resdag 0.6.0

PyTorch-native reservoir computing library with GPU acceleration

ResDAG

Reservoir computing for PyTorch.
Compose reservoir models as DAGs, train readouts with a single algebraic solve, run it all on the GPU.

---

ResDAG treats reservoir models — echo state networks and beyond — as ordinary PyTorch layers. Reservoirs, readouts, and transforms are nn.Modules wired together with a functional API; training a readout is one teacher-forced pass and one conjugate-gradient ridge solve, with no epochs. Models move with .to(device), serialize with state_dict(), and embed in larger PyTorch pipelines, optimizers included.

Documentation →

Installation

pip install resdag            # core
pip install "resdag[hpo]"     # + Optuna hyperparameter optimization

Python ≥ 3.11, PyTorch ≥ 2.10.

Try it

A reservoir forecaster on a toy signal, end to end:

import torch
import resdag as rd

t = torch.linspace(0, 60, 3000)
data = torch.sin(t).reshape(1, -1, 1)            # (batch, time, features)

warmup, train, target, f_warmup, val = rd.utils.prepare_esn_data(
    data, warmup_steps=100, train_steps=2000, val_steps=300)

model = rd.models.classic_esn(reservoir_size=300, feedback_size=1, output_size=1)
rd.ESNTrainer(model).fit((warmup,), (train,), targets={"output": target})

prediction = model.forecast(f_warmup, horizon=300)   # autoregressive, (1, 300, 1)

The first forecast walkthrough does the same on the Lorenz attractor, with the math explained.

Compose, don't configure

Architectures are DAGs you wire, not options you toggle. Two reservoirs on different timescales, read out together:

from resdag import CGReadoutLayer, Concatenate, ESNModel, reservoir_input
from resdag.layers import ESNLayer

inp    = reservoir_input(3)
fast   = ESNLayer(64, feedback_size=3, leak_rate=1.0, spectral_radius=0.9)(inp)
slow   = ESNLayer(64, feedback_size=3, leak_rate=0.2, spectral_radius=0.9)(inp)
merged = Concatenate()(fast, slow)
model  = ESNModel(inp, CGReadoutLayer(128, 3, name="output")(merged))

Branches, feature augmentations, and multiple readout heads compose the same way — one reservoir, squared-state augmentation, two heads:

All heads fit in a single pass, in dependency order. The composition handbook covers the patterns.

Documentation

Start	Install, a first trained forecaster, the mental model
Build	Layers, readouts, architectures, topologies, initializers
Work	Training paths, forecasting with drivers, tuning, GPU
Theory	Every equation, stated against the code
Reference	The full public API

Ecosystem

Built on pytorch_symbolic for graph composition. Pairs with TSDynamics, a companion library of dynamical systems — it generates the systems, ResDAG forecasts them.

Contributing

See CONTRIBUTING.md — releases are automated from conventional commits, and most component types are one registry decorator away.

License

MIT — © Daniel Estevez-Moya