Guided Evolution with Binary Discriminators for ML Program Search

• URL: http://arxiv.org/abs/2402.05821v1
• Date: Thu, 8 Feb 2024 16:59:24 GMT
• Title: Guided Evolution with Binary Discriminators for ML Program Search
• Authors: John D. Co-Reyes, Yingjie Miao, George Tucker, Aleksandra Faust, Esteban Real
• Abstract summary: We propose guiding evolution with a binary discriminator, trained online to distinguish which program is better given a pair of programs. We demonstrate our method can speed up evolution across a set of diverse problems including a 3.7x speedup on the symbolic search for MLs and a 4x speedup for RL loss functions.
• Score: 64.44893463120584
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: How to automatically design better machine learning programs is an open problem within AutoML. While evolution has been a popular tool to search for better ML programs, using learning itself to guide the search has been less successful and less understood on harder problems but has the promise to dramatically increase the speed and final performance of the optimization process. We propose guiding evolution with a binary discriminator, trained online to distinguish which program is better given a pair of programs. The discriminator selects better programs without having to perform a costly evaluation and thus speed up the convergence of evolution. Our method can encode a wide variety of ML components including symbolic optimizers, neural architectures, RL loss functions, and symbolic regression equations with the same directed acyclic graph representation. By combining this representation with modern GNNs and an adaptive mutation strategy, we demonstrate our method can speed up evolution across a set of diverse problems including a 3.7x speedup on the symbolic search for ML optimizers and a 4x speedup for RL loss functions.

Related papers

• Evolution Transformer: In-Context Evolutionary Optimization [6.873777465945062]
  We introduce Evolution Transformer, a causal Transformer architecture, which can flexibly characterize a family of Evolution Strategies. We train the model weights using Evolutionary Algorithm Distillation, a technique for supervised optimization of sequence models. We analyze the resulting properties of the Evolution Transformer and propose a technique to fully self-referentially train the Evolution Transformer.
  arXiv  Detail & Related papers  (2024-03-05T14:04:13Z)
• Graph Neural Network Autoencoders for Efficient Quantum Circuit Optimisation [69.43216268165402]
  We present for the first time how to use graph neural network (GNN) autoencoders for the optimisation of quantum circuits. We construct directed acyclic graphs from the quantum circuits, encode the graphs and use the encodings to represent RL states. Our method is the first realistic first step towards very large scale RL quantum circuit optimisation.
  arXiv  Detail & Related papers  (2023-03-06T16:51:30Z)
• evosax: JAX-based Evolution Strategies [0.0]
  We release evosax: a JAX-based library of evolutionary optimization algorithms. evosax implements 30 evolutionary optimization algorithms including finite-difference-based, estimation-of-distribution evolution strategies and various genetic algorithms. It is designed in a modular fashion and allows for flexible usage via a simple ask-evaluate-tell API.
  arXiv  Detail & Related papers  (2022-12-08T10:34:42Z)
• VeLO: Training Versatile Learned Optimizers by Scaling Up [67.90237498659397]
  We leverage the same scaling approach behind the success of deep learning to learn versatiles. We train an ingest for deep learning which is itself a small neural network that ingests and outputs parameter updates. We open source our learned, meta-training code, the associated train test data, and an extensive benchmark suite with baselines at velo-code.io.
  arXiv  Detail & Related papers  (2022-11-17T18:39:07Z)
• 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 to Optimize Quasi-Newton Methods [22.504971951262004]
  This paper introduces a novel machine learning called LODO, which tries to online meta-learn the best preconditioner during optimization. Unlike other L2O methods, LODO does not require any meta-training on a training task distribution. We show that our gradient approximates the inverse Hessian in noisy loss landscapes and is capable of representing a wide range of inverse Hessians.
  arXiv  Detail & Related papers  (2022-10-11T03:47:14Z)
• Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories [72.15369769265398]
  Machine learning has emerged as a promising paradigm for branching. We propose retro branching; a simple yet effective approach to RL for branching. We outperform the current state-of-the-art RL branching algorithm by 3-5x and come within 20% of the best IL method's performance on MILPs with 500 constraints and 1000 variables.
  arXiv  Detail & Related papers  (2022-05-28T06:08:07Z)
• Learning to Optimize: A Primer and A Benchmark [94.29436694770953]
  Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods. This article is poised to be the first comprehensive survey and benchmark of L2O for continuous optimization.
  arXiv  Detail & Related papers  (2021-03-23T20:46:20Z)
• Transferable Graph Optimizers for ML Compilers [18.353830282858834]
  We propose an end-to-end, transferable deep reinforcement learning method for computational graph optimization (GO) GO generates decisions on the entire graph rather than on each individual node autoregressively, drastically speeding up the search compared to prior methods. GO achieves 21% improvement over human experts and 18% improvement over the prior state of the art with 15x faster convergence.
  arXiv  Detail & Related papers  (2020-10-21T20:28:33Z)

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.