1 citations · 1 across the 1 of their papers we have counts for
2 papers
cs.CL2025
Diversity Is All You Need for Contrastive Learning: Spectral Bounds on Gradient Magnitudes
Peter Ochieng
We derive non-asymptotic spectral bands that bound the squared InfoNCE gradient norm via alignment, temperature, and batch spectrum, recovering the \(1/τ^{2}\) law and closely trac…
cs.SD2023★ 1 cited
Speech Separation based on Contrastive Learning and Deep Modularization
Peter Ochieng
The current monaural state of the art tools for speech separation relies on supervised learning. This means that they must deal with permutation problem, they are impacted by the m…