Papers Program Synthesis
“Program Synthesis” 태그가 달린 논문 538편 · 필터 해제
Generating Programmatic Referring Expressions via Program Synthesis
Incorporating symbolic reasoning into machine learning algorithms is a promising approach to improve performance on learning tasks that require logical reasoning. We study the problem of generating a programmatic variant…
Enumerative SearchLogical ReasoningProgram SynthesisTowards Neural-Guided Program Synthesis for Linear Temporal Logic Specifications
Synthesizing a program that realizes a logical specification is a classical problem in computer science. We examine a particular type of program synthesis, where the objective is to synthesize a strategy that reacts to a…
Program SynthesisAdaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation
Sequence generation models are commonly refined with reinforcement learning over user-defined metrics. However, high gradient variance hinders the practical use of this method. To stabilize this method, we adapt to conte…
Image CaptioningProgram SynthesisReinforcement LearningSynthetic Datasets for Neural Program Synthesis
The goal of program synthesis is to automatically generate programs in a particular language from corresponding specifications, e.g. input-output behavior. Many current approaches achieve impressive results after trainin…
Program SynthesisNovel positional encodings to enable tree-based transformers
Neural models optimized for tree-based problems are of great value in tasks like SQL query extraction and program synthesis. On sequence-structured data, transformers have been shown to learn relationships across arbitra…
Program SynthesisSemantic ParsingTranslationDeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement Learning
This paper proposes DeepSynth, a method for effective training of deep Reinforcement Learning (RL) agents when the reward is sparse and non-Markovian, but at the same time progress towards the reward requires achieving a…
Deep Reinforcement LearningHierarchical Reinforcement LearningMontezuma's RevengeProbabilistic Deep Learning+4Program synthesis performance constrained by non-linear spatial relations in Synthetic Visual Reasoning Test
Despite remarkable advances in automated visual recognition by machines, some visual tasks remain challenging for machines. Fleuret et al. (2011) introduced the Synthetic Visual Reasoning Test (SVRT) to highlight this po…
Few-Shot LearningProgram SynthesisUnsupervised Few-Shot LearningVisual ReasoningConstraint-based Learning of Phonological Processes
Phonological processes are context-dependent sound changes in natural languages. We present an unsupervised approach to learning human-readable descriptions of phonological processes from collections of related utterance…
Program SynthesisBayesian causal inference via probabilistic program synthesis
Causal inference can be formalized as Bayesian inference that combines a prior distribution over causal models and likelihoods that account for both observations and interventions. We show that it is possible to implemen…
Bayesian InferenceCausal InferenceProbabilistic ProgrammingProgram SynthesisProbabilistic Surrogate Networks for Simulators with Unbounded Randomness
We present a framework for automatically structuring and training fast, approximate, deep neural surrogates of stochastic simulators. Unlike traditional approaches to surrogate modeling, our surrogates retain the interpr…
Probabilistic ProgrammingProgram SynthesisNeural Program Synthesis By Self-Learning
Neural inductive program synthesis is a task generating instructions that can produce desired outputs from given inputs. In this paper, we focus on the generation of a chunk of assembly code that can be executed to match…
CPUProgram SynthesisReinforcement LearningReinforcement Learning (RL)+1Mapping Natural-language Problems to Formal-language Solutions Using Structured Neural Representations
Generating formal-language programs represented by relational tuples, such as Lisp programs or mathematical operations, to solve problems stated in natural language is a challenging task because it requires explicitly ca…
DecoderProgram SynthesisText GenerationMaking sense of sensory input
This paper attempts to answer a central question in unsupervised learning: what does it mean to "make sense" of a sensory sequence? In our formalization, making sense involves constructing a symbolic causal theory that b…
Inductive BiasProgram SynthesisUnitySynthesizing Action Sequences for Modifying Model Decisions
When a model makes a consequential decision, e.g., denying someone a loan, it needs to additionally generate actionable, realistic feedback on what the person can do to favorably change the decision. We cast this problem…
modelProgram SynthesisOptimal Sizing of Stand-alone Solar PV Systems via Automated Formal Synthesis
There exist various methods and tools to size solar photovoltaic systems; however, these tools rely on simulations, which do not cover all aspects of the design space during the search for optimal solution. In prior stud…
Program SynthesisNatural- to formal-language generation using Tensor Product Representations
Generating formal-language represented by relational tuples, such as Lisp programs or mathematical expressions, from a natural-language input is an extremely challenging task because it requires to explicitly capture dis…
DecoderMathProgram SynthesisText GenerationIterative Target Augmentation for Effective Conditional Generation
Many challenging prediction problems, from molecular optimization to program synthesis, involve creating complex structured objects as outputs. However, available training data may not be sufficient for a generative mode…
Program SynthesisADAPTIVE GENERATION OF PROGRAMMING PUZZLES
AI today is far from being able to write complex programs. What type of problems would be best for computers to learn to program, and how should such problems be generated? To answer the first question, we suggest progra…
Program SynthesisLearning Fitness Functions for Machine Programming
The problem of automatic software generation is known as Machine Programming. In this work, we propose a framework based on genetic algorithms to solve this problem. Although genetic algorithms have been used successfull…
Program SynthesisImitation-Projected Programmatic Reinforcement Learning
We study the problem of programmatic reinforcement learning, in which policies are represented as short programs in a symbolic language. Programmatic policies can be more interpretable, generalizable, and amenable to for…
continuous-controlContinuous ControlImitation LearningProgram Synthesis+3