563 citations · 648 across the 6 of their papers we have counts for
6 papers
Analytics for Quality Assurance for Item Pools (AQuAP): Monitoring and Maintaining Item Bank Health in AI-Driven Assessment Systems
Alina A. von Davier, Xiaowan Zhang, Yigal Attali +5
The large-scale digitization of educational assessment has made the continuous oversight of item banks both essential and complex. This paper presents Analytics for Quality Assuran…
S2A3: Thompson Sampling and Stochastic Exposure Control for High-Stakes CATs
James Sharpnack, Alexander Tsigler, J. R. Lockwood +2
High-stakes computerized adaptive tests (CATs) require a continuous supply of calibrated items, yet traditional item piloting is slow, expensive, and operationally hazardous. We in…
Benign Overfitting and the Geometry of the Ridge Regression Solution in Binary Classification
Alexander Tsigler, Luiz F. O. Chamon, Spencer Frei +1
In this work, we investigate the behavior of ridge regression in an overparameterized binary classification task. We assume examples are drawn from (anisotropic) class-conditional…
Benign overfitting in ridge regression
A. Tsigler, P. L. Bartlett
In many modern applications of deep learning the neural network has many more parameters than the data points used for its training. Motivated by those practices, a large body of r…
Benign Overfitting in Linear Regression
Peter L. Bartlett, Philip M. Long, Gábor Lugosi +1
The phenomenon of benign overfitting is one of the key mysteries uncovered by deep learning methodology: deep neural networks seem to predict well, even with a perfect fit to noisy…
Optimality of codes with respect to error probability in Gaussian noise
Alexey Balitskiy, Roman Karasev, Alexander Tsigler
We consider geometrical optimization problems related to optimizing the error probability in the presence of a Gaussian noise. One famous questions in the field is the "weak simple…