Activation-Descent Regularization for Input Optimization of ReLU Networks

• URL: http://arxiv.org/abs/2406.00494v1
• Date: Sat, 1 Jun 2024 16:46:46 GMT
• Title: Activation-Descent Regularization for Input Optimization of ReLU Networks
• Authors: Hongzhan Yu, Sicun Gao,
• Abstract summary: We present a new approach for input optimization of ReLU networks that explicitly takes into account the effect of changes in activation patterns. We convert the discrete space of activation patterns into differentiable representations and propose regularization terms that improve each descent step. Our experiments demonstrate the effectiveness of the proposed input-optimization methods for improving the state-of-the-art in various areas.
• Score: 14.855585146315741
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a new approach for input optimization of ReLU networks that explicitly takes into account the effect of changes in activation patterns. We analyze local optimization steps in both the input space and the space of activation patterns to propose methods with superior local descent properties. To accomplish this, we convert the discrete space of activation patterns into differentiable representations and propose regularization terms that improve each descent step. Our experiments demonstrate the effectiveness of the proposed input-optimization methods for improving the state-of-the-art in various areas, such as adversarial learning, generative modeling, and reinforcement learning.

Related papers

• Model Uncertainty in Evolutionary Optimization and Bayesian Optimization: A Comparative Analysis [5.6787965501364335]
  Black-box optimization problems are common in many real-world applications. These problems require optimization through input-output interactions without access to internal workings. Two widely used gradient-free optimization techniques are employed to address such challenges. This paper aims to elucidate the similarities and differences in the utilization of model uncertainty between these two methods.
  arXiv  Detail & Related papers  (2024-03-21T13:59:19Z)
• Hallmarks of Optimization Trajectories in Neural Networks: Directional Exploration and Redundancy [75.15685966213832]
  We analyze the rich directional structure of optimization trajectories represented by their pointwise parameters. We show that training only scalar batchnorm parameters some while into training matches the performance of training the entire network.
  arXiv  Detail & Related papers  (2024-03-12T07:32:47Z)
• Beyond Single-Model Views for Deep Learning: Optimization versus Generalizability of Stochastic Optimization Algorithms [13.134564730161983]
  This paper adopts a novel approach to deep learning optimization, focusing on gradient descent (SGD) and its variants. We show that SGD and its variants demonstrate performance on par with flat-minimas like SAM, albeit with half the gradient evaluations. Our study uncovers several key findings regarding the relationship between training loss and hold-out accuracy, as well as the comparable performance of SGD and noise-enabled variants.
  arXiv  Detail & Related papers  (2024-03-01T14:55:22Z)
• Analyzing and Enhancing the Backward-Pass Convergence of Unrolled Optimization [50.38518771642365]
  The integration of constrained optimization models as components in deep networks has led to promising advances on many specialized learning tasks. A central challenge in this setting is backpropagation through the solution of an optimization problem, which often lacks a closed form. This paper provides theoretical insights into the backward pass of unrolled optimization, showing that it is equivalent to the solution of a linear system by a particular iterative method. A system called Folded Optimization is proposed to construct more efficient backpropagation rules from unrolled solver implementations.
  arXiv  Detail & Related papers  (2023-12-28T23:15:18Z)
• Acceleration in Policy Optimization [50.323182853069184]
  We work towards a unifying paradigm for accelerating policy optimization methods in reinforcement learning (RL) by integrating foresight in the policy improvement step via optimistic and adaptive updates. We define optimism as predictive modelling of the future behavior of a policy, and adaptivity as taking immediate and anticipatory corrective actions to mitigate errors from overshooting predictions or delayed responses to change. We design an optimistic policy gradient algorithm, adaptive via meta-gradient learning, and empirically highlight several design choices pertaining to acceleration, in an illustrative task.
  arXiv  Detail & Related papers  (2023-06-18T15:50:57Z)
• Efficient Training of Physics-Informed Neural Networks with Direct Grid Refinement Algorithm [0.0]
  This research presents the development of an innovative algorithm tailored for the adaptive sampling of residual points within the framework of Physics-Informed Neural Networks (PINNs) By addressing the limitations inherent in existing adaptive sampling techniques, our proposed methodology introduces a direct mesh refinement approach that effectively ensures both computational efficiency and adaptive point placement.
  arXiv  Detail & Related papers  (2023-06-14T07:04:02Z)
• Randomized Adversarial Style Perturbations for Domain Generalization [49.888364462991234]
  We propose a novel domain generalization technique, referred to as Randomized Adversarial Style Perturbation (RASP) The proposed algorithm perturbs the style of a feature in an adversarial direction towards a randomly selected class, and makes the model learn against being misled by the unexpected styles observed in unseen target domains. We evaluate the proposed algorithm via extensive experiments on various benchmarks and show that our approach improves domain generalization performance, especially in large-scale benchmarks.
  arXiv  Detail & Related papers  (2023-04-04T17:07:06Z)
• Latent Variable Representation for Reinforcement Learning [131.03944557979725]
  It remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of model-based reinforcement learning. We provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism principle. In particular, we propose a computationally efficient planning algorithm with UCB exploration by incorporating kernel embeddings of latent variable models.
  arXiv  Detail & Related papers  (2022-12-17T00:26:31Z)
• Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimization [8.37077056358265]
  We propose a new computational primitive for building invariant networks based instead on optimization. We provide empirical and theoretical corroboration of the efficiency gains and soundness of our proposed method. We demonstrate its utility in constructing an efficient invariant network for a simple hierarchical object detection task.
  arXiv  Detail & Related papers  (2022-03-09T19:04:08Z)
• Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis [54.94682858474711]
  Class Activation Mapping (CAM) approaches provide an effective visualization by taking weighted averages of the activation maps. We propose a novel set of metrics to quantify explanation maps, which show better effectiveness and simplify comparisons between approaches.
  arXiv  Detail & Related papers  (2021-04-20T21:34:24Z)

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.