Break a Lag: Triple Exponential Moving Average for Enhanced Optimization

• URL: http://arxiv.org/abs/2306.01423v3
• Date: Mon, 09 Dec 2024 16:59:29 GMT
• Title: Break a Lag: Triple Exponential Moving Average for Enhanced Optimization
• Authors: Roi Peleg, Yair Smadar, Teddy Lazebnik, Assaf Hoogi,
• Abstract summary: We introduce Fast Adaptive Moment Estimation (FAME), a novel optimization technique that leverages the power of Triple Exponential Moving Average. FAME enhances responsiveness to data dynamics, mitigates trend identification lag, and optimize learning efficiency. Our comprehensive evaluation encompasses different computer vision tasks including image classification, object detection, and semantic segmentation, integrating FAME into 30 distinct architectures.
• Score: 2.0199251985015434
• License:
• Abstract: The performance of deep learning models is critically dependent on sophisticated optimization strategies. While existing optimizers have shown promising results, many rely on first-order Exponential Moving Average (EMA) techniques, which often limit their ability to track complex gradient trends accurately. This fact can lead to a significant lag in trend identification and suboptimal optimization, particularly in highly dynamic gradient behavior. To address this fundamental limitation, we introduce Fast Adaptive Moment Estimation (FAME), a novel optimization technique that leverages the power of Triple Exponential Moving Average. By incorporating an advanced tracking mechanism, FAME enhances responsiveness to data dynamics, mitigates trend identification lag, and optimizes learning efficiency. Our comprehensive evaluation encompasses different computer vision tasks including image classification, object detection, and semantic segmentation, integrating FAME into 30 distinct architectures ranging from lightweight CNNs to Vision Transformers. Through rigorous benchmarking against state-of-the-art optimizers, FAME demonstrates superior accuracy and robustness. Notably, it offers high scalability, delivering substantial improvements across diverse model complexities, architectures, tasks, and benchmarks.

Related papers

• Understanding Optimization in Deep Learning with Central Flows [53.66160508990508]
  We show that an RMS's implicit behavior can be explicitly captured by a "central flow:" a differential equation. We show that these flows can empirically predict long-term optimization trajectories of generic neural networks.
  arXiv  Detail & Related papers  (2024-10-31T17:58:13Z)
• Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate [105.86576388991713]
  We introduce a normalized gradient difference (NGDiff) algorithm, enabling us to have better control over the trade-off between the objectives. We provide a theoretical analysis and empirically demonstrate the superior performance of NGDiff among state-of-the-art unlearning methods on the TOFU and MUSE datasets.
  arXiv  Detail & Related papers  (2024-10-29T14:41:44Z)
• Improving Instance Optimization in Deformable Image Registration with Gradient Projection [7.6061804149819885]
  Deformable image registration is inherently a multi-objective optimization problem. These conflicting objectives often lead to poor optimization outcomes. Deep learning methods have recently gained popularity in this domain due to their efficiency in processing large datasets.
  arXiv  Detail & Related papers  (2024-10-21T08:27:13Z)
• HGSLoc: 3DGS-based Heuristic Camera Pose Refinement [13.393035855468428]
  Visual localization refers to the process of determining camera poses and orientation within a known scene representation. In this paper, we propose HGSLoc, which integrates 3D reconstruction with a refinement strategy to achieve higher pose estimation accuracy. Our method demonstrates a faster rendering speed and higher localization accuracy compared to NeRF-based neural rendering approaches.
  arXiv  Detail & Related papers  (2024-09-17T06:48:48Z)
• Track Everything Everywhere Fast and Robustly [46.362962852140015]
  We propose a novel test-time optimization approach for efficiently tracking any pixel in a video. We introduce a novel invertible deformation network, CaDeX++, which factorizes the function representation into a local spatial-temporal feature grid. Our experiments demonstrate a substantial improvement in training speed (more than textbf10 times faster), robustness, and accuracy in tracking over the SoTA optimization-based method OmniMotion.
  arXiv  Detail & Related papers  (2024-03-26T17:58:22Z)
• Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers [109.52244418498974]
  We propose a novel textscAdmeta (textbfADouble exponential textbfMov averagtextbfE textbfAdaptive and non-adaptive momentum) framework. We provide two implementations, textscAdmetaR and textscAdmetaS, the former based on RAdam and the latter based on SGDM.
  arXiv  Detail & Related papers  (2023-07-02T18:16:06Z)
• Learning Large-scale Neural Fields via Context Pruned Meta-Learning [60.93679437452872]
  We introduce an efficient optimization-based meta-learning technique for large-scale neural field training. We show how gradient re-scaling at meta-test time allows the learning of extremely high-quality neural fields. Our framework is model-agnostic, intuitive, straightforward to implement, and shows significant reconstruction improvements for a wide range of signals.
  arXiv  Detail & Related papers  (2023-02-01T17:32:16Z)
• Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision [74.9260745577362]
  This paper proposes a unified optimization-inspired learning framework to aggregate Generative, Discriminative, and Corrective (GDC) principles. We construct three propagative modules to effectively solve the optimization models with flexible combinations. Experiments across varied low-level vision tasks validate the efficacy and adaptability of GDC.
  arXiv  Detail & Related papers  (2020-12-10T03:24:53Z)
• 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)
• Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives [73.15276998621582]
  We propose a generic feature learning mechanism to advance CNN training with enhanced generalization ability. Partially inspired by DSN, we fork delicately designed side branches from the intermediate layers of a given neural network. Experiments on both category and instance recognition tasks demonstrate the substantial improvements of our proposed method.
  arXiv  Detail & Related papers  (2020-03-24T09:56:13Z)

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.