No abstract

No abstract

No abstract

In this paper, we study contrastive learning from an optimization perspective, aiming to analyze and address a fundamental issue of existing contrastive learning methods that either rely on a large batch size or a large dictionary. We consider a global objective for contrastive learning, which contrasts each positive pair with all negative pairs for an anchor point. From the optimization perspective, we explain why existing methods such as SimCLR requires a large batch size in order to achieve a satisfactory result. In order to remove such requirement, we propose a memory-efficient Stochastic Optimization algorithm for solving the Global objective of Contrastive Learning of Representations, named SogCLR. We show that its optimization error is negligible under a reasonable condition after a sufficient number of iterations or is diminishing for a slightly different global contrastive objective. Empirically, we demonstrate that on ImageNet with a batch size 256, SogCLR achieves a performance of 69.4% for top-1 linear evaluation accuracy using ResNet-50, which is on par with SimCLR (69.3%) with a large batch size 8,192. We also attempt to show that the proposed optimization technique is generic and can be applied to solving other contrastive losses, e.g., two-way contrastive losses for bimodal contrastive learning.

At present, China's economy is facing a stage of reform, in which the changes in the social financing structure are the most significant. In order to improve the liquidity and stability of traditional monetary policy, the People's Bank of China has proposed the Medium-term Lending Facility. The research of this article combs and analyzes the monetary policy of Medium-term Lending facility. The reasons for its occurrence, its characteristics, as well as its influence are introduced in detail, and data analysis is used to prove it. At the end, the article also put forward suggestions for future development changes.