Workshop
Advances in Programming Languages and Neurosymbolic Systems (AIPLANS)
Breandan Considine · Disha Shrivastava · David Yu-Tung Hui · Chin-Wei Huang · Shawn Tan · Xujie Si · Prakash Panangaden · Guy Van den Broeck · Daniel Tarlow
Tue 14 Dec, 3:45 a.m. PST
Neural information processing systems have benefited tremendously from the availability of programming languages and frameworks for automatic differentiation (AD). Not only do NeurIPS benefit from programming languages for automatic inference but can also be considered as a language in their own right, consisting of differentiable and stochastic primitives. Combined with neural language models, these systems are increasingly capable of generating symbolic programs a human programmer might write in a high-level language. Developing neurosymbolic systems for automatic program synthesis requires insights from both statistical learning and programming languages.
AIPLANS invites all researchers working towards the same purpose in these two communities to build on common ground. Our workshop is designed to be as inclusive as possible towards researchers engaged in building programming languages and neurosymbolic systems.
Schedule
Tue 3:45 a.m. - 4:00 a.m.
|
Introductory remarks
(
Introductory Remarks
)
>
SlidesLive Video |
Breandan Considine 🔗 |
Tue 4:00 a.m. - 4:45 a.m.
|
Thinking like Transformers - Gail Weiss - Technion - Israel Institute of Technology
(
Invited Talk
)
>
SlidesLive Video |
Gail Weiss 🔗 |
Tue 4:45 a.m. - 4:55 a.m.
|
Q&A - Gail Weiss
(
Post Talk Q & A
)
>
|
🔗 |
Tue 5:00 a.m. - 6:00 a.m.
|
When Gödel discovered Automatic Differentiation - Marie Kerjean - Centre national de la recherche scientifique
(
Invited Talk
)
>
SlidesLive Video |
AIPLANS 2021 🔗 |
Tue 6:00 a.m. - 7:00 a.m.
|
Building machines that learn and think like people by learning to write programs: progress, open problems, and next steps - Josh Tenenbaum - Massachusetts Institute of Technology
(
Invited Talk
)
>
SlidesLive Video |
Josh Tenenbaum 🔗 |
Tue 7:00 a.m. - 7:15 a.m.
|
Short break
|
🔗 |
Tue 7:15 a.m. - 8:15 a.m.
|
Panel Discussion
(
Panel Discussion
)
>
SlidesLive Video |
🔗 |
Tue 8:15 a.m. - 8:55 a.m.
|
Daniel Selsam Microsoft Research
(
Tutorial
)
>
SlidesLive Video |
Daniel Selsam 🔗 |
Tue 8:55 a.m. - 9:05 a.m.
|
Q&A - Daniel Selsam
(
Post Talk Q & A
)
>
|
🔗 |
Tue 9:00 a.m. - 10:15 a.m.
|
Lunch / Poster Session ( Poster Session ) > link | 🔗 |
Tue 10:15 a.m. - 10:20 a.m.
|
Remarks from Organisers
(
Introduction
)
>
|
🔗 |
Tue 10:20 a.m. - 10:46 a.m.
|
Randomized Automatic Differentiation - Ryan Adams - Princeton University
(
Invited Talk
)
>
SlidesLive Video |
Ryan Adams 🔗 |
Tue 10:46 a.m. - 10:56 a.m.
|
Q&A - Ryan Adams
(
Post Talk Q & A
)
>
|
🔗 |
Tue 11:00 a.m. - 11:45 a.m.
|
Dependent Types for Machine Learning in Dex - David Duvenaud - University of Toronto
(
Invited Talk
)
>
SlidesLive Video |
David Duvenaud · AIPLANS 2021 🔗 |
Tue 11:45 a.m. - 11:55 a.m.
|
Q&A - David Duvenaud
(
Post Talk Q & A
)
>
|
🔗 |
Tue 12:00 p.m. - 12:45 p.m.
|
Differential Inference: A Criminally Underused Tool. - Alexander Rush - Cornell University
(
Invited Talk
)
>
SlidesLive Video |
Alexander Rush 🔗 |
Tue 12:45 p.m. - 12:55 p.m.
|
Q&A - Alexander Rush
(
Post Talk Q & A
)
>
|
🔗 |
Tue 1:00 p.m. - 1:05 p.m.
|
Introduction to Spotlight Speakers
(
Organiser Remarks
)
>
|
🔗 |
Tue 1:05 p.m. - 1:15 p.m.
|
Meta-Learning an Inference Algorithm for Probabilistic Programs - Gwonsoo Che
(
Spotlight Talks
)
>
SlidesLive Video |
AIPLANS 2021 · Gwonsoo Che 🔗 |
Tue 1:15 p.m. - 1:22 p.m.
|
LazyPPL: laziness and types in non-parametric probabilistic programs - Hugo Paquet
(
Spotlight Talk
)
>
SlidesLive Video |
AIPLANS 2021 · Hugo Paquet 🔗 |
Tue 1:22 p.m. - 1:32 p.m.
|
Learning Rules with Stratified Negation in Differentiable ILP - Giri Krishnan
(
Spotlight Talks
)
>
SlidesLive Video |
AIPLANS 2021 · Giri Krishnan 🔗 |
Tue 1:32 p.m. - 1:41 p.m.
|
Learning Adaptive Control Flow in Transformers for Improved Systematic Generalization - Róbert Csordás
(
Spotlight Talk
)
>
SlidesLive Video |
AIPLANS 2021 · Róbert Csordás 🔗 |
Tue 1:41 p.m. - 1:51 p.m.
|
Type Inference as Optimization - Eirene V. Pandi
(
Spotlight Talk
)
>
SlidesLive Video |
AIPLANS 2021 · Eirini V. Pandi 🔗 |
Tue 1:51 p.m. - 2:00 p.m.
|
Q&A for Spotlight Authors
(
Q & A
)
>
|
🔗 |
Tue 2:00 p.m. - 2:15 p.m.
|
Closing Remarks
(
Closing remarks
)
>
SlidesLive Video |
Breandan Considine 🔗 |
Tue 2:15 p.m. - 3:00 p.m.
|
Poster Session ( Poster Session ) > link | AIPLANS 2021 🔗 |
-
|
Type Inference as Optimization ( Poster ) > link | Eirini V. Pandi · Earl Barr · Andrew Gordon · Charles Sutton 🔗 |
-
|
Are Transformers All That Karel Needs? ( Poster ) > link | Abhay Garg · Anand Sriraman · Shirish Karande 🔗 |
-
|
Towards Neural Functional Program Evaluation ( Poster ) > link | Torsten Scholak · Jonathan Pilault 🔗 |
-
|
Staged compilation of tensor expressions ( Poster ) > link | Marco Zocca 🔗 |
-
|
Safe Neurosymbolic Learning with Differentiable Symbolic Execution ( Poster ) > link | Chenxi Yang · Swarat Chaudhuri 🔗 |
-
|
AutoCoder: Leveraging Transformers for Automatic Code Synthesis ( Poster ) > link | Mrinal Anand · Mayank Singh 🔗 |
-
|
Learning Rules with Stratified Negation in Differentiable ILP. ( Poster ) > link | Giri Krishnan · Ramyaa Ramyaa 🔗 |
-
|
AutumnSynth: Synthesis of Reactive Programs with Structured Latent State ( Poster ) > link | Ria Das · Zenna Tavares · Josh Tenenbaum · Armando Solar-Lezama 🔗 |
-
|
PAC Synthesis of Machine Learning Programs ( Poster ) > link | Osbert Bastani 🔗 |
-
|
Learning compositional programs with arguments and sampling ( Poster ) > link | Giovanni De Toni · Andrea Passerini 🔗 |
-
|
Learning Adaptive Control Flow in Transformers for Improved Systematic Generalization ( Poster ) > link | Róbert Csordás · Kazuki Irie · Jürgen Schmidhuber 🔗 |
-
|
Adversarial Robustness of Program Synthesis Models ( Poster ) > link | Mrinal Anand · Mayank Singh 🔗 |
-
|
Learning C to x86 Translation: An Experiment in Neural Compilation ( Poster ) > link | Jordi Armengol-Estapé · Michael O'Boyle 🔗 |
-
|
Synthesizing Video Trajectory Queries ( Poster ) > link | Stephen Mell · Favyen Bastani · Stephan Zdancewic · Osbert Bastani 🔗 |
-
|
Augmenting Classic Algorithms with Neural Components for Strong Generalisation on Ambiguous and High-Dimensional Data ( Poster ) > link | Imanol Schlag · Jürgen Schmidhuber 🔗 |
-
|
Meta-Learning an Inference Algorithm for Probabilistic Programs ( Poster ) > link | Gwonsoo Che · Hongseok Yang 🔗 |
-
|
Scallop: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning ( Poster ) > link | Jiani Huang · Ziyang Li · Binghong Chen · Karan Samel · Mayur Naik · Le Song · Xujie Si 🔗 |
-
|
LazyPPL: laziness and types in non-parametric probabilistic programs ( Poster ) > link | Hugo Paquet · Sam Staton 🔗 |
-
|
Proof Extraction for Logical Neural Networks ( Poster ) > link | Thabang Lebese · Ndivhuwo Makondo · Cristina Cornelio · Naweed A Khan 🔗 |
-
|
A Genetic Programming Approach To Zero-Shot Neural Architecture Ranking ( Poster ) > link | Yash Akhauri · Juan Munoz · Ravishankar Iyer · Nilesh Jain 🔗 |