Search Results for author:
Found 5 papers, 0 papers with code
Oracle Efficient Online Multicalibration and Omniprediction
We develop a new online multicalibration algorithm that is well defined for infinite benchmark classes $F$, and is oracle efficient (i. e. for any class $F$, the algorithm has the form of an efficient reduction to a no-regret learning algorithm for $F$).
Memory-Sample Lower Bounds for Learning Parity with Noise
We show that any learning algorithm for the learning problem corresponding to $M$, with error, requires either a memory of size at least $\Omega\left(\frac{k \cdot \ell}{\varepsilon} \right)$, or at least $2^{\Omega(r)}$ samples.
The Role of Randomness and Noise in Strategic Classification
Showing that if the objective is to maximize the efficiency of the classification process (defined as the accuracy of the outcome minus the sunk cost of the qualified players manipulating their features to gain a better outcome), then using randomized classifiers (that is, ones where the probability of a given feature vector to be accepted by the classifier is strictly between 0 and 1) is necessary.
Tracking and Improving Information in the Service of Fairness
As algorithmic prediction systems have become widespread, fears that these systems may inadvertently discriminate against members of underrepresented populations have grown.
Extractor-Based Time-Space Lower Bounds for Learning
We show that any learning algorithm for the learning problem corresponding to $M$ requires either a memory of size at least $\Omega\left(k \cdot \ell \right)$, or at least $2^{\Omega(r)}$ samples.
