SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.14591 · 2020

Bidirectional compression in heterogeneous settings for distributed or federated learning with partial participation: tight convergence guarantees

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 2 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
copy not recorded — 2 of 3
FunctionStatusWhere it lives
batch_step_size Ran this paper's copy was not recorded; identical code first harvested from philipco/mcm-bidirectional-compression
pointer only · get_code("e6a79a6be3304f23")
iid_step_size Ran this paper's copy was not recorded; identical code first harvested from philipco/mcm-bidirectional-compression
pointer only · get_code("ed195ba6ad252639")
deacreasing_step_size Not yet run this paper's copy was not recorded; identical code first harvested from philipco/mcm-bidirectional-compression
pointer only · get_code("c178c850d8327c3d")

Repositories linked to this paper

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

Abstract

We introduce a framework - Artemis - to tackle the problem of learning in a distributed or federated setting with communication constraints and device partial participation. Several workers (randomly sampled) perform the optimization process using a central server to aggregate their computations. To alleviate the communication cost, Artemis allows to compress the information sent in both directions (from the workers to the server and conversely) combined with a memory mechanism. It improves on existing algorithms that only consider unidirectional compression (to the server), or use very strong assumptions on the compression operator, and often do not take into account devices partial participation. We provide fast rates of convergence (linear up to a threshold) under weak assumptions on the stochastic gradients (noise's variance bounded only at optimal point) in non-i.i.d. setting, highlight the impact of memory for unidirectional and bidirectional compression, analyze Polyak-Ruppert averaging. We use convergence in distribution to obtain a lower bound of the asymptotic variance that highlights practical limits of compression. We propose two approaches to tackle the challenging case of devices partial participation and provide experimental results to demonstrate the validity of our analysis.

For agents

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

get_harvested_code_for_paper("2006.14591")
get_code_for_paper("2006.14591")
have("2006.14591")

Connect an agent — have() is free.