Assistant Professor, Yale University
2 papers at NeurIPS 2025
We revisit the single-index models and argue that spherical harmonics, not Hermite polynomials, are a natural basis. We characterize the complexity for any spherically symmetric input measure, & provide several new insights for the Gaussian case.
We propose a refined Franz-Parisi criterion, and show that it is equivalent to Statistical Query lower bounds under a mild, verifiable assumption satisfied by a broad class of statistical models.
