Misses the Mark

Causal Inference from Competing Treatments

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

Causal Inference out of Control: Estimating Performativity without Treatment Randomization

papers (11)

Retiring Adult: New Datasets for Fair Machine Learning

Stochastic Optimization for Performative Prediction

Performative Power

Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the data

Unprocessing Seven Years of Algorithmic Fairness

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

Allocation Requires Prediction Only if Inequality Is Low

How Benchmark Prediction from Fewer Data Misses the Mark

Causal Inference from Competing Treatments

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

Causal Inference out of Control: Estimating Performativity without Treatment Randomization