M
Martin Rinard
Researcher at Massachusetts Institute of Technology
Publications - 381
Citations - 19269
Martin Rinard is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Data structure & Compiler. The author has an hindex of 70, co-authored 372 publications receiving 18126 citations. Previous affiliations of Martin Rinard include University of California, Santa Barbara & Stanford University.
Papers
More filters
Posted Content
Neurosymbolic Transformers for Multi-Agent Communication
Jeevana Priya Inala,Yichen Yang,James Paulos,Yewen Pu,Osbert Bastani,Vijay Kumar,Martin Rinard,Armando Solar-Lezama +7 more
Abstract: We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication. We quantify the amount of communication as the maximum degree of the communication graph; this metric captures settings where agents have limited bandwidth. Minimizing communication is challenging due to the combinatorial nature of both the decision space and the objective; for instance, we cannot solve this problem by training neural networks using gradient descent. We propose a novel algorithm that synthesizes a control policy that combines a programmatic communication policy used to generate the communication graph with a transformer policy network used to choose actions. Our algorithm first trains the transformer policy, which implicitly generates a "soft" communication graph; then, it synthesizes a programmatic communication policy that "hardens" this graph, forming a neurosymbolic transformer. Our experiments demonstrate how our approach can synthesize policies that generate low-degree communication graphs while maintaining near-optimal performance.
Posted Content
Exact Symbolic Inference in Probabilistic Programs via Sum-Product Representations.
TL;DR: This work formalizes SPPL in terms of a novel translation strategy from probabilistic programs to a semantic domain of sum-product representations, and presents new algorithms for exactly conditioning on and computing probabilities of queries, and proves their soundness under the semantics.
Journal ArticleDOI
Emergence of Locally Suboptimal Behavior in Finitely Repeated Games
Yichen Yang,Martin Rinard +1 more
TL;DR: In this paper , the authors studied the emergence of locally suboptimal behavior in finitely repeated games with complete information and proved sufficient and necessary conditions on the stage game G that ensures that, for all T and all subgame-perfect equilibria of the repeated game G(T), the strategy profile at every round of G (T) forms a Nash equilibrium.
OSUIF: SUIF 2.0 With Objects
Andrew Duncan,Bogdan Cocosel,Costin Iancu,Holger Kienle,Radu Rugina,Urs Hölzle,Martin Rinard +6 more
TL;DR: OSUIF is an extension to SUIF 2.0 that provides support for the compilation of object-oriented languages and extends standard SUIF in three main areas: symbol table, intermediate language, and exception handling.
Patent
System, method, and apparatus for reducing power dissipation of sensor data for bit-serial communication
TL;DR: In this paper, a communication system receives a binary sequence from a sensor, identifies a power consuming characteristic of the binary sequence, and determines an error component configured to reduce the power consuming characteristics of binary sequence.