t-SNE Explained: the Math Behind Preserving Local Neighborhoods in High-Dimensional Visualization
burny_tech · x · 2026-09-19
A refresher on t-SNE's core math: conditional similarities in high-dimensional space are computed with Gaussian kernels, while low-dimensional similarities use a heavy-tailed Student-t distribution. The embedding is found by minimizing KL divergence via gradient descent — the heavy tails help separate moderately distant points while keeping neighbors together, making it ideal for 2D/3D visualization.
More from Research
- SE veteran calls for de-anonymized peer review to catch AI-generated paper spam — moarbugs · 2026-09-19
- OpenDataArena's Spark-234K, a 234K-sample machine-generated English text dataset, trends on Hugging Face — OpenDataArena · 2026-09-19
- match-seq: Viral Proximity Barcoding Enables In Vivo Intercellular CRISPR Screens — anshulkundaje · 2026-09-19
- Robot Control Explained for ML People: PID, FK/IK, and Why ACT Outputs Joint Angles — kamathsblog · 2026-09-19
- Google's ScientistTwo agent runs the full AI research discovery loop unsupervised — dair_ai · 2026-09-19
- RSI-Exam leaderboard update: GPT-6-astra tops recursive self-improvement benchmark at 0.5126 — yuyinzhou_cs · 2026-09-19