Research map / Optimization / Distributed and compressed
A Stochastic Newton Algorithm for Distributed Convex Optimization
Brian Bullins, Kumar Kshitij Patel, Ohad Shamir, Nathan Srebro, Blake Woodworth
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use FedSN-Lite instead of FedAc, Minibatch SGD and Local SGD | distributed convex optimization · LIBSVM a9a logistic regression, M in {100,200} | loss / relative sub-optimality | Improved |
| Add internal regularization to FedAc (1e-2 to 1e-6) for general convex objectives | FedAc · LIBSVM a9a unregularized | training/validation loss | No clear effect |
| Add Polyak momentum beta in {0.1,...,0.9} to baselines | Minibatch SGD, Local SGD, FedAc · LIBSVM a9a | loss | No clear effect |
| Vary regularization strength mu between 1e-4 and 1e-6 | all algorithms · LIBSVM a9a regularized | relative sub-optimality | Mixed |
Closest papers by meaning
- Distributed Stochastic Variance Reduced Gradient Methods by Sampling Extra Data with Replacement (JMLR 2017 · similarity 0.91)
- Optimal Convergence Rates for Convex Distributed Optimization in Networks (JMLR 2019 · similarity 0.90)
- S-D-RSM: Stochastic Distributed Regularized Splitting Method for Large-Scale Convex Optimization Problems (AAAI 2026 · similarity 0.89)
- Gradient Sparsification for Communication-Efficient Distributed Optimization (NeurIPS 2018 · similarity 0.89)
- Universal Gradient Methods for Stochastic Convex Optimization (ICML 2024 · similarity 0.89)
- Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers (ICML 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
