Search Results for author:
Found 7 papers, 4 papers with code
Certified Robust Neural Networks: Generalization and Corruption Resistance
We demonstrate both theoretically as well as empirically the loss to enjoy a certified level of robustness against two common types of corruption--data evasion and poisoning attacks--while ensuring guaranteed generalization.
Holistic Robust Data-Driven Decisions
However, we show how in the context of classification and regression problems that several popular regularized and robust formulations reduce to a particular case of our proposed novel formulation.
Sparse Regression: Scalable algorithms and empirical performance
A cogent feature selection method is expected to exhibit a two-fold convergence, namely the accuracy and false detection rate should converge to $1$ and $0$ respectively, as the sample size increases.
Methodology
Bootstrap Robust Prescriptive Analytics
The associated robust prescriptive methods furthermore reduce to convenient tractable convex optimization problems in the context of local learning methods such as nearest neighbors and Nadaraya-Watson learning.
Sparse Classification and Phase Transitions: A Discrete Optimization Perspective
In this paper, we formulate the sparse classification problem of $n$ samples with $p$ features as a binary convex optimization problem and propose a cutting-plane algorithm to solve it exactly.
Optimization and Control
Sparse High-Dimensional Regression: Exact Scalable Algorithms and Phase Transitions
We present a novel binary convex reformulation of the sparse regression problem that constitutes a new duality perspective.
Sparse Hierarchical Regression with Polynomials
The ability of our method to identify all $k$ relevant inputs and all $\ell$ monomial terms is shown empirically to experience a phase transition.
