Search Results for author:
Found 13 papers, 2 papers with code
On Computationally Efficient Multi-Class Calibration
Projected smooth calibration gives strong guarantees for all downstream decision makers who want to use the predictor for binary classification problems of the form: does the label belong to a subset $T \subseteq [k]$: e. g. is this an image of an animal?
Omnipredictors for Regression and the Approximate Rank of Convex Functions
An \textit{omnipredictor} for a class $\mathcal L$ of loss functions and a class $\mathcal C$ of hypotheses is a predictor whose predictions incur less expected loss than the best hypothesis in $\mathcal C$ for every loss in $\mathcal L$.
When Does Optimizing a Proper Loss Yield Calibration?
Optimizing proper loss functions is popularly believed to yield predictors with good calibration properties; the intuition being that for such losses, the global optimum is to predict the ground-truth probabilities, which is indeed calibrated.
Loss Minimization Yields Multicalibration for Large Neural Networks
We show that minimizing the squared loss over all neural nets of size $n$ implies multicalibration for all but a bounded number of unlucky values of $n$.
Swap Agnostic Learning, or Characterizing Omniprediction via Multicalibration
We establish an equivalence between swap variants of omniprediction and multicalibration and swap agnostic learning.
A Unifying Theory of Distance from Calibration
We study the fundamental question of how to define and measure the distance from calibration for probabilistic predictors.
Loss Minimization through the Lens of Outcome Indistinguishability
This decomposition highlights the utility of a new multi-group fairness notion that we call calibrated multiaccuracy, which lies in between multiaccuracy and multicalibration.
Low-Degree Multicalibration
This stringent notion -- that predictions be well-calibrated across a rich class of intersecting subpopulations -- provides its strong guarantees at a cost: the computational and sample complexity of learning multicalibrated predictors are high, and grow exponentially with the number of class labels.
KL Divergence Estimation with Multi-group Attribution
Estimating the Kullback-Leibler (KL) divergence between two distributions given samples from them is well-studied in machine learning and information theory.
Omnipredictors
We suggest a rigorous new paradigm for loss minimization in machine learning where the loss function can be ignored at the time of learning and only be taken into account when deciding an action.
Multicalibrated Partitions for Importance Weights
We significantly strengthen previous work that use the MaxEntropy approach, that define the importance weights based on a distribution $Q$ closest to $P$, that looks the same as $R$ on every set $C \in \mathcal{C}$, where $\mathcal{C}$ may be a huge collection of sets.
PIDForest: Anomaly Detection via Partial Identification
We consider the problem of detecting anomalies in a large dataset.
Efficient Anomaly Detection via Matrix Sketching
We consider the problem of finding anomalies in high-dimensional data using popular PCA based anomaly scores.
