Towards stable training of parallel continual learning

• URL: http://arxiv.org/abs/2407.08214v1
• Date: Thu, 11 Jul 2024 06:31:04 GMT
• Title: Towards stable training of parallel continual learning
• Authors: Li Yuepan, Fan Lyu, Yuyang Li, Wei Feng, Guangcan Liu, Fanhua Shang,
• Abstract summary: Parallel Continual Learning tasks investigate the training methods for continual learning with multi-source input. Multiple tasks need to be trained simultaneously, leading to severe training instability in PCL. This paper introduces Stable Parallel Continual Learning (SPCL), a novel approach that enhances the training stability of PCL for both forward and backward propagation.
• Score: 27.774814769630453
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Parallel Continual Learning (PCL) tasks investigate the training methods for continual learning with multi-source input, where data from different tasks are learned as they arrive. PCL offers high training efficiency and is well-suited for complex multi-source data systems, such as autonomous vehicles equipped with multiple sensors. However, at any time, multiple tasks need to be trained simultaneously, leading to severe training instability in PCL. This instability manifests during both forward and backward propagation, where features are entangled and gradients are conflict. This paper introduces Stable Parallel Continual Learning (SPCL), a novel approach that enhances the training stability of PCL for both forward and backward propagation. For the forward propagation, we apply Doubly-block Toeplit (DBT) Matrix based orthogonality constraints to network parameters to ensure stable and consistent propagation. For the backward propagation, we employ orthogonal decomposition for gradient management stabilizes backpropagation and mitigates gradient conflicts across tasks. By optimizing gradients by ensuring orthogonality and minimizing the condition number, SPCL effectively stabilizing the gradient descent in complex optimization tasks. Experimental results demonstrate that SPCL outperforms state-of-the-art methjods and achieve better training stability.

