Non-convergence to the optimal risk for Adam and stochastic gradient descent optimization in the training of deep neural networks

• URL: http://arxiv.org/abs/2503.01660v1
• Date: Mon, 03 Mar 2025 15:36:01 GMT
• Title: Non-convergence to the optimal risk for Adam and stochastic gradient descent optimization in the training of deep neural networks
• Authors: Thang Do, Arnulf Jentzen, Adrian Riekert,
• Abstract summary: It remains an open question to prove or disprove convergence of the true risk of SGD optimization methods to optimal true risk value in the training of DNNs.<n>In the training of any arbitrary fully-connected feedforward DNN it does not hold that the true risk of the considered converges in probability to the optimal true risk value.
• Score: 5.052293146674794
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the omnipresent use of stochastic gradient descent (SGD) optimization methods in the training of deep neural networks (DNNs), it remains, in basically all practically relevant scenarios, a fundamental open problem to provide a rigorous theoretical explanation for the success (and the limitations) of SGD optimization methods in deep learning. In particular, it remains an open question to prove or disprove convergence of the true risk of SGD optimization methods to the optimal true risk value in the training of DNNs. In one of the main results of this work we reveal for a general class of activations, loss functions, random initializations, and SGD optimization methods (including, for example, standard SGD, momentum SGD, Nesterov accelerated SGD, Adagrad, RMSprop, Adadelta, Adam, Adamax, Nadam, Nadamax, and AMSGrad) that in the training of any arbitrary fully-connected feedforward DNN it does not hold that the true risk of the considered optimizer converges in probability to the optimal true risk value. Nonetheless, the true risk of the considered SGD optimization method may very well converge to a strictly suboptimal true risk value.

Related papers

• Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality [52.906438147288256]
  We show that our algorithm can identify the globally optimal reward and policy under certain neural network structures. This is the first IRL algorithm with a non-asymptotic convergence guarantee that provably achieves global optimality.
  arXiv  Detail & Related papers  (2025-03-22T21:16:08Z)
• Global-Decision-Focused Neural ODEs for Proactive Grid Resilience Management [50.34345101758248]
  We propose predict-all-then-optimize-globally (PATOG), a framework that integrates outage prediction with globally optimized interventions. Our approach ensures spatially and temporally coherent decision-making, improving both predictive accuracy and operational efficiency. Experiments on synthetic and real-world datasets demonstrate significant improvements in outage prediction consistency and grid resilience.
  arXiv  Detail & Related papers  (2025-02-25T16:15:35Z)
• Non-convergence to global minimizers in data driven supervised deep learning: Adam and stochastic gradient descent optimization provably fail to converge to global minimizers in the training of deep neural networks with ReLU activation [3.6185342807265415]
  It remains an open problem of research to explain the success and the limitations of SGD methods in rigorous theoretical terms.<n>In this work we prove for a large class of SGD methods that the considered does with high probability not converge to global minimizers of the optimization problem.<n>The general non-convergence results of this work do not only apply to the plain vanilla standard SGD method but also to a large class of accelerated and adaptive SGD methods.
  arXiv  Detail & Related papers  (2024-10-14T14:11:37Z)
• 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)
• Non-convergence of Adam and other adaptive stochastic gradient descent optimization methods for non-vanishing learning rates [3.6185342807265415]
  Deep learning algorithms are the key ingredients in many artificial intelligence (AI) systems. Deep learning algorithms are typically consisting of a class of deep neural networks trained by a gradient descent (SGD) optimization method.
  arXiv  Detail & Related papers  (2024-07-11T00:10:35Z)
• Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization [59.758009422067]
  We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. We propose a new uncertainty Bellman equation (UBE) whose solution converges to the true posterior variance over values. We introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC) that can be applied for either risk-seeking or risk-averse policy optimization.
  arXiv  Detail & Related papers  (2023-12-07T15:55:58Z)
• Risk-sensitive Markov Decision Process and Learning under General Utility Functions [3.069335774032178]
  Reinforcement Learning (RL) has gained substantial attention across diverse application domains and theoretical investigations.<n>We consider a scenario where the decision-maker seeks to optimize a general utility function of the cumulative reward in the framework of a decision process (MDP)<n>We propose a modified value iteration algorithm that employs an epsilon-covering over the space of cumulative reward.<n>In the absence of a simulator, our algorithm, designed with an upper-confidence-bound exploration approach, identifies a near-optimal policy.
  arXiv  Detail & Related papers  (2023-11-22T18:50:06Z)
• Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks [59.142826407441106]
  We study the generalization behavior of shallow neural networks (SNNs) by leveraging the concept of algorithmic stability. We consider gradient descent (GD) and gradient descent (SGD) to train SNNs, for both of which we develop consistent excess bounds.
  arXiv  Detail & Related papers  (2022-09-19T18:48:00Z)
• Benign Underfitting of Stochastic Gradient Descent [72.38051710389732]
  We study to what extent may gradient descent (SGD) be understood as a "conventional" learning rule that achieves generalization performance by obtaining a good fit training data. We analyze the closely related with-replacement SGD, for which an analogous phenomenon does not occur and prove that its population risk does in fact converge at the optimal rate.
  arXiv  Detail & Related papers  (2022-02-27T13:25:01Z)
• Convergence proof for stochastic gradient descent in the training of deep neural networks with ReLU activation for constant target functions [1.7149364927872015]
  gradient descent (SGD) type optimization methods perform very effectively in the training of deep neural networks (DNNs) In this work we study SGD type optimization methods in the training of fully-connected feedforward DNNs with rectified linear unit (ReLU) activation.
  arXiv  Detail & Related papers  (2021-12-13T11:45:36Z)

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.