← Search

Sawan Kumar

2 accepted papers

2026

Scalable Random Wavelet Features: Efficient Non-Stationary Kernel Approximation with Convergence Guarantees

ICLR 2026poster

Modeling non-stationary processes, where statistical properties vary across the input domain, is a critical challenge in machine learning; yet most scalable methods rely on a simplifying assumption of stationarity. This forces a difficult trade-off: use expressive but computationally demanding model…

Cited by 0SourceScholar