paper-with-me

홈 › Papers

Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems

2025-06-04 · Yujun Kim, Jaeyoung Cha, Chulhee Yun

Recent theoretical results demonstrate that the convergence rates of permutation-based SGD (e.g., random reshuffling SGD) are faster than uniform-sampling SGD; however, these studies focus mainly on the large epoch regime, where the number of epochs $K$ exceeds the condition number $\kappa$. In contrast, little is known when $K$ is smaller than $\kappa$, and it is still a challenging open question whether permutation-based SGD can converge faster in this small epoch regime (Safran and Shamir, 2021). As a step toward understanding this gap, we study the naive deterministic variant, Incremental Gradient Descent (IGD), on smooth and strongly convex functions. Our lower bounds reveal that for the small epoch regime, IGD can exhibit surprisingly slow convergence even when all component functions are strongly convex. Furthermore, when some component functions are allowed to be nonconvex, we prove that the optimality gap of IGD can be significantly worse throughout the small epoch regime. Our analyses reveal that the convergence properties of permutation-based SGD in the small epoch regime may vary drastically depending on the assumptions on component functions. Lastly, we supplement the paper with tight upper and lower bounds for IGD in the large epoch regime.

📄 PDF Abstract BibTeX arXiv:2506.04126

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…
Focus 설명 없음

Similar Papers 제목 키워드 기반

Pairwise Neural Networks (PairNets) with Low Memory for Fast On-Device Applications

2020-02-10 · Luna M. Zhang

A traditional artificial neural network (ANN) is normally trained slowly by a gradient descent algorithm, such as the backpropagation algorithm, since a large number of hyperparameters of the ANN need to be fine-tuned wi…

Hyperparameter OptimizationIncremental Learning

A Unified Analysis of Stochastic Gradient Descent with Arbitrary Data Permutations and Beyond

2025-01-27 · Yipeng Li, Xinchen Lyu, Zhenyu Liu

We aim to provide a unified convergence analysis for permutation-based Stochastic Gradient Descent (SGD), where data examples are permuted before each epoch. By examining the relations among permutations, we categorize e…

Federated Learning

Correlated Noise in Epoch-Based Stochastic Gradient Descent: Implications for Weight Variances

2023-06-08 · Marcel Kühn, Bernd Rosenow

Stochastic gradient descent (SGD) has become a cornerstone of neural network optimization, yet the noise introduced by SGD is often assumed to be uncorrelated over time, despite the ubiquity of epoch-based training. In t…

ATM: Improving Model Merging by Alternating Tuning and Merging

2024-11-05 · Luca Zhou, Daniele Solombrino, Donato Crisostomi, Maria Sofia Bucarelli 외

Model merging has recently emerged as a cost-efficient paradigm for multi-task learning. Among current approaches, task arithmetic stands out for its simplicity and effectiveness. In this paper, we motivate the effective…

Federated LearningMulti-Task LearningTask Arithmetic

Occam Gradient Descent

2024-05-30 · B. N. Kausik

Deep learning neural network models must be large enough to adapt to their problem domain, while small enough to avoid overfitting training data during gradient descent. To balance these competing demands, overprovisione…

image-classificationImage ClassificationLearning TheoryModel Compression