Approximately Correct Machine Intelligence (ACMI) Lab's repositories
cmu-10717-the-art-of-the-paper
Official repository for CMU Machine Learning Department's 10717: "The Art of the Paper".
cmu-10721-philosophy-machine-intelligence
Official repository for CMU Machine Learning Department's 10721: "Philosophical Foundations of Machine Intelligence".
superheroes-deep-learning
Thrilling tales of heroic feats by ML's larger-than-life champions.
counterfactually-augmented-data
Learning the Difference that Makes a Difference with Counterfactually-Augmented Data
cmu-10732-robustness-adaptivity-shift
Official repository for CMU Machine Learning Department's 10732: Robustness and Adaptivity in Shifting Environments
PU_learning
Code and results accompanying our paper titled Mixture Proportion Estimation and PU Learning: A Modern Approach at Neurips 2021 (Spotlight)
modular-summarization
code for modular summarization work published in ACL2021 by Krishna et al
Open-Set-Label-Shift
Code and results accompanying our paper titled Domain Adaptation under Open Set Label Shift
papers-worth-reading
A Curated Set of Papers Actually Worth Reading
pretraining-with-nonsense
Pretraining summarization models using a corpus of nonsense
local-causal-discovery
Code for the paper "Local Causal Discovery for Estimating Causal Effects".
online-moment-selection
Code for the paper "Efficient Online Estimation of Causal Effects by Deciding What to Observe".
RATT_generalization_bound
Code and results accompanying our paper titled RATT: Leveraging Unlabeled Data to guarantee generalization at ICML 2021 (Long Talk)
EvaluationOverTime
Python package for Evaluating Medical Datasets Over Time (EMDOT).
OnlineLabelShift
Code accompanying our paper titled Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms
imp-regularizers
Official implementation for the ICLR 2023 paper: Disentangling the Mechanisms Behind Implicit Regularization in SGD.
Latent-Label-Shift-DDFA
Code and results accompanying our paper titled Unsupervised Learning under Latent Label Shift at NeurIPS 2022
Missingness-Shift
Code accompanying our paper "Domain Adaptation under Missingness Shift" at AISTATS 2023.