Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning

• URL: http://arxiv.org/abs/2311.15161v5
• Date: Sat, 21 Sep 2024 01:23:30 GMT
• Title: Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning
• Authors: Jiaqi Li, Yuanhao Lai, Rui Wang, Changjian Shui, Sabyasachi Sahoo, Charles X. Ling, Shichun Yang, Boyu Wang, Christian Gagné, Fan Zhou,
• Abstract summary: Continual learning aims to learn a series of tasks sequentially without forgetting the knowledge acquired from the previous ones. We propose the Hessian Aware Low-Rank Perturbation algorithm for continual learning.
• Score: 19.850893012601638
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual learning aims to learn a series of tasks sequentially without forgetting the knowledge acquired from the previous ones. In this work, we propose the Hessian Aware Low-Rank Perturbation algorithm for continual learning. By modeling the parameter transitions along the sequential tasks with the weight matrix transformation, we propose to apply the low-rank approximation on the task-adaptive parameters in each layer of the neural networks. Specifically, we theoretically demonstrate the quantitative relationship between the Hessian and the proposed low-rank approximation. The approximation ranks are then globally determined according to the marginal increment of the empirical loss estimated by the layer-specific gradient and low-rank approximation error. Furthermore, we control the model capacity by pruning less important parameters to diminish the parameter growth. We conduct extensive experiments on various benchmarks, including a dataset with large-scale tasks, and compare our method against some recent state-of-the-art methods to demonstrate the effectiveness and scalability of our proposed method. Empirical results show that our method performs better on different benchmarks, especially in achieving task order robustness and handling the forgetting issue. The source code is at https://github.com/lijiaqi/HALRP.

Related papers

• Gradient Descent Efficiency Index [0.0]
  This study introduces a new efficiency metric, Ek, designed to quantify the effectiveness of each iteration. The proposed metric accounts for both the relative change in error and the stability of the loss function across iterations. Ek has the potential to guide more informed decisions in the selection and tuning of optimization algorithms in machine learning applications.
  arXiv  Detail & Related papers  (2024-10-25T10:22:22Z)
• FLOPS: Forward Learning with OPtimal Sampling [1.694989793927645]
  gradient-based computation methods have recently gained focus for learning with only forward passes, also referred to as queries. Conventional forward learning consumes enormous queries on each data point for accurate gradient estimation through Monte Carlo sampling. We propose to allocate the optimal number of queries over each data in one batch during training to achieve a good balance between estimation accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2024-10-08T12:16:12Z)
• An Effective Dynamic Gradient Calibration Method for Continual Learning [11.555822066922508]
  Continual learning (CL) is a fundamental topic in machine learning, where the goal is to train a model with continuously incoming data and tasks. Due to the memory limit, we cannot store all the historical data, and therefore confront the catastrophic forgetting'' problem. We develop an effective algorithm to calibrate the gradient in each updating step of the model.
  arXiv  Detail & Related papers  (2024-07-30T16:30:09Z)
• Unsupervised Learning of Initialization in Deep Neural Networks via Maximum Mean Discrepancy [74.34895342081407]
  We propose an unsupervised algorithm to find good initialization for input data. We first notice that each parameter configuration in the parameter space corresponds to one particular downstream task of d-way classification. We then conjecture that the success of learning is directly related to how diverse downstream tasks are in the vicinity of the initial parameters.
  arXiv  Detail & Related papers  (2023-02-08T23:23:28Z)
• Efficient Meta-Learning for Continual Learning with Taylor Expansion Approximation [2.28438857884398]
  Continual learning aims to alleviate catastrophic forgetting when handling consecutive tasks under non-stationary distributions. We propose a novel efficient meta-learning algorithm for solving the online continual learning problem. Our method achieves better or on-par performance and much higher efficiency compared to the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-10-03T04:57:05Z)
• Continual Learning via Bit-Level Information Preserving [88.32450740325005]
  We study the continual learning process through the lens of information theory. We propose Bit-Level Information Preserving (BLIP) that preserves the information gain on model parameters. BLIP achieves close to zero forgetting while only requiring constant memory overheads throughout continual learning.
  arXiv  Detail & Related papers  (2021-05-10T15:09:01Z)
• Meta-Regularization: An Approach to Adaptive Choice of the Learning Rate in Gradient Descent [20.47598828422897]
  We propose textit-Meta-Regularization, a novel approach for the adaptive choice of the learning rate in first-order descent methods. Our approach modifies the objective function by adding a regularization term, and casts the joint process parameters.
  arXiv  Detail & Related papers  (2021-04-12T13:13:34Z)
• SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation [81.03485688525133]
  We propose a novel multi-person pose estimation framework, SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation (SIMPLE) Specifically, in the training process, we enable SIMPLE to mimic the pose knowledge from the high-performance top-down pipeline. Besides, SIMPLE formulates human detection and pose estimation as a unified point learning framework to complement each other in single-network.
  arXiv  Detail & Related papers  (2021-04-06T13:12:51Z)
• Adaptive Gradient Method with Resilience and Momentum [120.83046824742455]
  We propose an Adaptive Gradient Method with Resilience and Momentum (AdaRem) AdaRem adjusts the parameter-wise learning rate according to whether the direction of one parameter changes in the past is aligned with the direction of the current gradient. Our method outperforms previous adaptive learning rate-based algorithms in terms of the training speed and the test error.
  arXiv  Detail & Related papers  (2020-10-21T14:49:00Z)
• Reparameterized Variational Divergence Minimization for Stable Imitation [57.06909373038396]
  We study the extent to which variations in the choice of probabilistic divergence may yield more performant ILO algorithms. We contribute a re parameterization trick for adversarial imitation learning to alleviate the challenges of the promising $f$-divergence minimization framework. Empirically, we demonstrate that our design choices allow for ILO algorithms that outperform baseline approaches and more closely match expert performance in low-dimensional continuous-control tasks.
  arXiv  Detail & Related papers  (2020-06-18T19:04:09Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.