KOALA: A Kalman Optimization Algorithm with Loss Adaptivity

• URL: http://arxiv.org/abs/2107.03331v3
• Date: Mon, 24 Mar 2025 12:12:36 GMT
• Title: KOALA: A Kalman Optimization Algorithm with Loss Adaptivity
• Authors: Aram Davtyan, Sepehr Sameni, Llukman Cerkezi, Givi Meishvilli, Adam Bielski, Paolo Favaro,
• Abstract summary: We show that when training neural networks the loss function changes over (it gradient) time due to the randomized selection of a subset of the samples.<n>We propose to consider the loss as a noisy observation with respect to some reference.<n>This interpretation of the loss allows us to adopt Kalman filtering as an gradient, as its formulation is designed to estimate unknown parameters from noisy measurements.
• Score: 21.93777064606377
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Optimization is often cast as a deterministic problem, where the solution is found through some iterative procedure such as gradient descent. However, when training neural networks the loss function changes over (iteration) time due to the randomized selection of a subset of the samples. This randomization turns the optimization problem into a stochastic one. We propose to consider the loss as a noisy observation with respect to some reference optimum. This interpretation of the loss allows us to adopt Kalman filtering as an optimizer, as its recursive formulation is designed to estimate unknown parameters from noisy measurements. Moreover, we show that the Kalman Filter dynamical model for the evolution of the unknown parameters can be used to capture the gradient dynamics of advanced methods such as Momentum and Adam. We call this stochastic optimization method KOALA, which is short for Kalman Optimization Algorithm with Loss Adaptivity. KOALA is an easy to implement, scalable, and efficient method to train neural networks. We provide convergence analysis and show experimentally that it yields parameter estimates that are on par with or better than existing state of the art optimization algorithms across several neural network architectures and machine learning tasks, such as computer vision and language modeling.

