Author

Anay Mehrotra

2 papers indexed here

Fetches their full publication history.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Optimal Rates for Learning with Monotone Adversaries

This model shows that adding correctly labeled examples can make learning harder by a logarithmic factor, even for classes that admit finite mistake bounds in online learning.

Anay Mehrotra · 3 citations · ⚡2

Jun 2026

Surprises in Proper Positive-Only Learning

This work revisits and settles the question: a concept class is properly learnable from positive-only samples if and only if it has finite VC dimension and satisfies a new combinatorial condition, which is called uniform exterior separability.

S. Ben-David, Farnam Mansouri, Anay Mehrotra et al. · arXiv.org · 0 citations