DNCs Require More Planning Steps

• URL: http://arxiv.org/abs/2406.02187v1
• Date: Tue, 4 Jun 2024 10:31:03 GMT
• Title: DNCs Require More Planning Steps
• Authors: Yara Shamshoum, Nitzan Hodos, Yuval Sieradzki, Assaf Schuster,
• Abstract summary: We investigate the effect of computational time and memory on generalization of implicit algorithmic solvers. We show how the planning budget can drastically change the behavior of the learned algorithm.
• Score: 7.837209773889032
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many recent works use machine learning models to solve various complex algorithmic problems. However, these models attempt to reach a solution without considering the problem's required computational complexity, which can be detrimental to their ability to solve it correctly. In this work we investigate the effect of computational time and memory on generalization of implicit algorithmic solvers. To do so, we focus on the Differentiable Neural Computer (DNC), a general problem solver that also lets us reason directly about its usage of time and memory. In this work, we argue that the number of planning steps the model is allowed to take, which we call "planning budget", is a constraint that can cause the model to generalize poorly and hurt its ability to fully utilize its external memory. We evaluate our method on Graph Shortest Path, Convex Hull, Graph MinCut and Associative Recall, and show how the planning budget can drastically change the behavior of the learned algorithm, in terms of learned time complexity, training time, stability and generalization to inputs larger than those seen during training.

Related papers

• Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs [76.43407125275202]
  o1-like models can emulate human-like long-time thinking during inference. This paper presents the first comprehensive study on the prevalent issue of overthinking in these models. We propose strategies to mitigate overthinking, streamlining reasoning processes without compromising accuracy.
  arXiv  Detail & Related papers  (2024-12-30T18:55:12Z)
• Learning to Optimize for Mixed-Integer Non-linear Programming [20.469394148261838]
  Mixed-integer non-NLP programs (MINLPs) arise in various domains, such as energy systems and transportation, but are notoriously difficult to solve. Recent advances in machine learning have led to remarkable successes in optimization, area broadly known as learning to optimize. We propose two differentiable correction layers that generate integer outputs while preserving gradient.
  arXiv  Detail & Related papers  (2024-10-14T20:14:39Z)
• A General Framework for Learning from Weak Supervision [93.89870459388185]
  This paper introduces a general framework for learning from weak supervision (GLWS) with a novel algorithm. Central to GLWS is an Expectation-Maximization (EM) formulation, adeptly accommodating various weak supervision sources. We also present an advanced algorithm that significantly simplifies the EM computational demands.
  arXiv  Detail & Related papers  (2024-02-02T21:48:50Z)
• Learning to Configure Mathematical Programming Solvers by Mathematical Programming [0.8075866265341176]
  We discuss the issue of finding a good mathematical programming solver configuration for a particular instance of a given problem. A specific difficulty of learning a good solver configuration is that parameter settings may not all be independent. We tackle this issue in the second phase of our approach, where we use the learnt information to construct and solve an optimization problem.
  arXiv  Detail & Related papers  (2024-01-10T10:02:01Z)
• Taking the human out of decomposition-based optimization via artificial intelligence: Part II. Learning to initialize [0.0]
  The proposed approach can lead to a significant reduction in solution time. Active and supervised learning is used to learn a surrogate model that predicts the computational performance. The results show that the proposed approach can lead to a significant reduction in solution time.
  arXiv  Detail & Related papers  (2023-10-10T23:49:26Z)
• Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning [70.65666982566655]
  Permutation flow shop scheduling (PFSS) is widely used in manufacturing systems. We propose to train the model via expert-driven imitation learning, which accelerates convergence more stably and accurately. Our model's network parameters are reduced to only 37% of theirs, and the solution gap of our model towards the expert solutions decreases from 6.8% to 1.3% on average.
  arXiv  Detail & Related papers  (2022-10-31T09:46:26Z)
• Learning Iterative Reasoning through Energy Minimization [77.33859525900334]
  We present a new framework for iterative reasoning with neural networks. We train a neural network to parameterize an energy landscape over all outputs. We implement each step of the iterative reasoning as an energy minimization step to find a minimal energy solution.
  arXiv  Detail & Related papers  (2022-06-30T17:44:20Z)
• End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking [52.05847268235338]
  We show how machine learning systems can perform logical extrapolation without overthinking problems. We propose a recall architecture that keeps an explicit copy of the problem instance in memory so that it cannot be forgotten. We also employ a progressive training routine that prevents the model from learning behaviors that are specific to number and instead pushes it to learn behaviors that can be repeated indefinitely.
  arXiv  Detail & Related papers  (2022-02-11T18:43:28Z)
• CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints [20.659237363210774]
  We aim to integrate integer programming solvers into neural network architectures as layers capable of learning both the cost terms and the constraints. The resulting end-to-end trainable architectures jointly extract features from raw data and solve a suitable (learned) problem with state-of-the-art integer programming solvers.
  arXiv  Detail & Related papers  (2021-05-05T21:52:53Z)
• Learning to Sparsify Travelling Salesman Problem Instances [0.5985204759362747]
  We use a pruning machine learning as a pre-processing step followed by an exact Programming approach to sparsify the travelling salesman problem. Our learning approach requires very little training data and is amenable to mathematical analysis.
  arXiv  Detail & Related papers  (2021-04-19T14:35:14Z)
• SOLO: Search Online, Learn Offline for Combinatorial Optimization Problems [4.777801093677586]
  We study problems with real world applications such as machine scheduling, routing, and assignment. We propose a method that combines Reinforcement Learning (RL) and planning. This method can equally be applied to both the offline, as well as online, variants of the problem, in which the problem components are not known in advance, but rather arrive during the decision-making process.
  arXiv  Detail & Related papers  (2021-04-04T17:12:24Z)
• Sufficiently Accurate Model Learning for Planning [119.80502738709937]
  This paper introduces the constrained Sufficiently Accurate model learning approach. It provides examples of such problems, and presents a theorem on how close some approximate solutions can be. The approximate solution quality will depend on the function parameterization, loss and constraint function smoothness, and the number of samples in model learning.
  arXiv  Detail & Related papers  (2021-02-11T16:27:31Z)
• 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)

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.