The Optimal Sample Complexity of Multiclass and List Learning
Settles a long-standing open problem in learning theory by determining the optimal sample complexity for multiclass classification, benefiting the theoretical machine learning community.
The paper resolves the optimal sample complexity of multiclass classification by proving that the maximum hypergraph density of a multiclass hypothesis class is bounded by its DS dimension, confirming a conjecture by Daniely and Shalev-Shwartz (2014). This yields tight sample complexity bounds for both multiclass and list learning.
While the optimal sample complexity of binary classification in terms of the VC dimension is well-established, determining the optimal sample complexity of multiclass classification has remained open. The appropriate complexity parameter for multiclass classification is the DS dimension, and despite significant efforts, a gap of $\sqrt{\text{DS}}$ has persisted between the upper and lower bounds on sample complexity. Recent work by Hanneke et al. (2026) shows a novel algebraic characterization of multiclass hypothesis classes in terms of their DS dimension. Building up on this, we show that the maximum hypergraph density of any multiclass hypothesis class is upper-bounded by its DS dimension. This proves a longstanding conjecture of Daniely and Shalev-Shwartz (2014). As a consequence, we determine the optimal dependence of the sample complexity on the DS dimension for multiclass as well as list learning.