Searching Latent Program Spaces
- URL: http://arxiv.org/abs/2411.08706v1
- Date: Wed, 13 Nov 2024 15:50:32 GMT
- Title: Searching Latent Program Spaces
- Authors: Clément Bonnet, Matthew V Macfarlane,
- Abstract summary: We propose an algorithm for program induction that learns a distribution over latent programs in a continuous space, enabling efficient search and test-time adaptation.
We show that can generalize beyond its training distribution and adapt to unseen tasks by utilizing test-time adaptation mechanisms.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Program synthesis methods aim to automatically generate programs restricted to a language that can explain a given specification of input-output pairs. While purely symbolic approaches suffer from a combinatorial search space, recent methods leverage neural networks to learn distributions over program structures to narrow this search space significantly, enabling more efficient search. However, for challenging problems, it remains difficult to train models to perform program synthesis in one shot, making test-time search essential. Most neural methods lack structured search mechanisms during inference, relying instead on stochastic sampling or gradient updates, which can be inefficient. In this work, we propose the Latent Program Network (LPN), a general algorithm for program induction that learns a distribution over latent programs in a continuous space, enabling efficient search and test-time adaptation. We explore how to train these networks to optimize for test-time computation and demonstrate the use of gradient-based search both during training and at test time. We evaluate LPN on ARC-AGI, a program synthesis benchmark that evaluates performance by generalizing programs to new inputs rather than explaining the underlying specification. We show that LPN can generalize beyond its training distribution and adapt to unseen tasks by utilizing test-time computation, outperforming algorithms without test-time adaptation mechanisms.
Related papers
- LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
arXiv Detail & Related papers (2025-02-19T14:58:48Z) - Learning Semantics-aware Search Operators for Genetic Programming [0.20718016474717196]
Fitness landscapes in test-based program synthesis are known to be extremely rugged.
We propose a semantics-aware search operator that steers the search towards candidate programs that are valuable.
arXiv Detail & Related papers (2025-02-06T23:46:04Z) - ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks [0.0]
We present ExpTest, a sophisticated method for initial learning rate searching and subsequent learning rate tuning.
We mathematically justify ExpTest and provide empirical support.
arXiv Detail & Related papers (2024-11-25T22:58:22Z) - Using deep learning to construct stochastic local search SAT solvers
with performance bounds [0.0]
We train oracles using Graph Neural Networks and evaluate them on two SLS solvers on random SAT instances of varying difficulty.
We find that access to GNN-based oracles significantly boosts the performance of both solvers.
arXiv Detail & Related papers (2023-09-20T16:27:52Z) - Using Machine Learning To Identify Software Weaknesses From Software
Requirement Specifications [49.1574468325115]
This research focuses on finding an efficient machine learning algorithm to identify software weaknesses from requirement specifications.
Keywords extracted using latent semantic analysis help map the CWE categories to PROMISE_exp. Naive Bayes, support vector machine (SVM), decision trees, neural network, and convolutional neural network (CNN) algorithms were tested.
arXiv Detail & Related papers (2023-08-10T13:19:10Z) - Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency.
We present an IPU-optimized release of our custom SNN Python package, snnTorch.
arXiv Detail & Related papers (2022-11-19T15:44:08Z) - CrossBeam: Learning to Search in Bottom-Up Program Synthesis [51.37514793318815]
We propose training a neural model to learn a hands-on search policy for bottom-up synthesis.
Our approach, called CrossBeam, uses the neural model to choose how to combine previously-explored programs into new programs.
We observe that CrossBeam learns to search efficiently, exploring much smaller portions of the program space compared to the state-of-the-art.
arXiv Detail & Related papers (2022-03-20T04:41:05Z) - Scaling Neural Program Synthesis with Distribution-based Search [7.137293485620867]
We introduce two new search algorithms: Heap Search and SQRT Sampling.
We show how they integrate with probabilistic and neural techniques, and demonstrate how they can operate at scale across parallel compute environments.
arXiv Detail & Related papers (2021-10-24T16:46:01Z) - Searching for More Efficient Dynamic Programs [61.79535031840558]
We describe a set of program transformations, a simple metric for assessing the efficiency of a transformed program, and a search procedure to improve this metric.
