MALI: A memory efficient and reverse accurate integrator for Neural ODEs

• URL: http://arxiv.org/abs/2102.04668v1
• Date: Tue, 9 Feb 2021 06:33:47 GMT
• Title: MALI: A memory efficient and reverse accurate integrator for Neural ODEs
• Abstract summary: Memory-efficient ALF integrator (MALI) for Neural ordinary differential equations (Neural ODEs) MALI is first to enable feasible training of a Neural ODE on ImageNet and outperform a well-tuned ResNet. For time series modeling, MALI significantly outperforms the adjoint method. For continuous generative models, MALI achieves new state-of-the-art performance.
• Score: 11.786863362728868
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural ordinary differential equations (Neural ODEs) are a new family of deep-learning models with continuous depth. However, the numerical estimation of the gradient in the continuous case is not well solved: existing implementations of the adjoint method suffer from inaccuracy in reverse-time trajectory, while the naive method and the adaptive checkpoint adjoint method (ACA) have a memory cost that grows with integration time. In this project, based on the asynchronous leapfrog (ALF) solver, we propose the Memory-efficient ALF Integrator (MALI), which has a constant memory cost \textit{w.r.t} number of solver steps in integration similar to the adjoint method, and guarantees accuracy in reverse-time trajectory (hence accuracy in gradient estimation). We validate MALI in various tasks: on image recognition tasks, to our knowledge, MALI is the first to enable feasible training of a Neural ODE on ImageNet and outperform a well-tuned ResNet, while existing methods fail due to either heavy memory burden or inaccuracy; for time series modeling, MALI significantly outperforms the adjoint method; and for continuous generative models, MALI achieves new state-of-the-art performance.

Related papers

• Symplectic Neural Networks for learning Generalized Hamiltonians [5.793251439782513]
  Hamiltonian Neural Networks (HNNs) integrate physical priors into neural models by learning a system's Hamiltonian, improving generalization and sample efficiency.<n>For simulations to faithfully reflect the long-term behavior of Hamiltonian systems, it is essential to use symplectic iteration, which preserve the system's geometric structure.<n>In our work, we explore this alternate method of HNN training under noisy observation of trajectories with our HNN model based on an implicit symplectic integrator.
  arXiv  Detail & Related papers  (2026-06-25T13:36:44Z)
• Fast Image Super-Resolution via Consistency Rectified Flow [65.54302099728712]
  Diffusion models (DMs) have demonstrated remarkable success in real-world image super-resolution (SR)<n>Recent efforts have introduced few- or single-step solutions, but existing methods inefficiently model the process from noisy input.<n>We propose FlowSR, a novel approach that reformulates the SR problem as a rectified flow from low-resolution (LR) to high-resolution (HR) images.
  arXiv  Detail & Related papers  (2026-05-12T16:42:38Z)
• Parallel Diffusion Solver via Residual Dirichlet Policy Optimization [88.7827307535107]
  Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature.<n>Existing solver-based acceleration methods often face significant image quality degradation under a low-dimensional budget.<n>We propose the Ensemble Parallel Direction solver (dubbed as EPD-EPr), a novel ODE solver that mitigates these errors by incorporating multiple gradient parallel evaluations in each step.
  arXiv  Detail & Related papers  (2025-12-28T05:48:55Z)
• Mixed Precision Training of Neural ODEs [1.3382837742547355]
  This paper presents a mixed precision training framework for neural ODEs.<n>It combines explicit ODE solvers with a custom backpropagation scheme.<n>It achieves approximately 50% memory reduction and up to 2x speedup while maintaining accuracy comparable to single-precision training.
  arXiv  Detail & Related papers  (2025-10-27T16:32:56Z)
• Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning [59.6658995479243]
  We propose texttext-Perturb-and-Merge (P&M), a novel continual learning framework that integrates model merging into the CL paradigm to avoid forgetting.<n>Through theoretical analysis, we minimize the total loss increase across all tasks and derive an analytical solution for the optimal merging coefficient.<n>Our proposed approach achieves state-of-the-art performance on several continual learning benchmark datasets.
  arXiv  Detail & Related papers  (2025-05-28T14:14:19Z)
• Implicit Neural Differential Model for Spatiotemporal Dynamics [5.1854032131971195]
  We introduce Im-PiNDiff, a novel implicit physics-integrated neural differentiable solver for stabletemporal dynamics.<n>Inspired by deep equilibrium models, Im-PiNDiff advances the state using implicit fixed-point layers, enabling robust long-term simulation.<n>Im-PiNDiff achieves superior predictive performance, enhanced numerical stability, and substantial reductions in memory and cost.
  arXiv  Detail & Related papers  (2025-04-03T04:07:18Z)
• A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning [74.80956524812714]
  We tackle the general differentiable meta learning problem that is ubiquitous in modern deep learning. These problems are often formalized as Bi-Level optimizations (BLO) We introduce a novel perspective by turning a given BLO problem into a ii optimization, where the inner loss function becomes a smooth distribution, and the outer loss becomes an expected loss over the inner distribution.
  arXiv  Detail & Related papers  (2024-10-14T12:10:06Z)
• 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)
• Meta-learning to Calibrate Gaussian Processes with Deep Kernels for Regression Uncertainty Estimation [43.23399636191726]
  We propose a meta-learning method for calibrating deep kernel GPs for improving regression uncertainty estimation performance. The proposed method meta-learns how to calibrate uncertainty using data from various tasks by minimizing the test expected calibration error. Our experiments demonstrate that the proposed method improves uncertainty estimation performance while keeping high regression performance.
  arXiv  Detail & Related papers  (2023-12-13T07:58:47Z)
• On Tuning Neural ODE for Stability, Consistency and Faster Convergence [0.0]
  We propose a first-order Nesterov's accelerated gradient (NAG) based ODE-solver which is proven to be tuned vis-a-vis CCS conditions. We empirically demonstrate the efficacy of our approach by training faster, while achieving better or comparable performance against neural-ode.
  arXiv  Detail & Related papers  (2023-12-04T06:18:10Z)
• Guaranteed Approximation Bounds for Mixed-Precision Neural Operators [83.64404557466528]
  We build on intuition that neural operator learning inherently induces an approximation error. We show that our approach reduces GPU memory usage by up to 50% and improves throughput by 58% with little or no reduction in accuracy.
  arXiv  Detail & Related papers  (2023-07-27T17:42:06Z)
• Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows [54.050498411883495]
  We develop a novel training method for generative models, such as Generative Adversarial Networks and Normalizing Flows. We show that achieving a specified precision-recall trade-off corresponds to minimizing a unique $f$-divergence from a family we call the textitPR-divergences. Our approach improves the performance of existing state-of-the-art models like BigGAN in terms of either precision or recall when tested on datasets such as ImageNet.
  arXiv  Detail & Related papers  (2023-05-30T10:07:17Z)
• Loop Unrolled Shallow Equilibrium Regularizer (LUSER) -- A Memory-Efficient Inverse Problem Solver [26.87738024952936]
  In inverse problems we aim to reconstruct some underlying signal of interest from potentially corrupted and often ill-posed measurements. We propose an LU algorithm with shallow equilibrium regularizers (L) These implicit models are as expressive as deeper convolutional networks, but far more memory efficient during training.
  arXiv  Detail & Related papers  (2022-10-10T19:50:37Z)
• A memory-efficient neural ODE framework based on high-level adjoint differentiation [4.063868707697316]
  We present a new neural ODE framework, PNODE, based on high-level discrete algorithmic differentiation. We show that PNODE achieves the highest memory efficiency when compared with other reverse-accurate methods.
  arXiv  Detail & Related papers  (2022-06-02T20:46:26Z)
• Continuous-Time Meta-Learning with Forward Mode Differentiation [65.26189016950343]
  We introduce Continuous Meta-Learning (COMLN), a meta-learning algorithm where adaptation follows the dynamics of a gradient vector field. Treating the learning process as an ODE offers the notable advantage that the length of the trajectory is now continuous. We show empirically its efficiency in terms of runtime and memory usage, and we illustrate its effectiveness on a range of few-shot image classification problems.
  arXiv  Detail & Related papers  (2022-03-02T22:35:58Z)
• Neural Control Variates [71.42768823631918]
  We show that a set of neural networks can face the challenge of finding a good approximation of the integrand. We derive a theoretically optimal, variance-minimizing loss function, and propose an alternative, composite loss for stable online training in practice. Specifically, we show that the learned light-field approximation is of sufficient quality for high-order bounces, allowing us to omit the error correction and thereby dramatically reduce the noise at the cost of negligible visible bias.
  arXiv  Detail & Related papers  (2020-06-02T11:17:55Z)

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.