Gast ::
| Hauptseite > Publikationsdatenbank > Optimizing Automatic Differentiation with Deep Reinforcement Learning > print |
| Hauptseite > Publikationsdatenbank > Optimizing Automatic Differentiation with Deep Reinforcement Learning > print |
| 001 | 1038109 | ||
| 005 | 20250203133240.0 | ||
| 024 | 7 | _ | |a 10.34734/FZJ-2025-01156 |2 datacite_doi |
| 037 | _ | _ | |a FZJ-2025-01156 |
| 082 | _ | _ | |a 500 |
| 100 | 1 | _ | |a Lohoff, Jamie |0 P:(DE-Juel1)192147 |b 0 |
| 111 | 2 | _ | |a 38th Conference on Neural Information Processing Systems |g NeurIPS |c Vancouver |d 2024-12-09 - 2024-12-16 |w Canada |
| 245 | _ | _ | |a Optimizing Automatic Differentiation with Deep Reinforcement Learning |
| 260 | _ | _ | |c 2024 |
| 300 | _ | _ | |a n/a |
| 336 | 7 | _ | |a CONFERENCE_PAPER |2 ORCID |
| 336 | 7 | _ | |a Conference Paper |0 33 |2 EndNote |
| 336 | 7 | _ | |a INPROCEEDINGS |2 BibTeX |
| 336 | 7 | _ | |a conferenceObject |2 DRIVER |
| 336 | 7 | _ | |a Output Types/Conference Paper |2 DataCite |
| 336 | 7 | _ | |a Contribution to a conference proceedings |b contrib |m contrib |0 PUB:(DE-HGF)8 |s 1738249743_31342 |2 PUB:(DE-HGF) |
| 336 | 7 | _ | |a Contribution to a book |0 PUB:(DE-HGF)7 |2 PUB:(DE-HGF) |m contb |
| 490 | 0 | _ | |a Advances in neural information processing systems |
| 500 | _ | _ | |a Accepted as a spotlight paper. |
| 520 | _ | _ | |a Computing Jacobians with automatic differentiation is ubiquitous in many scientific domains such as machine learning, computational fluid dynamics, robotics, and finance. Even small savings in the number of computations or memory usage in Jacobian computations can already incur massive savings in energy consumption and runtime. While there exist many methods that allow for such savings, they generally trade computational efficiency for approximations of the exact Jacobian. In this paper, we present a novel method to optimize the number of necessary multiplications for Jacobian computation by leveraging deep reinforcement learning (RL) and a concept called cross-country elimination while still computing the exact Jacobian. Cross-country elimination is a framework for automatic differentiation that phrases Jacobian accumulation as ordered elimination of all vertices on the computational graph where every elimination incurs a certain computational cost. We formulate the search for the optimal elimination order that minimizes the number of necessary multiplications as a single player game which is played by an RL agent. We demonstrate that this method achieves up to 33% improvements over state-of-the-art methods on several relevant tasks taken from diverse domains. Furthermore, we show that these theoretical gains translate into actual runtime improvements by providing a cross-country elimination interpreter in JAX that can efficiently execute the obtained elimination orders. |
| 536 | _ | _ | |a 5234 - Emerging NC Architectures (POF4-523) |0 G:(DE-HGF)POF4-5234 |c POF4-523 |f POF IV |x 0 |
| 536 | _ | _ | |a BMBF 16ME0400 - Verbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC II - (16ME0400) |0 G:(BMBF)16ME0400 |c 16ME0400 |x 1 |
| 536 | _ | _ | |a GREENEDGE - Taming the environmental impact of mobile networks through GREEN EDGE computing platforms (953775) |0 G:(EU-Grant)953775 |c 953775 |f H2020-MSCA-ITN-2020 |x 2 |
| 700 | 1 | _ | |a Neftci, Emre |0 P:(DE-Juel1)188273 |b 1 |
| 773 | _ | _ | |y 2024 |0 PERI:(DE-600)1012320-9 |v 38 |x 1049-5258 |
| 856 | 4 | _ | |u https://neurips.cc/virtual/2024/poster/94064 |
| 856 | 4 | _ | |u https://juser.fz-juelich.de/record/1038109/files/AlphaGrad_camera_rdy.pdf |y OpenAccess |
| 909 | C | O | |o oai:juser.fz-juelich.de:1038109 |p openaire |p open_access |p driver |p VDB |p ec_fundedresources |p dnbdelivery |
| 910 | 1 | _ | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 0 |6 P:(DE-Juel1)192147 |
| 910 | 1 | _ | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 1 |6 P:(DE-Juel1)188273 |
| 913 | 1 | _ | |a DE-HGF |b Key Technologies |l Natural, Artificial and Cognitive Information Processing |1 G:(DE-HGF)POF4-520 |0 G:(DE-HGF)POF4-523 |3 G:(DE-HGF)POF4 |2 G:(DE-HGF)POF4-500 |4 G:(DE-HGF)POF |v Neuromorphic Computing and Network Dynamics |9 G:(DE-HGF)POF4-5234 |x 0 |
| 914 | 1 | _ | |y 2024 |
| 915 | _ | _ | |a OpenAccess |0 StatID:(DE-HGF)0510 |2 StatID |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0300 |2 StatID |b Medline |
| 920 | _ | _ | |l yes |
| 920 | 1 | _ | |0 I:(DE-Juel1)PGI-15-20210701 |k PGI-15 |l Neuromorphic Software Eco System |x 0 |
| 980 | _ | _ | |a contrib |
| 980 | _ | _ | |a VDB |
| 980 | _ | _ | |a UNRESTRICTED |
| 980 | _ | _ | |a contb |
| 980 | _ | _ | |a I:(DE-Juel1)PGI-15-20210701 |
| 980 | 1 | _ | |a FullTexts |
| Library | Collection | CLSMajor | CLSMinor | Language | Author |
|---|