Evidence Before Expansion: Reuse, Spawn, or Defer in Lifelong Expert Pools
Streaming systems that maintain a pool of expert models must repeatedly decide whether to reuse an existing expert for arriving data, spawn a new one, or defer. We present a decision layer that makes all three outcomes statistically meaningful. Reuse and spawn are posed as one-sided sequential hypotheses on a conditional (mechanism-level) discrepancy, separated by an indifference zone; defer is exactly the state in which neither betting e-process has accumulated sufficient evidence. We prove finite-time anytime validity for the observable surrogate discrepancy of a predictable discriminator sequence, and an unconditional one-sided transfer to the population quantity in which each side's slack is the excess risk of a single discriminator; an empirically observed downward-bias regularity makes the spawn side exactly conservative. Recency without sacrificing the guarantee is obtained by a restarted e-detector: a bank of unwindowed betting supermartingales at geometrically spaced restart times (O(log t) memory), with the error budget spent over restart instances, which preserves lifetime anytime validity; spending over expert-creation order likewise controls multiplicity for unboundedly many experts. On synthetic multi-concept streams, Electricity, Covertype, and the recurrence-heavy INSECTS benchmark, the instance-accounted restarted bank achieves zero false spawns and zero false reuses after switches and matches or exceeds the retired windowed heuristic (INSECTS-reoccurring accuracy 0.675), making the deployed algorithm and the guaranteed algorithm one and the same.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA
Large language model (LLM) agents still struggle with long-term memory question answering, where answer-supporting evidence is often scattered across long conversational histories and buried in substantial irrelevant con…
Reinforcement LearningQuestion AnsweringOmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning
Unified multimodal large language models (MLLMs) and multi-agent systems have advanced visual generation. However, three limitations remain. (1) Existing methods often distill task-specific experience with limited genera…
Why Ask One When You Can Ask $k$? Two-Stage Learning-to-Defer to the Top-$k$ Experts
Although existing Learning-to-Defer (L2D) frameworks support multiple experts, they allocate each query to a single expert, limiting their ability to leverage collective expertise in complex decision-making scenarios. To…
Decision MakingTripLe: Revisiting Pretrained Model Reuse and Progressive Learning for Efficient Vision Transformer Scaling and Searching
One promising way to accelerate transformer training is to reuse small pretrained models to initialize the transformer, as their existing representation power facilitates faster model convergence. Previous works desi…
Knowledge DistillationNeural Architecture SearchDon't Commit Alone: Joint Token Commitment in Diffusion Large Language Models
Diffusion large language models (dLLMs) commit multiple tokens per denoising step by decoding each selected position independently from the shared context; when those positions are dependent, the resulting factorization …