LGDSMay 20

Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals

arXiv:2605.2142845.8
Predicted impact top 55% in LG · last 90 daysOriginality Highly original
AI Analysis

This work addresses the lack of efficient robust algorithms for multiclass linear classification with more than two classes, a problem relevant to machine learning theory.

The paper develops polynomial-time robust algorithms for multiclass linear classification under Gaussian marginals, achieving error guarantees that scale with the optimal error. For general k, they achieve error Õ(k^{3/2}√opt)+ε, and for k=3, they achieve O(opt)+ε.

We study the task of agnostic learning of multiclass linear classifiers under the Gaussian distribution. Given labeled examples $(x, y)$ from a distribution over $\mathbb{R}^d \times [k]$, with Gaussian $x$-marginal, the goal is to output a hypothesis whose error is comparable to that of the best $k$-class linear classifier. While the binary case $k=2$ has a well-developed algorithmic theory, much less is known for $k \ge 3$. Even for $k=3$, prior robust algorithms incur exponential dependence on the inverse of the desired accuracy in both complexity and representation size. In this work, we develop new structural results for multiclass linear classifiers and use them to design fully polynomial-time robust learners with dimension-independent error guarantees. Our first result shows that the standard multiclass perceptron algorithm requires super-polynomially many samples and updates, even with clean labels and Gaussian marginals, revealing a basic obstruction absent in the binary case. Our main positive result is a pairwise improper-learning framework which yields an efficient learner with error $\widetilde O(k^{3/2}\sqrt{\mathrm{opt}})+ε$ for general $k$. Additionally, we develop a sharper localization-based framework which leads to error $O(\mathrm{opt})+ε$ for $k=3$, and error $\mathrm{poly}(k)\mathrm{opt}+ε$ for geometrically regular $k$-class linear classifiers.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes