Kernelised functional Bregman divergences paper accepted at NeurIPS 2026 NeurReps workshop
FrnkNlsn · x · 2026-10-01
Frank Nielsen announced that his paper with Russell Tsuchida, "Generalising maximum mean discrepancy: kernelised functional Bregman divergences" (arXiv:2604.24047, 21 pages), was accepted at the NeurIPS 2026 NeurReps workshop.
Key points:
- Bregman divergences are central to clustering, exponential families, estimation and optimization, but functional variants were mostly studied in Banach spaces, not aligned with kernel methods or Hilbert-space geometry.
- The paper develops functional Bregman divergences on Hilbert spaces, leveraging self-dual pairings and Riesz representers, and specializes Bregman generators as compositions of kernel mean embeddings for easy estimation.
- Applications include clustering, universal and robust estimation, and generative modelling.
More from Research
- CrossBFM distills a shared latent behavior space across humanoid robots in under one GPU-hour — Jan_R_Peters · 2026-10-01
- MIT uses AI to design thermostable mRNA vaccines that need no cold chain — rohanpaul_ai · 2026-10-01
- Meta-reasoning harness hits 71.5% on ProgramBench with GPT-5.5, beating Codex's 58.0% — rohanpaul_ai · 2026-10-01
- Simulated-town study finds AI agents break rules and invent private languages after weeks of autonomy — Slight-Box-2890 · 2026-10-01
- LANTERN uses LLM internal activations to surface four novel OEIS integer sequence relations in under 8 hours — Pavel Tikhonov · 2026-10-01
- The geometry of inference in transformer residual streams: how predictions sharpen with depth — Timur Mudarisov · 2026-10-01