Search Results for author:
Found 5 papers, 1 papers with code
AdaBoost and robust one-bit compressed sensing
This paper studies binary classification in robust one-bit compressed sensing with adversarial errors.
On the robustness of minimum norm interpolators and regularized empirical risk minimizers
This article develops a general theory for minimum norm interpolating estimators and regularized empirical risk minimizers (RERM) in linear models in the presence of additive, potentially adversarial, errors.
On the robustness of the minimum $\ell_2$ interpolator
For low signal to noise ratio, we also provide lower bound holding with large probability.
ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels
When $r_N$ is minimax-rate-optimal in a non-contaminated setting, the rate $r_N + AL|\cO|/N$ is also minimax-rate-optimal when $|\cO|$ outliers contaminate the label.
Gradient Descent can Learn Less Over-parameterized Two-layer Neural Networks on Classification Problems
Most studies especially focused on the regression problems with the squared loss function, except for a few, and the importance of the positivity of the neural tangent kernel has been pointed out.
