Skip to content

Booksellers & Trade Customers: Sign up for online bulk buying at trade.atlanticbooks.com for wholesale discounts

Booksellers: Create Account on our B2B Portal for wholesale discounts

Riemannian Online Learning

by XI Wang , Guodong Shi
Sold out
Current price ₹8,887.00
Original price ₹9,125.00
Original price ₹9,125.00
Original price ₹9,125.00
(-3%)
₹8,887.00
Current price ₹8,887.00

Imported Edition - Ships in 18-21 Days

Free Shipping in India on orders above Rs. 500

Request Bulk Quantity Quote
+91
Book cover type: Paperback
  • ISBN13: 9781638286103
  • Binding: Paperback
  • Subject: N/A
  • Publisher: Now Publishers
  • Publisher Imprint: Now Publishers
  • Publication Date:
  • Pages: 170
  • Original Price: GBP 73.0
  • Language: English
  • Edition: N/A
  • Item Weight: 250 grams
  • BISAC Subject(s): General

Riemannian optimization is a powerful tool for decision-making in situations where the data and decision space are structured as non-flat spaces due to physical constraints and/or underlying symmetries. In emerging fields such as machine learning, quantum computing, biomedical imaging, and robotics, data and decisions often exist in curved, non-Euclidean spaces due to physical constraints or underlying symmetries. Riemannian online optimization provides a new framework for handling learning tasks where data arrives sequentially in geometric spaces. This monograph offers a comprehensive overview of online learning over Riemannian manifolds, and offers a unified overview of the state-of-the-art algorithms for online optimization over Riemannian manifolds. Also presented is a detailed and systematic analysis of achievable regret for those algorithms. The study emphasizes how the curvature of manifolds influences the trade-off between exploration and exploitation, and the performance of the algorithms. After an introduction, Section 2 briefly introduces Riemannian manifolds, together with the preliminary knowledge of Riemannian optimization and Euclidean online optimization. In Section 3, the fundamental Riemannian online gradient descent algorithm under full information feedback is presented, and the achievable regret on both Hadamard manifolds and general manifolds is analyzed. Section 4 extends the Riemannian online gradient descent algorithm to the bandit feedback setting. In Sections 5 and 6, the authors turn to two advanced Riemannian online optimization algorithms designed for dynamic regret minimization, the Riemannian online extra gradient descent and the Riemannian online optimistic gradient descent.

Trusted for over 49 years

Family Owned Company

Secure Payment

All Major Credit Cards/Debit Cards/UPI & More Accepted

New & Authentic Products

India's Largest Distributor

Need Support?

Whatsapp Us