1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Balancing Rates And Variance Via Adaptive Batch-Sizes In First-Order Stochastic Optimization

Balancing Rates And Variance Via Adaptive Batch-Sizes In First-Order Stochastic Optimization

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

Stochastic gradient descent is a canonical tool for addressing stochastic optimization problems, and forms the bedrock of modern machine learning and statistics. In this work, we seek to balance the fact that attenuating step-sizes is required for exact a

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Balancing Rates And Variance Via Adaptive Batch-Sizes In First-Order Stochastic Optimization

00:13:39

0 views

Stochastic gradient descent is a canonical tool for addressing stochastic optimization problems, and forms the bedrock of modern machine learning and statistics. In this work, we seek to balance the fact that attenuating step-sizes is required for exact a