SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.08484 · ICLR · 2024

FOSI: Hybrid First and Second Order Optimization

Assaf Schuster, Hadar Sivan, Moshe Gabel

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
hsivan/fosi canonical 0 of 1
FunctionStatusWhere it lives
loss_fn Not yet run hsivan/fosi/examples/fosi_torch_example.py
code served (permissive licence) · get_code("a0b5a0ec8b3915d2")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Popular machine learning approaches forgo second-order information due to the difficulty of computing curvature in high dimensions. We present FOSI, a novel meta-algorithm that improves the performance of any base first-order optimizer by efficiently incorporating second-order information during the optimization process. In each iteration, FOSI implicitly splits the function into two quadratic functions defined on orthogonal subspaces, then uses a second-order method to minimize the first, and the base optimizer to minimize the other. We formally analyze FOSI's convergence and the conditions under which it improves a base optimizer. Our empirical evaluation demonstrates that FOSI improves the convergence rate and optimization time of first-order methods such as Heavy-Ball and Adam, and outperforms second-order methods (K-FAC and L-BFGS).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2302.08484")
get_code_for_paper("2302.08484")
have("2302.08484")

Connect an agent — have() is free.