On Sequential Loss Approximation for Continual Learning

• URL: http://arxiv.org/abs/2405.16498v2
• Date: Sun, 24 Nov 2024 05:18:42 GMT
• Title: On Sequential Loss Approximation for Continual Learning
• Authors: Menghao Waiyan William Zhu, Ercan Engin Kuruoğlu,
• Abstract summary: We introduce for continual learning Autodiff Quadratic Consolidation (AQC) and Neural Consolidation (NC) AQC approximates the previous loss function with a quadratic function, and NC approximates the previous loss function with a neural network. We empirically study these methods in class-incremental learning, for which regularization-based methods produce unsatisfactory results.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce for continual learning Autodiff Quadratic Consolidation (AQC), which approximates the previous loss function with a quadratic function, and Neural Consolidation (NC), which approximates the previous loss function with a neural network. Although they are not scalable to large neural networks, they can be used with a fixed pre-trained feature extractor. We empirically study these methods in class-incremental learning, for which regularization-based methods produce unsatisfactory results, unless combined with replay. We find that for small datasets, quadratic approximation of the previous loss function leads to poor results, even with full Hessian computation, and NC could significantly improve the predictive performance, while for large datasets, when used with a fixed pre-trained feature extractor, AQC provides superior predictive performance. We also find that using tanh-output features can improve the predictive performance of AQC. In particular, in class-incremental Split MNIST, when a Convolutional Neural Network (CNN) with tanh-output features is pre-trained on EMNIST Letters and used as a fixed pre-trained feature extractor, AQC can achieve predictive performance comparable to joint training.

Related papers

• YOSO: You-Only-Sample-Once via Compressed Sensing for Graph Neural Network Training [9.02251811867533]
  YOSO (You-Only-Sample-Once) is an algorithm designed to achieve efficient training while preserving prediction accuracy. YOSO not only avoids costly computations in traditional compressed sensing (CS) methods, such as orthonormal basis calculations, but also ensures high-probability accuracy retention.
  arXiv  Detail & Related papers  (2024-11-08T16:47:51Z)
• Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms [80.37846867546517]
  We show how to train eight different neural networks with custom objectives. We exploit their second-order information via their empirical Fisherssian matrices. We apply Loss Lossiable algorithms to achieve significant improvements for less differentiable algorithms.
  arXiv  Detail & Related papers  (2024-10-24T18:02:11Z)
• Unrolled denoising networks provably learn optimal Bayesian inference [54.79172096306631]
  We prove the first rigorous learning guarantees for neural networks based on unrolling approximate message passing (AMP) For compressed sensing, we prove that when trained on data drawn from a product prior, the layers of the network converge to the same denoisers used in Bayes AMP.
  arXiv  Detail & Related papers  (2024-09-19T17:56:16Z)
• Minimizing Chebyshev Prototype Risk Magically Mitigates the Perils of Overfitting [1.6574413179773757]
  We develop multicomponent loss functions that reduce intra-class feature correlation and maximize inter-class feature distance. We implement the terms of the Chebyshev Prototype Risk (CPR) bound into our Explicit CPR loss function. Our training algorithm reduces overfitting and improves upon previous approaches in many settings.
  arXiv  Detail & Related papers  (2024-04-10T15:16:04Z)
• What to Do When Your Discrete Optimization Is the Size of a Neural Network? [24.546550334179486]
  Machine learning applications using neural networks involve solving discrete optimization problems. classical approaches used in discrete settings do not scale well to large neural networks. We take continuation path (CP) methods to represent using purely the former and Monte Carlo (MC) methods to represent the latter.
  arXiv  Detail & Related papers  (2024-02-15T21:57:43Z)
• Random Linear Projections Loss for Hyperplane-Based Optimization in Neural Networks [22.348887008547653]
  This work introduces Random Linear Projections (RLP) loss, a novel approach that enhances training efficiency by leveraging geometric relationships within the data. Our empirical evaluations, conducted across benchmark datasets and synthetic examples, demonstrate that neural networks trained with RLP loss outperform those trained with traditional loss functions.
  arXiv  Detail & Related papers  (2023-11-21T05:22:39Z)
• Equation Discovery with Bayesian Spike-and-Slab Priors and Efficient Kernels [57.46832672991433]
  We propose a novel equation discovery method based on Kernel learning and BAyesian Spike-and-Slab priors (KBASS) We use kernel regression to estimate the target function, which is flexible, expressive, and more robust to data sparsity and noises. We develop an expectation-propagation expectation-maximization algorithm for efficient posterior inference and function estimation.
  arXiv  Detail & Related papers  (2023-10-09T03:55:09Z)
• Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants [166.916517335816]
  In this paper, we offer a unified solution to the misalignment dilemma in the three tasks. We propose neural collapse terminus that is a fixed structure with the maximal equiangular inter-class separation for the whole label space. Our method holds the neural collapse optimality in an incremental fashion regardless of data imbalance or data scarcity.
  arXiv  Detail & Related papers  (2023-08-03T13:09:59Z)
• Ordering for Non-Replacement SGD [7.11967773739707]
  We seek to find an ordering that can improve the convergence rates for the non-replacement form of the algorithm. We develop optimal orderings for constant and decreasing step sizes for strongly convex and convex functions. In addition, we are able to combine the ordering with mini-batch and further apply it to more complex neural networks.
  arXiv  Detail & Related papers  (2023-06-28T00:46:58Z)
• Complementary Learning Subnetworks for Parameter-Efficient Class-Incremental Learning [40.13416912075668]
  We propose a rehearsal-free CIL approach that learns continually via the synergy between two Complementary Learning Subnetworks. Our method achieves competitive results against state-of-the-art methods, especially in accuracy gain, memory cost, training efficiency, and task-order.
  arXiv  Detail & Related papers  (2023-06-21T01:43:25Z)
• RF+clust for Leave-One-Problem-Out Performance Prediction [0.9281671380673306]
  We study leave-one-problem-out (LOPO) performance prediction. We analyze whether standard random forest (RF) model predictions can be improved by calibrating them with a weighted average of performance values.
  arXiv  Detail & Related papers  (2023-01-23T16:14:59Z)
• Understanding and Improving Transfer Learning of Deep Models via Neural Collapse [37.483109067209504]
  This work investigates the relationship between neural collapse (NC) and transfer learning for classification problems. We find strong correlation between feature collapse and downstream performance. Our proposed fine-tuning methods deliver good performances while reducing fine-tuning parameters by at least 90%.
  arXiv  Detail & Related papers  (2022-12-23T08:48:34Z)
• Simple Stochastic and Online Gradient DescentAlgorithms for Pairwise Learning [65.54757265434465]
  Pairwise learning refers to learning tasks where the loss function depends on a pair instances. Online descent (OGD) is a popular approach to handle streaming data in pairwise learning. In this paper, we propose simple and online descent to methods for pairwise learning.
  arXiv  Detail & Related papers  (2021-11-23T18:10:48Z)
• Imputation-Free Learning from Incomplete Observations [73.15386629370111]
  We introduce the importance of guided gradient descent (IGSGD) method to train inference from inputs containing missing values without imputation. We employ reinforcement learning (RL) to adjust the gradients used to train the models via back-propagation. Our imputation-free predictions outperform the traditional two-step imputation-based predictions using state-of-the-art imputation methods.
  arXiv  Detail & Related papers  (2021-07-05T12:44:39Z)
• Towards an Understanding of Benign Overfitting in Neural Networks [104.2956323934544]
  Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss. We examine how these benign overfitting phenomena occur in a two-layer neural network setting. We show that it is possible for the two-layer ReLU network interpolator to achieve a near minimax-optimal learning rate.
  arXiv  Detail & Related papers  (2021-06-06T19:08:53Z)
• A generalized quadratic loss for SVM and Deep Neural Networks [0.0]
  We consider some supervised binary classification tasks and a regression task, whereas SVM and Deep Learning, at present, exhibit the best generalization performances. We extend the work [3] on a generalized quadratic loss for learning problems that examines pattern correlations in order to concentrate the learning problem into input space regions where patterns are more densely distributed.
  arXiv  Detail & Related papers  (2021-02-15T15:49:08Z)
• LQF: Linear Quadratic Fine-Tuning [114.3840147070712]
  We present the first method for linearizing a pre-trained model that achieves comparable performance to non-linear fine-tuning. LQF consists of simple modifications to the architecture, loss function and optimization typically used for classification.
  arXiv  Detail & Related papers  (2020-12-21T06:40:20Z)
• Short-Term Memory Optimization in Recurrent Neural Networks by Autoencoder-based Initialization [79.42778415729475]
  We explore an alternative solution based on explicit memorization using linear autoencoders for sequences. We show how such pretraining can better support solving hard classification tasks with long sequences. We show that the proposed approach achieves a much lower reconstruction error for long sequences and a better gradient propagation during the finetuning phase.
  arXiv  Detail & Related papers  (2020-11-05T14:57:16Z)
• Multi-task Supervised Learning via Cross-learning [102.64082402388192]
  We consider a problem known as multi-task learning, consisting of fitting a set of regression functions intended for solving different tasks. In our novel formulation, we couple the parameters of these functions, so that they learn in their task specific domains while staying close to each other. This facilitates cross-fertilization in which data collected across different domains help improving the learning performance at each other task.
  arXiv  Detail & Related papers  (2020-10-24T21:35:57Z)
• Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint [35.5156045701898]
  We provide a novel viewpoint of regularization-based continual learning by formulating it as a second-order Taylor approximation of the loss function of each task. Based on this viewpoint, we study the optimization aspects (i.e., convergence) as well as generalization properties (i.e., finite-sample guarantees) of regularization-based continual learning.
  arXiv  Detail & Related papers  (2020-06-19T06:08:40Z)
• Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks [50.42141893913188]
  We study a distributed variable for large-scale AUC for a neural network as with a deep neural network. Our model requires a much less number of communication rounds and still a number of communication rounds in theory. Our experiments on several datasets show the effectiveness of our theory and also confirm our theory.
  arXiv  Detail & Related papers  (2020-05-05T18:08:23Z)
• Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
  Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques. We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
  arXiv  Detail & Related papers  (2020-02-03T04:11:13Z)

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.