research
∙
06/27/2023
What Makes ImageNet Look Unlike LAION
ImageNet was famously created from Flickr image search results. What if ...
share
research
∙
06/13/2023
Questioning the Survey Responses of Large Language Models
As large language models increase in capability, researchers have starte...
research
∙
06/12/2023
Unprocessing Seven Years of Algorithmic Fairness
Seven years ago, researchers proposed a postprocessing method to equaliz...
research
∙
05/29/2023
Test-Time Training on Nearest Neighbors for Large Language Models
Many recent efforts aim to augment language models with relevant informa...
research
∙
04/13/2023
Difficult Lessons on Social Prediction from Wisconsin Public Schools
Early warning systems (EWS) are prediction algorithms that have recently...
research
∙
02/10/2023
Causal Inference out of Control: Estimating the Steerability of Consumption
Regulators and academics are increasingly interested in the causal effec...
research
∙
02/08/2023
Algorithmic Collective Action in Machine Learning
We initiate a principled study of algorithmic collective action on digit...
research
∙
10/06/2022
A Theory of Dynamic Benchmarks
Dynamic benchmarks interweave model fitting and data collection in an at...
research
∙
06/23/2022
Backward baselines: Is your model predicting the past?
When does a machine learning model predict the future of individuals and...
research
∙
06/19/2022
Adversarial Scrutiny of Evidentiary Statistical Software
The U.S. criminal legal system increasingly relies on software output to...
research
∙
03/31/2022
Performative Power
We introduce the notion of performative power, which measures the abilit...
research
∙
10/21/2021
Algorithmic Amplification of Politics on Twitter
Content on Twitter's home timeline is selected and ordered by personaliz...
research
∙
08/10/2021
Retiring Adult: New Datasets for Fair Machine Learning
Although the fairness community has recognized the importance of data, r...
research
∙
07/19/2021
Causal Inference Struggles with Agency on Online Platforms
Online platforms regularly conduct randomized experiments to understand ...
research
∙
06/24/2021
Alternative Microfoundations for Strategic Classification
When reasoning about strategic behavior in a machine learning context it...
research
∙
02/10/2021
Patterns, predictions, and actions: A story about machine learning
This graduate textbook on machine learning tells a story of how patterns...
research
∙
09/23/2020
Revisiting Design Choices in Proximal Policy Optimization
Proximal Policy Optimization (PPO) is a popular deep policy gradient alg...
research
∙
08/21/2020
From Optimizing Engagement to Measuring Value
Most recommendation engines today are based on predicting user engagemen...
research
∙
06/12/2020
Stochastic Optimization for Performative Prediction
In performative prediction, the choice of a model influences the distrib...
research
∙
03/15/2020
Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning
While real-world decisions involve many competing objectives, algorithmi...
research
∙
02/16/2020
Performative Prediction
When predictions support decisions they may influence the outcome they a...
research
∙
10/23/2019
Strategic Adaptation to Classifiers: A Causal Perspective
Consequential decision-making incentivizes individuals to adapt their be...
research
∙
09/29/2019
Test-Time Training for Out-of-Distribution Generalization
We introduce a general approach, called test-time training, for improvin...
research
∙
08/02/2019
Linear Dynamics: Clustering without identification
Clustering time series is a delicate task; varying lengths and temporal ...
research
∙
07/10/2019
Explaining an increase in predicted risk for clinical alerts
Much work aims to explain a model's prediction on a static input. We con...
research
∙
05/29/2019
Model Similarity Mitigates Test Set Overuse
Excessive reuse of test data has become commonplace in today's machine l...
research
∙
05/24/2019
The advantages of multiple classes for reducing overfitting from test set reuse
Excessive reuse of holdout data can lead to overfitting. However, there ...
research
∙
02/13/2019
Identity Crisis: Memorization and Generalization under Extreme Overparameterization
We study the interplay between memorization and generalization of overpa...
research
∙
01/30/2019
Natural Analysts in Adaptive Data Analysis
Adaptive data analysis is frequently criticized for its pessimistic gene...
research
∙
10/13/2018
Massively Parallel Hyperparameter Tuning
Modern learning models are characterized by large hyperparameter spaces....
research
∙
10/08/2018
Sanity Checks for Saliency Maps
Saliency methods have emerged as a popular tool to highlight features in...
research
∙
08/29/2018
Group calibration is a byproduct of unconstrained learning
Much recent work on fairness in machine learning has focused on how well...
research
∙
08/25/2018
The Social Cost of Strategic Classification
Consequential decision-making typically incentivizes individuals to beha...
research
∙
07/13/2018
Model Reconstruction from Model Explanations
We show through theory and experiment that gradient-based explanations o...
research
∙
05/25/2018
When Recurrent Models Don't Need To Be Recurrent
We prove stable recurrent neural networks are well approximated by feed-...
research
∙
03/12/2018
Delayed Impact of Fair Machine Learning
Fairness in machine learning has predominantly been studied in static cl...
research
∙
06/08/2017
Avoiding Discrimination through Causal Reasoning
Recent work on fairness in machine learning has focused on various stati...
research
∙
11/14/2016
Identity Matters in Deep Learning
An emerging design principle in deep learning is that each layer of a de...
research
∙
09/16/2016
Gradient Descent Learns Linear Dynamical Systems
We prove that gradient descent efficiently converges to the global optim...
research
∙
09/03/2015
Train faster, generalize better: Stability of stochastic gradient descent
We show that parametric models trained by a stochastic gradient method (...
research
∙
07/15/2014
Fast matrix completion without the condition number
We give the first algorithm for Matrix Completion whose running time and...
research
∙
04/19/2014
Tight bounds for learning a mixture of two gaussians
We consider the problem of identifying the parameters of an unknown mixt...
research
∙
12/03/2013