Comments (2)
The main reason is that it is possible to efficiently reconstruct the forward pass during the backward pass. Doing so means we don't need to hold intermediate values in memory.
This is actually a very special case of the "continuous adjoint method" sometimes used in differential equations (e.g. as popularised for neural ODEs; also see Chapter 5 of https://arxiv.org/abs/2202.02435). Although in our case, because of the piecewise linear structure, we can recompute things without suffering any numerical truncation error. (Only floating point error, which usually isn't that bad.)
from signatory.
Really insightful views! I'll read this paper carefully.
Cheers!
from signatory.
Related Issues (20)
- How to generate the signature of each point in a sliding-window manner? HOT 4
- fail to install signatory HOT 3
- ERROR: Undefined symbol building with torch 1.8.0 HOT 1
- Error: unable to import signatory HOT 2
- Error installing signatory and torch simultaneously HOT 4
- Error Installing Signatory 1.2.5 HOT 1
- import signatory error HOT 1
- Installation on M1 Macbook HOT 4
- ERROR: No matching distribution found for signatory==1.2.7.1.11.0 HOT 1
- Is it possible to expose the exp map to the Python API via a logsignature_to_signature function? HOT 2
- Confusion about comment of the "include_original" in Augment
- No signatory 1.2.7 on PyPI HOT 1
- Is it possible to calculate new path points on signature? HOT 2
- How to invert log-signatures ? HOT 3
- Move to a modern poetry setup HOT 1
- Error importing signatory on Colab (undefined symbol error) HOT 2
- Signatory slower than iisignature HOT 3
- Installation error of signatory==1.2.6.1.7.1 on GCP HOT 1
- Error running from python3.9.9 on a guix system HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from signatory.