zackchase / label_shift
A simple algorithm to identify and correct for label shift.
☆22Updated 6 years ago
Related projects: ⓘ
- An Empirical Study of Invariant Risk Minimization☆28Updated 4 years ago
- ☆29Updated 3 years ago
- ☆32Updated 11 months ago
- MODALS: Modality-agnostic Automated Data Augmentation in the Latent Space☆40Updated 3 years ago
- Label shift experiments☆15Updated 3 years ago
- Model Patching: Closing the Subgroup Performance Gap with Data Augmentation☆42Updated 3 years ago
- Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning (AISTATS 2022 Oral)☆38Updated last year
- Using / reproducing DAC from the paper "Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees"☆25Updated 3 years ago
- Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"☆24Updated 2 years ago
- Code to study the generalisability of benchmark models on non-stationary EHRs.☆14Updated 5 years ago
- ☆19Updated 4 years ago
- ☆40Updated last year
- Code accompanying paper: Meta-Learning to Improve Pre-Training☆36Updated 2 years ago
- Active and Sample-Efficient Model Evaluation☆24Updated 3 years ago
- ☆33Updated 3 years ago
- Implementation of: Kristiadi, Agustinus, and Asja Fischer. "Predictive Uncertainty Quantification with Compound Density Networks." (2019)…☆15Updated 2 years ago
- Code for our ICML '19 paper: Neural Network Attributions: A Causal Perspective.☆50Updated 2 years ago
- (ICML 2021) Mandoline: Model Evaluation under Distribution Shift☆30Updated 3 years ago
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆35Updated 2 years ago
- An Empirical Framework for Domain Generalization In Clinical Settings☆27Updated 2 years ago
- MDL Complexity computations and experiments from the paper "Revisiting complexity and the bias-variance tradeoff".☆17Updated last year
- ☆27Updated 3 years ago
- Code for Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding☆21Updated last year
- ☆37Updated 3 years ago
- Code for the paper "Rethinking Importance Weighting for Deep Learning under Distribution Shift".☆24Updated 3 years ago
- Official PyTorch implementation of "Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error"☆30Updated last year
- ModelDiff: A Framework for Comparing Learning Algorithms☆52Updated last year
- Pytorch implementation for "The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction"☆33Updated 2 years ago
- Investigate the speed of adaptation of structural causal models☆16Updated 3 years ago
- Code for the paper "Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers" published in ICLR 2019☆13Updated 5 years ago