Nielsen clarifies: arithmetic mixtures are normalized by default, geometric ones are not
FrnkNlsn · x · 2026-09-18
A follow-up to the author's paper on geometric Jensen–Shannon divergences: ordinary mixtures are normalized by default when using the arithmetic mean, whereas geometric mixtures are not — which is why two variants of the geometric JSD exist. Best read alongside the original paper.
Related event: Nielsen Clarifies Two Definitions of Geometric JSD(2 posts)→
More from Research
- ML is leaving its alchemy era: assumed truths can now be instrumented and falsified — mike64_t · 2026-09-18
- Together AI paper: score centering cancels drift in off-policy RL under train-inference mismatch — PandaAshwinee · 2026-09-18
- Cell's AI-in-biology special issue debuts LongevityBench, a 17-task aging benchmark — JosephJacks_ · 2026-09-18
- After OpenAI cracks Navier-Stokes, the era of the human mathematician is ending — yeastsplainer · 2026-09-18
- Custom BB-SLAM hits 0.02m accuracy with pure visual odometry, no LiDAR or IMU — broodsugar · 2026-09-18
- AI4Science Breakthrough Said to Exceed Expectations, Could Transform Computational Chemistry — BenBlaiszik · 2026-09-18