Research map / Learning theory and algorithms / Sample complexity
HOGWILD!-Gibbs can be PanAccurate
Constantinos Daskalakis, Nishanth Dikkala, Siddhartha Jayanti
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 asynchronous rather than sequential Gibbs updates | Gibbs sampling under Dobrushin's condition · Functions Lipschitz in the d-th power of Hamming distance | expectation bias: K.(C(\tau, \alpha,d)\log^d n+1) | Mixed |
| Use asynchronous rather than sequential Gibbs updates | Gibbs sampling under Dobrushin's condition · Degree-d polynomials of high-temperature Ising models | variance: \mbox{\bf Var}\left[ f(Y_t) \right] \le \inftynorm{a}^2C(d,\alpha,\tau) n^{d} | No clear effect |
| Increase the number of asynchronous processors | HOGWILD!-Gibbs on CW(n, 0.5) · CW(n, 0.5) | average read delay: approximately 0.4 steps | Hurt |
| Increase n | HOGWILD!-Gibbs on CW(n, 0.5) · CW(n, 0.5) | average read delay | No clear effect |
Closest papers by meaning
- Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling (ICML 2016 · similarity 0.92)
- Minibatch Gibbs Sampling on Large Graphical Models (ICML 2018 · similarity 0.86)
- Scan Order in Gibbs Sampling: Models in Which it Matters and Bounds on How Much (NeurIPS 2016 · similarity 0.86)
- Fast Doubly-Adaptive MCMC to Estimate the Gibbs Partition Function with Weak Mixing Time Bounds (NeurIPS 2021 · similarity 0.86)
- Online sampling from log-concave distributions (NeurIPS 2019 · similarity 0.86)
- NETS: A Non-equilibrium Transport Sampler (ICML 2025 · similarity 0.83)
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.