Related papers

• Accelerated zero-order SGD under high-order smoothness and overparameterized regime [79.85163929026146]
  We present a novel gradient-free algorithm to solve convex optimization problems. Such problems are encountered in medicine, physics, and machine learning. We provide convergence guarantees for the proposed algorithm under both types of noise.
  arXiv  Detail & Related papers  (2024-11-21T10:26:17Z)
• 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)
• Learning rate adaptive stochastic gradient descent optimization methods: numerical simulations for deep learning methods for partial differential equations and convergence analyses [5.052293146674794]
  It is known that the standard descent (SGD) optimization method, as well as accelerated and adaptive SGD optimization methods such as the Adam fail to converge if the learning rates do not converge to zero. In this work we propose and study a learning-rate-adaptive approach for SGD optimization methods in which the learning rate is adjusted based on empirical estimates.
  arXiv  Detail & Related papers  (2024-06-20T14:07:39Z)
• Random Scaling and Momentum for Non-smooth Non-convex Optimization [38.443430569753026]
  Training neural networks requires a loss function that may be highly irregular, and in particular neither convex nor smooth. Popular training algorithms are based on gradient descent with momentum (SGDM), for which analysis applies only if the loss is either convex or smooth.
  arXiv  Detail & Related papers  (2024-05-16T00:52:03Z)
• Fine-Tuning Adaptive Stochastic Optimizers: Determining the Optimal Hyperparameter $ε$ via Gradient Magnitude Histogram Analysis [0.7366405857677226]
  We introduce a new framework based on the empirical probability density function of the loss's magnitude, termed the "gradient magnitude histogram" We propose a novel algorithm using gradient magnitude histograms to automatically estimate a refined and accurate search space for the optimal safeguard.
  arXiv  Detail & Related papers  (2023-11-20T04:34:19Z)
• Low-rank extended Kalman filtering for online learning of neural networks from streaming data [71.97861600347959]
  We propose an efficient online approximate Bayesian inference algorithm for estimating the parameters of a nonlinear function from a potentially non-stationary data stream. The method is based on the extended Kalman filter (EKF), but uses a novel low-rank plus diagonal decomposition of the posterior matrix. In contrast to methods based on variational inference, our method is fully deterministic, and does not require step-size tuning.
  arXiv  Detail & Related papers  (2023-05-31T03:48:49Z)
• A Particle-based Sparse Gaussian Process Optimizer [5.672919245950197]
  We present a new swarm-swarm-based framework utilizing the underlying dynamical process of descent. The biggest advantage of this approach is greater exploration around the current state before deciding descent descent.
  arXiv  Detail & Related papers  (2022-11-26T09:06:15Z)
• Optimal Rates for Random Order Online Optimization [60.011653053877126]
  We study the citetgarber 2020online, where the loss functions may be chosen by an adversary, but are then presented online in a uniformly random order. We show that citetgarber 2020online algorithms achieve the optimal bounds and significantly improve their stability.
  arXiv  Detail & Related papers  (2021-06-29T09:48:46Z)
• Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes [4.355567556995855]
  We propose Avare, a simple and efficient algorithm for adaptive importance sampling for finite-sum optimization and sampling with decreasing step-sizes. Under standard technical conditions, we show that Avare achieves $mathcalO(T2/3)$ and $mathcalO(T5/6)$ dynamic regret for SGD and SGLD respectively when run with $mathcalO(T5/6)$ step sizes.
  arXiv  Detail & Related papers  (2021-03-23T00:28:15Z)
• Meta-Solver for Neural Ordinary Differential Equations [77.8918415523446]
  We investigate how the variability in solvers' space can improve neural ODEs performance. We show that the right choice of solver parameterization can significantly affect neural ODEs models in terms of robustness to adversarial attacks.
  arXiv  Detail & Related papers  (2021-03-15T17:26:34Z)
• Slowly Varying Regression under Sparsity [5.22980614912553]
  We present the framework of slowly hyper regression under sparsity, allowing regression models to exhibit slow and sparse variations. We suggest a procedure that reformulates as a binary convex algorithm. We show that the resulting model outperforms competing formulations in comparable times across various datasets.
  arXiv  Detail & Related papers  (2021-02-22T04:51:44Z)
• Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering [53.523517926927894]
  We explore the use of exact per-sample Hessian-vector products and gradients to construct self-tuning quadratics. We prove that our model-based procedure converges in noisy gradient setting. This is an interesting step for constructing self-tuning quadratics.
  arXiv  Detail & Related papers  (2020-11-09T22:07:30Z)
• Robust, Accurate Stochastic Optimization for Variational Inference [68.83746081733464]
  We show that common optimization methods lead to poor variational approximations if the problem is moderately large. Motivated by these findings, we develop a more robust and accurate optimization framework by viewing the underlying algorithm as producing a Markov chain.
  arXiv  Detail & Related papers  (2020-09-01T19:12:11Z)
• NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-End Learning and Control [22.120942106939122]
  We propose the use of adaptive search as a building block for general, non- neural optimization operations. We benchmark it against two existing alternatives on a synthetic energy-based structured task, and showcase its use in optimal control applications.
  arXiv  Detail & Related papers  (2020-06-22T03:40:36Z)
• Convergence of adaptive algorithms for weakly convex constrained optimization [59.36386973876765]
  We prove the $mathcaltilde O(t-1/4)$ rate of convergence for the norm of the gradient of Moreau envelope. Our analysis works with mini-batch size of $1$, constant first and second order moment parameters, and possibly smooth optimization domains.
  arXiv  Detail & Related papers  (2020-06-11T17:43:19Z)
• Stochastic batch size for adaptive regularization in deep network optimization [63.68104397173262]
  We propose a first-order optimization algorithm incorporating adaptive regularization applicable to machine learning problems in deep learning framework. We empirically demonstrate the effectiveness of our algorithm using an image classification task based on conventional network models applied to commonly used benchmark datasets.
  arXiv  Detail & Related papers  (2020-04-14T07:54:53Z)

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.