We show that in practice, automated search can find substantial improvements to the initial program.
arXiv Detail & Related papers (2021-09-14T20:52:55Z) - Efficient Nearest Neighbor Language Models [114.40866461741795]
Non-parametric neural language models (NLMs) learn predictive distributions of text utilizing an external datastore.
We show how to achieve up to a 6x speed-up in inference speed while retaining comparable performance.
arXiv Detail & Related papers (2021-09-09T12:32:28Z) - Waypoint Planning Networks [66.72790309889432]
We propose a hybrid algorithm based on LSTMs with a local kernel - a classic algorithm such as A*, and a global kernel using a learned algorithm.
We compare WPN against A*, as well as related works including motion planning networks (MPNet) and value networks (VIN)
It is shown that WPN's search space is considerably less than A*, while being able to generate near optimal results.
arXiv Detail & Related papers (2021-05-01T18:02:01Z) - Towards Optimally Efficient Tree Search with Deep Learning [76.64632985696237]
This paper investigates the classical integer least-squares problem which estimates signals integer from linear models.
The problem is NP-hard and often arises in diverse applications such as signal processing, bioinformatics, communications and machine learning.
We propose a general hyper-accelerated tree search (HATS) algorithm by employing a deep neural network to estimate the optimal estimation for the underlying simplified memory-bounded A* algorithm.
arXiv Detail & Related papers (2021-01-07T08:00:02Z) - BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided Exploration [72.88493072196094]
We present a new synthesis approach that leverages learning to guide a bottom-up search over programs.
In particular, we train a model to prioritize compositions of intermediate values during search conditioned on a set of input-output examples.
We show that the combination of learning and bottom-up search is remarkably effective, even with simple supervised learning approaches.
arXiv Detail & Related papers (2020-07-28T17:46:18Z) - Learning Differentiable Programs with Admissible Neural Heuristics [43.54820901841979]
We study the problem of learning differentiable functions expressed as programs in a domain-specific language.
We frame this optimization problem as a search in a weighted graph whose paths encode top-down derivations of program syntax.
Our key innovation is to view various classes of neural networks as continuous relaxations over the space of programs.
arXiv Detail & Related papers (2020-07-23T16:07:39Z) - CATCH: Context-based Meta Reinforcement Learning for Transferrable
Architecture Search [102.67142711824748]
CATCH is a novel Context-bAsed meTa reinforcement learning algorithm for transferrable arChitecture searcH.
The combination of meta-learning and RL allows CATCH to efficiently adapt to new tasks while being agnostic to search spaces.
It is also capable of handling cross-domain architecture search as competitive networks on ImageNet, COCO, and Cityscapes are identified.
arXiv Detail & Related papers (2020-07-18T09:35:53Z) - Strong Generalization and Efficiency in Neural Programs [69.18742158883869]
We study the problem of learning efficient algorithms that strongly generalize in the framework of neural program induction.
By carefully designing the input / output interfaces of the neural model and through imitation, we are able to learn models that produce correct results for arbitrary input sizes.
arXiv Detail & Related papers (2020-07-07T17:03:02Z) - Gradient-only line searches to automatically determine learning rates
for a variety of stochastic training algorithms [0.0]
We study the application of the Gradient-Only Line Search that is Inexact (GOLS-I) to determine the learning rate schedule for a selection of popular neural network training algorithms.
GOLS-I's learning rate schedules are competitive with manually tuned learning rates, over seven optimization algorithms, three types of neural network architecture, 23 datasets and two loss functions.
arXiv Detail & Related papers (2020-06-29T08:59:31Z) - AdaS: Adaptive Scheduling of Stochastic Gradients [50.80697760166045]
We introduce the notions of textit"knowledge gain" and textit"mapping condition" and propose a new algorithm called Adaptive Scheduling (AdaS)
Experimentation reveals that, using the derived metrics, AdaS exhibits: (a) faster convergence and superior generalization over existing adaptive learning methods; and (b) lack of dependence on a validation set to determine when to stop training.
arXiv Detail & Related papers (2020-06-11T16:36:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.