upd examples and readme

README.md

@@ -21,7 +21,7 @@ pip install -e .
 ## Examples
 Examples are placed in the [`examples`](./examples) directory.
 
-We encourage those who are interested in using this library to take a look at `examples/ode_demo.py` for understanding how to use `torchdiffeq` to fit a simple spiral ODE.
+We encourage those who are interested in using this library to take a look at [`examples/ode_demo.py`](./examples/ode_demo.py) for understanding how to use `torchdiffeq` to fit a simple spiral ODE.
 
 <p align="center">
 <img align="middle" src="./assets/ode_demo.gif" alt="ODE Demo" width="500" height="250" />
@@ -74,3 +74,15 @@ Fixed-step:
 
 ### References
 [1] Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, David Duvenaud. "Neural Ordinary Differential Equations." *Advances in Neural Processing Information Systems.* 2018.
+
+---
+
+If you found this library useful in your research, please consider citing
+```
+@article{chen2018neural,
+  title={Neural Ordinary Differential Equations},
+  author={Chen, Ricky T. Q. and Rubanova, Yulia and Bettencourt, Jesse and Duvenaud, David},
+  journal={Advances in Neural Information Processing Systems},
+  year={2018}
+}
+```

examples/ode_demo.py

@@ -8,7 +8,7 @@
 import torch.optim as optim
 
 parser = argparse.ArgumentParser('ODE demo')
-parser.add_argument('--method', type=str, default='dopri5')
+parser.add_argument('--method', type=str, choices=['dopri5', 'adams'], default='dopri5')
 parser.add_argument('--data_size', type=int, default=1000)
 parser.add_argument('--batch_time', type=int, default=10)
 parser.add_argument('--batch_size', type=int, default=20)
@@ -38,7 +38,7 @@ def forward(self, t, y):
 
 
 with torch.no_grad():
-    true_y = odeint(Lambda(), true_y0, t)
+    true_y = odeint(Lambda(), true_y0, t, method='dopri5')
 
 
 def get_batch():
@@ -152,7 +152,7 @@ def update(self, val):
     ii = 0
 
     func = ODEFunc()
-    optimizer = optim.Adam(func.parameters(), lr=1e-3)
+    optimizer = optim.RMSprop(func.parameters(), lr=1e-3)
     end = time.time()
 
     time_meter = RunningAverageMeter(0.97)