Related papers

• Continual Multimodal Contrastive Learning [70.60542106731813]
  Multimodal contrastive learning (MCL) advances in aligning different modalities and generating multimodal representations in a joint space. However, a critical yet often overlooked challenge remains: multimodal data is rarely collected in a single process, and training from scratch is computationally expensive. In this paper, we formulate CMCL through two specialized principles of stability and plasticity. We theoretically derive a novel optimization-based method, which projects updated gradients from dual sides onto subspaces where any gradient is prevented from interfering with the previously learned knowledge.
  arXiv  Detail & Related papers  (2025-03-19T07:57:08Z)
• Scale-Distribution Decoupling: Enabling Stable and Effective Training of Large Language Models [21.16132396642158]
  Training stability is a persistent challenge in the pre-training of large language models (LLMs) We propose Scale-Distribution Decoupling (SDD), a novel approach that stabilizes training by explicitly decoupling the scale and distribution of the weight matrix in fully-connected layers.
  arXiv  Detail & Related papers  (2025-02-21T14:49:34Z)
• SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning [51.10866035483686]
  High update-to-data (UTD) ratio algorithms in reinforcement learning (RL) improve sample efficiency but incur high computational costs, limiting real-world scalability. We propose Offline Stabilization Phases for Efficient Q-Learning (SPEQ), an RL algorithm that combines low-UTD online training with periodic offline stabilization phases. During these phases, Q-functions are fine-tuned with high UTD ratios on a fixed replay buffer, reducing redundant updates on suboptimal data.
  arXiv  Detail & Related papers  (2025-01-15T09:04:19Z)
• SALE-Based Offline Reinforcement Learning with Ensemble Q-Networks [0.0]
  We propose a model-free actor-critic algorithm that integrates ensemble Q-networks and a gradient diversity penalty from EDAC. Our algorithm achieves higher convergence speed, stability, and performance compared to existing methods.
  arXiv  Detail & Related papers  (2025-01-07T10:22:30Z)
• Continual Task Learning through Adaptive Policy Self-Composition [54.95680427960524]
  CompoFormer is a structure-based continual transformer model that adaptively composes previous policies via a meta-policy network. Our experiments reveal that CompoFormer outperforms conventional continual learning (CL) methods, particularly in longer task sequences.
  arXiv  Detail & Related papers  (2024-11-18T08:20:21Z)
• Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales [13.818149654692863]
  Reinforcement learning (RL) training is inherently unstable due to factors such as moving targets and high gradient variance. In this work, we improve the stability of RL training by adapting the reverse cross entropy (RCE) from supervised learning for noisy data to define a symmetric RL loss.
  arXiv  Detail & Related papers  (2024-05-27T19:28:33Z)
• Q-value Regularized Transformer for Offline Reinforcement Learning [70.13643741130899]
  We propose a Q-value regularized Transformer (QT) to enhance the state-of-the-art in offline reinforcement learning (RL) QT learns an action-value function and integrates a term maximizing action-values into the training loss of Conditional Sequence Modeling (CSM) Empirical evaluations on D4RL benchmark datasets demonstrate the superiority of QT over traditional DP and CSM methods.
  arXiv  Detail & Related papers  (2024-05-27T12:12:39Z)
• Improving Data-aware and Parameter-aware Robustness for Continual Learning [3.480626767752489]
  This paper analyzes that this insufficiency arises from the ineffective handling of outliers. We propose a Robust Continual Learning (RCL) method to address this issue. The proposed method effectively maintains robustness and achieves new state-of-the-art (SOTA) results.
  arXiv  Detail & Related papers  (2024-05-27T11:21:26Z)
• Efficiently Training Deep-Learning Parametric Policies using Lagrangian Duality [55.06411438416805]
  Constrained Markov Decision Processes (CMDPs) are critical in many high-stakes applications. This paper introduces a novel approach, Two-Stage Deep Decision Rules (TS- DDR) to efficiently train parametric actor policies. It is shown to enhance solution quality and to reduce computation times by several orders of magnitude when compared to current state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-23T18:19:47Z)
• Adversarial Training of Two-Layer Polynomial and ReLU Activation Networks via Convex Optimization [40.68266398473983]
  Training neural networks which are robust to adversarial attacks remains an important problem in deep learning. We reformulate the training problems for two-layer ReLU andfty$ activation networks as convex programs. We demonstrate the practical utility of convex adversarial training on large-scale problems.
  arXiv  Detail & Related papers  (2024-05-22T22:08:13Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning [22.287106840756483]
  We show how off-policy learning techniques based on return-conditioned supervised learning (RCSL) are able to circumvent challenges of Bellman completeness. We propose a simple framework called MBRCSL, granting RCSL methods the ability of dynamic programming to stitch together segments from distinct trajectories.
  arXiv  Detail & Related papers  (2023-10-30T07:03:14Z)
• Boosting Offline Reinforcement Learning via Data Rebalancing [104.3767045977716]
  offline reinforcement learning (RL) is challenged by the distributional shift between learning policies and datasets. We propose a simple yet effective method to boost offline RL algorithms based on the observation that resampling a dataset keeps the distribution support unchanged. We dub our method ReD (Return-based Data Rebalance), which can be implemented with less than 10 lines of code change and adds negligible running time.
  arXiv  Detail & Related papers  (2022-10-17T16:34:01Z)
• Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL [0.0]
  Decision Transformer (DT) combines the conditional policy approach and a transformer architecture. DT lacks stitching ability -- one of the critical abilities for offline RL to learn the optimal policy. We propose the Q-learning Decision Transformer (QDT) to address the shortcomings of DT.
  arXiv  Detail & Related papers  (2022-09-08T18:26:39Z)
• Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp [119.69304125647785]
  This paper introduces a concise yet powerful method to construct Continuous Transition. Specifically, we propose to synthesize new transitions for training by linearly interpolating the consecutive transitions. To keep the constructed transitions authentic, we also develop a discriminator to guide the construction process automatically.
  arXiv  Detail & Related papers  (2020-11-30T01:20:23Z)
• Training Generative Adversarial Networks by Solving Ordinary Differential Equations [54.23691425062034]
  We study the continuous-time dynamics induced by GAN training. From this perspective, we hypothesise that instabilities in training GANs arise from the integration error. We experimentally verify that well-known ODE solvers (such as Runge-Kutta) can stabilise training.
  arXiv  Detail & Related papers  (2020-10-28T15:23:49Z)

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.