Meta-Learning an Inference Algorithm for Probabilistic Programs

• URL: http://arxiv.org/abs/2103.00737v1
• Date: Mon, 1 Mar 2021 04:05:11 GMT
• Title: Meta-Learning an Inference Algorithm for Probabilistic Programs
• Authors: Gwonsoo Che and Hongseok Yang
• Abstract summary: We present a meta-algorithm for learning a posterior-inference algorithm for restricted probabilistic programs. Key feature of our approach is the use of a white-box inference algorithm that extracts information directly from model descriptions.
• Score: 13.528656805820459
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a meta-algorithm for learning a posterior-inference algorithm for restricted probabilistic programs. Our meta-algorithm takes a training set of probabilistic programs that describe models with observations, and attempts to learn an efficient method for inferring the posterior of a similar program. A key feature of our approach is the use of what we call a white-box inference algorithm that extracts information directly from model descriptions themselves, given as programs in a probabilistic programming language. Concretely, our white-box inference algorithm is equipped with multiple neural networks, one for each type of atomic command in the language, and computes an approximate posterior of a given probabilistic program by analysing individual atomic commands in the program using these networks. The parameters of these networks are then learnt from a training set by our meta-algorithm. Our empirical evaluation for six model classes shows the promise of our approach.

Related papers

• From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models [63.188607839223046]
  This survey focuses on the benefits of scaling compute during inference. We explore three areas under a unified mathematical formalism: token-level generation algorithms, meta-generation algorithms, and efficient generation.
  arXiv  Detail & Related papers  (2024-06-24T17:45:59Z)
• Front-propagation Algorithm: Explainable AI Technique for Extracting Linear Function Approximations from Neural Networks [0.0]
  This paper introduces the front-propagation algorithm, a novel AI technique designed to elucidate the decision-making logic of deep neural networks. Unlike other popular explainability algorithms such as Integrated Gradients or Shapley Values, the proposed algorithm is able to extract an accurate and consistent linear function explanation of the network. We demonstrate its efficacy in providing accurate linear functions with three different neural network architectures trained on publicly available benchmark datasets.
  arXiv  Detail & Related papers  (2024-05-25T14:50:23Z)
• Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP [81.00800920928621]
  We study representation learning in partially observable Markov Decision Processes (POMDPs) We first present an algorithm for decodable POMDPs that combines maximum likelihood estimation (MLE) and optimism in the face of uncertainty (OFU) We then show how to adapt this algorithm to also work in the broader class of $gamma$-observable POMDPs.
  arXiv  Detail & Related papers  (2023-06-21T16:04:03Z)
• Foundation Posteriors for Approximate Probabilistic Inference [11.64841553345271]
  We formulate inference as masked language modeling in a probabilistic program. We train a neural network to unmask the random values, defining an approximate posterior distribution. We show the efficacy of the approach, zero-shot and fine-tuned, on a benchmark of STAN programs.
  arXiv  Detail & Related papers  (2022-05-19T17:42:37Z)
• Scalable computation of prediction intervals for neural networks via matrix sketching [79.44177623781043]
  Existing algorithms for uncertainty estimation require modifying the model architecture and training procedure. This work proposes a new algorithm that can be applied to a given trained neural network and produces approximate prediction intervals.
  arXiv  Detail & Related papers  (2022-05-06T13:18:31Z)
• 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)
• pRSL: Interpretable Multi-label Stacking by Learning Probabilistic Rules [0.0]
  We present the probabilistic rule stacking (pRSL) which uses probabilistic propositional logic rules and belief propagation to combine the predictions of several underlying classifiers. We derive algorithms for exact and approximate inference and learning, and show that pRSL reaches state-of-the-art performance on various benchmark datasets.
  arXiv  Detail & Related papers  (2021-05-28T14:06:21Z)
• Information Theoretic Meta Learning with Gaussian Processes [74.54485310507336]
  We formulate meta learning using information theoretic concepts; namely, mutual information and the information bottleneck. By making use of variational approximations to the mutual information, we derive a general and tractable framework for meta learning.
  arXiv  Detail & Related papers  (2020-09-07T16:47:30Z)
• 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)
• Learned Factor Graphs for Inference from Stationary Time Sequences [107.63351413549992]
  We propose a framework that combines model-based algorithms and data-driven ML tools for stationary time sequences. neural networks are developed to separately learn specific components of a factor graph describing the distribution of the time sequence. We present an inference algorithm based on learned stationary factor graphs, which learns to implement the sum-product scheme from labeled data.
  arXiv  Detail & Related papers  (2020-06-05T07:06:19Z)
• CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus [62.86856923633923]
  We present a robust estimator for fitting multiple parametric models of the same form to noisy measurements. In contrast to previous works, which resorted to hand-crafted search strategies for multiple model detection, we learn the search strategy from data. For self-supervised learning of the search, we evaluate the proposed algorithm on multi-homography estimation and demonstrate an accuracy that is superior to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-01-08T17:37:01Z)

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.