Learning Approximate Distribution-Sensitive Data Structures

We model representations as data-structures which are distribution sensitive, i.e., which exploit regularities in their usage patterns to reduce time or space complexity. We introduce probabilistic axiomatic specifications to extend abstract data structures which specify a class of representations with equivalent logical behavior to a distribution-sensitive data structures. We reformulate synthesis of distribution-sensitive data structures as a continuous function approximation problem, such that the functions of a data-structure deep neural networks, such as a stack, queue, natural number, set, and binary tree.

[1]  Nell Dale,et al.  Abstract data types: Specifications, implementations, and applications , 1996 .

[2]  C. Lee Giles,et al.  The Neural Network Pushdown Automaton: Model, Stack and Learning Simulations , 2017, ArXiv.

[3]  Sumit Gulwani,et al.  Static analysis for probabilistic programs: inferring whole program properties from finitely many paths , 2013, PLDI.

[4]  Jason Weston,et al.  End-To-End Memory Networks , 2015, NIPS.

[5]  Klaus Willmes,et al.  On the Magnitude Representations of Two-Digit Numbers , 2005 .

[6]  Ellis Horowitz,et al.  Abstract data types and software validation , 1978, CACM.

[7]  Ben Wegbreit,et al.  The verification and synthesis of data structures , 2004, Acta Informatica.

[8]  Dan Grossman,et al.  Expressing and verifying probabilistic assertions , 2014, PLDI.

[9]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[10]  Pierre Pica,et al.  Geometry as a Universal mental Construction , 2011 .

[11]  Daniel C. Hyde,et al.  Human Neuroscience Hypothesis and Theory Article Two Systems of Non-symbolic Numerical Cognition , 2022 .

[12]  David Poole,et al.  First-order probabilistic inference , 2003, IJCAI.

[13]  Armando Solar-Lezama,et al.  Program synthesis from polymorphic refinement types , 2015, PLDI.

[14]  Armando Solar-Lezama,et al.  The Sketching Approach to Program Synthesis , 2009, APLAS.

[15]  Phil Blunsom,et al.  Learning to Transduce with Unbounded Memory , 2015, NIPS.

[16]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[17]  Ernest Lepore,et al.  The compositionality papers , 2002 .

[18]  Alejandro López-Ortiz,et al.  Space-Efficient Data Structures, Streams, and Algorithms , 2013 .

[19]  Xin Zhang,et al.  End to End Learning for Self-Driving Cars , 2016, ArXiv.

[20]  J. Loeckx,et al.  Algebraic specification of abstract data types , 2001, Logic in Computer Science.