CASSM
Thin wrapper around the bundled CASSM sparse filter/smoother.
Source
- Registry name:
cassm - Model class:
ladys.models.cassm.CASSM - Config class:
ladys.models.cassm.CASSMConfig - Source file:
src/ladys/models/cassm.py
When to use
Use CASSM when benchmarking computation-aware sparse state-space models
against latent dynamics baselines. LaDyS keeps the compact filtering core
inside ladys.models and maps it onto the shared model, loss, prediction,
and device contracts.
Inputs
forward expects observations shaped (batch, time, neurons).
Outputs
The training path returns the CASSM ELBO-style loss in extras["loss"].
predict_rates calls CASSM's native filtering path and returns nonnegative
rate predictions shaped like the input observations.
Configuration
Config for the bundled sparse CASSM adapter.
| Field | Type | Default |
|---|---|---|
name |
Literal['cassm'] |
'cassm' |
objective |
str |
'cassm_elbo' |
projection_dim |
int |
20 |
dt |
float |
0.01 |
dataset_name |
Optional[str] |
None |
save_model |
bool |
False |
use_dense_projection |
bool |
False |
health_checks |
bool |
True |
optimization |
OptimizationConfig |
OptimizationConfig(name='gradient', optimizer='Adam', lr=0.05, weight_decay=0.0, gradient_clip=300.0) |
Contracts
forwardinputs use(batch, time, neurons)observations.- Runtime outputs follow the model output contract.
- Optimizer epochs follow the optimizer contract.