Stabilizing Bandit Mixture-of-Experts and Zipfian Stream Clustering via Router Replay and Clamped Laguerre Potentials

Discrete routing rules assign specialist experts, cluster prototypes, or memory blocks without evaluating unchosen candidates. In partial-feedback or imbalanced-stream settings, standard gradient and optimal-transport updates lead to unstable assignments. When routing parameters are updated across multiple epochs on logged bandit data, router weights drift from the behavior distribution. This drift flips expert assignments and distorts credit attribution. Similarly, in online clustering with bursty Zipfian class arrivals, prototype collapse occurs when optimal-transport potentials enforce uniform marginals within micro-batches or accumulate unbounded load debt. Here, we propose two methods: Rollout Router Replay with Dense Control-Variate Mixing (R3-DenseMixer) for contextual-bandit mixtures of experts, and Windowed Clamped Laguerre Debt for imbalanced stream clustering. Router replay fixes routing decisions to the behavior rollout during inner updates and centers gradients around an all-expert critic, giving unbiased updates with lower variance. Clamped Laguerre potentials restrict load debt over a sliding window inside dispersion-scaled power diagrams, ensuring invariance to positive scale in each coordinate and preserving rare prototypes. On 30 unseen contextual-bandit benchmarks, R3-DenseMixer achieves a median test loss of 0.6928 (p_holm <= 0.00736 against all baselines). In bursty Zipfian streams, clamped Laguerre routing raises median Adjusted Rand Index to 0.6024.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-19
DOI
https://doi.org/10.5281/zenodo.24374079
Primary Topic
Advanced Bandit Algorithms Research
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Stabilizing Bandit Mixture-of-Experts and Zipfian Stream Clustering via Router Replay and Clamped Laguerre Potentials

Felipe Provezano Coutinho
Zenodo (CERN European Organization for Nuclear Research)
Advanced Bandit Algorithms Research
preprint

Stabilizing Bandit Mixture-of-Experts and Zipfian Stream Clustering via Router Replay and Clamped Laguerre Potentials

Felipe Provezano Coutinho
preprint en

Abstract

Discrete routing rules assign specialist experts, cluster prototypes, or memory blocks without evaluating unchosen candidates. In partial-feedback or imbalanced-stream settings, standard gradient and optimal-transport updates lead to unstable assignments. When routing parameters are updated across multiple epochs on logged bandit data, router weights drift from the behavior distribution. This drift flips expert assignments and distorts credit attribution. Similarly, in online clustering with bursty Zipfian class arrivals, prototype collapse occurs when optimal-transport potentials enforce uniform marginals within micro-batches or accumulate unbounded load debt. Here, we propose two methods: Rollout Router Replay with Dense Control-Variate Mixing (R3-DenseMixer) for contextual-bandit mixtures of experts, and Windowed Clamped Laguerre Debt for imbalanced stream clustering. Router replay fixes routing decisions to the behavior rollout during inner updates and centers gradients around an all-expert critic, giving unbiased updates with lower variance. Clamped Laguerre potentials restrict load debt over a sliding window inside dispersion-scaled power diagrams, ensuring invariance to positive scale in each coordinate and preserving rare prototypes. On 30 unseen contextual-bandit benchmarks, R3-DenseMixer achieves a median test loss of 0.6928 (p_holm <= 0.00736 against all baselines). In bursty Zipfian streams, clamped Laguerre routing raises median Adjusted Rand Index to 0.6024.

Zenodo (CERN European Organization for Nuclear Research)
Advanced Bandit Algorithms Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon