AIPLANS (Advances in Programming Languages and Neurosymbolic Systems): a new workshop at NeurIPS 2021 fusing ML with programming theory to create neurosymbolic program-writing machines!
- Paper submission deadline: Oct. 4th, 2021 AoE
- Reviews released: Oct. 23rd, 2021
- Camera-ready deadline: Dec. 1st, 2021 AoE
- Workshop date: Dec. 14th, 2021
Our workshop brings together researchers from various backgrounds. We believe developing neurosymbolic systems will require engineers, designers and theorists from statistical learning and programming language research.
- Machine learning researchers can present advances in meta-learning, reinforcement learning and program synthesis. AIPLANS offers these participants an opportunity to share their research and learn about new automatic programming languages and techniques for inference.
- Programming language designers can give insight into the design and implementation of automatic programming languages and DSLs. AIPLANS offers them the opportunity to gather feedback about design choices, promote the language and engage with their users.
- Programming language theorists can present fundamental theory of mechanical reasoning and automatic programming languages, such as functional, semiring or array programming. AIPLANS will help them bridge the gap between theory and practice, and gain insight into the capabilities and limitations of machine learning technology.
Specifically, AIPLANS seeks to encourage research and highlight recent advances among the following list of topics:
- Neural program synthesis (e.g., search-based, syntax or execution-guided)
- Bayesian program learning (e.g., higher-order probabilistic programming)
- Neural-symbolic reasoning (e.g., automated program verification and testing)
- Neural program extraction (e.g., procedural or relational knowledge distillation)
- Induction of formal languages (e.g., grammar inference, automata extraction)
- Natural language programming (e.g., machine teaching, programming by example)
- New programming languages for logical reasoning (e.g., Prolog, Datalog, miniKanren, HOL, LF/Twelf, L∃∀N, et al.)
- New programming languages for learning (e.g., JAX, Dex, HaskTorch, et al.)
- New programming languages for probability (e.g., Stan, Edward, PyMC3, Pyro, torch-struct)
- Programing language theory (e.g., type theory, category theory, denotational semantics)
- Satisfiability checking and symbolic computation (e.g. SAT/SMT solving, boolean circuits)
- Calculus and equational reasoning (e.g., λ-calculus, π-calculus, tensor and combinator calculi)
- Inference algorithms (e.g., backpropagation, belief propagation, survey propagation et al.)
- Array programming (e.g. TensorNetwork, opt_einsum, Naperian Functors, pointful, et al.)
- Dynamic programming and reinforcement learning (e.g. Semiring programming, probabilistic programming)
Developers of languages, frameworks and libraries, including those who traditionally publish in venues such as SIGPLAN and SIGSOFT are encouraged to share ongoing work that would also be relevant to machine learning community.
AIPLANS is brought to you in collaboration with the organizers of the Differentiable Programming Workshop at NeurIPS 2021. We share their enthusiasm for differentiable and probabilistic programming and see many applications towards program synthesis and symbolic reasoning. Those with similar interests are highly encouraged to participate in both workshops, to be held on consecutive days (Dec. 13th and 14th, 2021).