Related papers: Learn2Hop: Learned Optimization on Rough Landscapes

Learn2Hop: Learned Optimization on Rough Landscapes

URL: http://arxiv.org/abs/2107.09661v1
Date: Tue, 20 Jul 2021 17:57:19 GMT
Title: Learn2Hop: Learned Optimization on Rough Landscapes
Authors: Amil Merchant, Luke Metz, Sam Schoenholz, Ekin Dogus Cubuk
Abstract summary: We propose adapting developments in metalearning to many-minima problems by learning an optimization algorithm for various loss configurations. We show that our learneds show promising generalizations with efficiency gains on never before elements or compositions.
Score: 19.30760260383794
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Optimization of non-convex loss surfaces containing many local minima remains a critical problem in a variety of domains, including operations research, informatics, and material design. Yet, current techniques either require extremely high iteration counts or a large number of random restarts for good performance. In this work, we propose adapting recent developments in meta-learning to these many-minima problems by learning the optimization algorithm for various loss landscapes. We focus on problems from atomic structural optimization--finding low energy configurations of many-atom systems--including widely studied models such as bimetallic clusters and disordered silicon. We find that our optimizer learns a 'hopping' behavior which enables efficient exploration and improves the rate of low energy minima discovery. Finally, our learned optimizers show promising generalization with efficiency gains on never before seen tasks (e.g. new elements or compositions). Code will be made available shortly.

Related papers

Can Learned Optimization Make Reinforcement Learning Less Difficult? [70.5036361852812]
We consider whether learned optimization can help overcome reinforcement learning difficulties. Our method, Learned Optimization for Plasticity, Exploration and Non-stationarity (OPEN), meta-learns an update rule whose input features and output structure are informed by previously proposed to these difficulties.
arXiv Detail & Related papers (2024-07-09T17:55:23Z)
Discovering Preference Optimization Algorithms with and for Large Language Models [50.843710797024805]
offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. We perform objective discovery to automatically discover new state-of-the-art preference optimization algorithms without (expert) human intervention. Experiments demonstrate the state-of-the-art performance of DiscoPOP, a novel algorithm that adaptively blends logistic and exponential losses.
arXiv Detail & Related papers (2024-06-12T16:58:41Z)
A Particle-based Sparse Gaussian Process Optimizer [5.672919245950197]
We present a new swarm-swarm-based framework utilizing the underlying dynamical process of descent. The biggest advantage of this approach is greater exploration around the current state before deciding descent descent.
arXiv Detail & Related papers (2022-11-26T09:06:15Z)
Improved Algorithms for Neural Active Learning [74.89097665112621]
We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. We introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work.
arXiv Detail & Related papers (2022-10-02T05:03:38Z)
Learning for Robust Combinatorial Optimization: Algorithm and Application [26.990988571097827]
Learning to optimize (L2O) has emerged as a promising approach to solving optimization problems by exploiting the strong prediction power of neural networks. In this paper, we propose a novel learning-based optimization, called LRCO, which quickly outputs a robust solution in the presence of uncertain context. Our results highlight that LRCO can greatly reduce the worst-case cost and runtime, while having a very low complexity.
arXiv Detail & Related papers (2021-12-20T07:58:50Z)
Fighting the curse of dimensionality: A machine learning approach to finding global optima [77.34726150561087]
This paper shows how to find global optima in structural optimization problems. By exploiting certain cost functions we either obtain the global at best or obtain superior results at worst when compared to established optimization procedures.
arXiv Detail & Related papers (2021-10-28T09:50:29Z)
Reverse engineering learned optimizers reveals known and novel mechanisms [50.50540910474342]
Learneds are algorithms that can themselves be trained to solve optimization problems. Our results help elucidate the previously murky understanding of how learneds work, and establish tools for interpreting future learneds.
arXiv Detail & Related papers (2020-11-04T07:12:43Z)
Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves [53.37905268850274]
We introduce a new, hierarchical, neural network parameterized, hierarchical with access to additional features such as validation loss to enable automatic regularization. Most learneds have been trained on only a single task, or a small number of tasks. We train ours on thousands of tasks, making use of orders of magnitude more compute, resulting in generalizes that perform better to unseen tasks.
arXiv Detail & Related papers (2020-09-23T16:35:09Z)
Learning fine-grained search space pruning and heuristics for combinatorial optimization [5.72274610208488]
We propose a framework for leveraging machine learning techniques to scale-up exact optimization algorithms. Our framework learns the relatively simpler task of pruning the elements in order to reduce the size of the problem instances. We show that our framework can prune a large fraction of the input graph and still detect almost all of the maximum cliques.
arXiv Detail & Related papers (2020-01-05T13:10:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.