Research / PEFT

Everything on this page is an opt-in research surface. No certified accuracy claims. Production default remains frozen trunk + Bayesian head (for_deployment).

Install:

pip install nimbus-bci[train]   # torch >= 2.14

BaLoRA + composed uncertainty

Bayesian LoRA on the trunk with composed trunk+head BALD sampling:

from nimbus_bci import Personalizer, Recipe, MCSamplingConfig

# Auto-wraps a raw torch trunk (rank=4 default)
p = Personalizer.for_balora(torch_model, ["left", "right"], rank=4)
p.fit(X_cal, y_cal)
# Escalate trunk adaptation when your protocol calls for it:
# p.adapt_trunk(...)  # see API / AdaptArm registry

# Or Recipe.BALORA_COMPOSED / MCSamplingConfig.balora() presets:
# MCSamplingConfig.balora(n_trunk=8, n_head=32)
# MCSamplingConfig.balora_fast() / .balora_standard()

mc_samples=(n_trunk, n_head) marginalises over the BaLoRA α-posterior and the Bayesian head.

Trunk-arm PEFT

Tool	Role
`wrap_lora`	LoRA on Linear + Conv2d
FiLM rung	Feature-wise linear modulation arm
`AdaptArm` registry	Named arms with measured cost estimates
`Personalizer.for_lora(...)`	Convenience factory when the trunk already has / needs LoRA

from nimbus_bci.middleware.adapters.lora import wrap_lora
from nimbus_bci import Personalizer, available_arms

enc = wrap_lora(torch_model, ...)
p = Personalizer.for_research(enc, ["left", "right"])
print(available_arms())  # cost estimates for trainer arms

Trainer arms accept hyperparameter overrides. Prefer measuring cost on your hardware before comparing to head-only partial_fit.

Other research-only mechanisms

API	Role
`adapt_pseudo`	Gated self-training on an unlabeled stream
`fit_tent`	Entropy minimization over trunk norm affine params
`T3APrototypeChannel`	Optimization-free recalibration on verified labels
`adapt_errp`	Soft-negative conjugate update from an external ErrP probability
`fit_population`	Warm-start from pooled LOSO posteriors + prior-predictive gate

These ship for experimentation — confirmation-drift and protocol risks apply.

Next read

Evidence

When head-only beats FT on cost

Transforms

Embedding-space alignment

Migration to 0.6

Breaking changes and adoption map

API Reference

Personalizer methods and configs

Getting started

Personalizer

Python SDK

Inference & pipelines

Heads & models

Concepts

Julia SDK

Cloud API

Examples

Research / PEFT

BaLoRA + composed uncertainty

Trunk-arm PEFT

Other research-only mechanisms

Next read

Evidence

Transforms

Migration to 0.6

API Reference

​BaLoRA + composed uncertainty

​Trunk-arm PEFT

​Other research-only mechanisms

​Next read

Evidence

Transforms

Migration to 0.6

API Reference

BaLoRA + composed uncertainty

Trunk-arm PEFT

Other research-only mechanisms

Next read