
Causal Inference Struggles with Agency on Online Platforms
Online platforms regularly conduct randomized experiments to understand ...
read it

Alternative Microfoundations for Strategic Classification
When reasoning about strategic behavior in a machine learning context it...
read it

Patterns, predictions, and actions: A story about machine learning
This graduate textbook on machine learning tells a story of how patterns...
read it

Revisiting Design Choices in Proximal Policy Optimization
Proximal Policy Optimization (PPO) is a popular deep policy gradient alg...
read it

From Optimizing Engagement to Measuring Value
Most recommendation engines today are based on predicting user engagemen...
read it

Stochastic Optimization for Performative Prediction
In performative prediction, the choice of a model influences the distrib...
read it

Balancing Competing Objectives with Noisy Data: ScoreBased Classifiers for WelfareAware Machine Learning
While realworld decisions involve many competing objectives, algorithmi...
read it

Performative Prediction
When predictions support decisions they may influence the outcome they a...
read it

Strategic Adaptation to Classifiers: A Causal Perspective
Consequential decisionmaking incentivizes individuals to adapt their be...
read it

TestTime Training for OutofDistribution Generalization
We introduce a general approach, called testtime training, for improvin...
read it

Linear Dynamics: Clustering without identification
Clustering time series is a delicate task; varying lengths and temporal ...
read it

Explaining an increase in predicted risk for clinical alerts
Much work aims to explain a model's prediction on a static input. We con...
read it

Model Similarity Mitigates Test Set Overuse
Excessive reuse of test data has become commonplace in today's machine l...
read it

The advantages of multiple classes for reducing overfitting from test set reuse
Excessive reuse of holdout data can lead to overfitting. However, there ...
read it

Identity Crisis: Memorization and Generalization under Extreme Overparameterization
We study the interplay between memorization and generalization of overpa...
read it

Natural Analysts in Adaptive Data Analysis
Adaptive data analysis is frequently criticized for its pessimistic gene...
read it

Massively Parallel Hyperparameter Tuning
Modern learning models are characterized by large hyperparameter spaces....
read it

Sanity Checks for Saliency Maps
Saliency methods have emerged as a popular tool to highlight features in...
read it

Group calibration is a byproduct of unconstrained learning
Much recent work on fairness in machine learning has focused on how well...
read it

The Social Cost of Strategic Classification
Consequential decisionmaking typically incentivizes individuals to beha...
read it

Model Reconstruction from Model Explanations
We show through theory and experiment that gradientbased explanations o...
read it

When Recurrent Models Don't Need To Be Recurrent
We prove stable recurrent neural networks are well approximated by feed...
read it

Delayed Impact of Fair Machine Learning
Fairness in machine learning has predominantly been studied in static cl...
read it

Avoiding Discrimination through Causal Reasoning
Recent work on fairness in machine learning has focused on various stati...
read it

Identity Matters in Deep Learning
An emerging design principle in deep learning is that each layer of a de...
read it

Gradient Descent Learns Linear Dynamical Systems
We prove that gradient descent efficiently converges to the global optim...
read it

Train faster, generalize better: Stability of stochastic gradient descent
We show that parametric models trained by a stochastic gradient method (...
read it

Fast matrix completion without the condition number
We give the first algorithm for Matrix Completion whose running time and...
read it

Tight bounds for learning a mixture of two gaussians
We consider the problem of identifying the parameters of an unknown mixt...
read it

Understanding Alternating Minimization for Matrix Completion
Alternating Minimization is a widely used and empirically successful heu...
read it
Moritz Hardt
is this you? claim profile