arXiv (All)
open access
Same Loss, Different Gradients
Differentiable learning typically assumes that the scalar objective evaluated in the forward pass and the gradient supplied to the optimizer in the backward pass describe the same mathematical object. We show that this correspondence can fail when probabilistic objectives rely on finite special-func
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Near-Optimal Exact-Value Zeroth-Order Complexity for Smooth Strongly Convex Optimization#1012895
- On the Convergence of a Noisy Gradient Method for Non-convex Distributed Resource Allocation: Saddle Point Escape#670365
- On the Convergence of a Noisy Gradient Method for Non-convex Distributed Resource Allocation: Saddle Point Escape#668300
- The Complexity of Convex Optimization with Mismatched Geometry#1117622
- Optimization, Learning Algorithms and Applications : 5th International Conference, OL2A 2025, Sesti Levante, Italy, April 28–30, 2025, Proceedings, Part I / edited by Ana I. Pereira, Florbela P. Fernandes, João P. Coelho, João P. Teixeira, José Lima, Maria F. Pacheco, Luca Oneto, Rui P. Lopes#995914
Record · ID 1143387
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive