paper-with-me

Papers

Efficiently Vectorized MCMC on Modern Accelerators

2025-03-20 · Hugh Dance, Pierre Glaser, Peter Orbanz, Ryan Adams

With the advent of automatic vectorization tools (e.g., JAX's $\texttt{vmap}$), writing multi-chain MCMC algorithms is often now as simple as invoking those tools on single-chain code. Whilst convenient, for various MCMC algorithms this results in a synchronization problem -- loosely speaking, at each iteration all chains running in parallel must wait until the last chain has finished drawing its sample. In this work, we show how to design single-chain MCMC algorithms in a way that avoids synchronization overheads when vectorizing with tools like $\texttt{vmap}$ by using the framework of finite state machines (FSMs). Using a simplified model, we derive an exact theoretical form of the obtainable speed-ups using our approach, and use it to make principled recommendations for optimal algorithm design. We implement several popular MCMC algorithms as FSMs, including Elliptical Slice Sampling, HMC-NUTS, and Delayed Rejection, demonstrating speed-ups of up to an order of magnitude in experiments.

📄 PDF Abstract BibTeX arXiv:2503.17405

Code (1)

hwdance/jax-fsm-mcmc 공식 구현 jax

Similar Papers 제목 키워드 기반

SynJax: Structured Probability Distributions for JAX

2023-08-07 · Miloš Stanojević, Laurent Sartran

The development of deep learning software libraries enabled significant progress in the field by allowing users to focus on modeling, while letting the library to take care of the tedious and time-consuming task of optim…

A Case for Quantifying Statistical Robustness of Specialized Probabilistic AI Accelerators

2019-10-27 · Xiangyu Zhang, Sayan Mukherjee, Alvin R. Lebeck

Statistical machine learning often uses probabilistic algorithms, such as Markov Chain Monte Carlo (MCMC), to solve a wide range of problems. Many accelerators are proposed using specialized hardware to address sampling …

Diagnostic

evosax: JAX-based Evolution Strategies

2022-12-08 · Robert Tjarko Lange

The deep learning revolution has greatly been accelerated by the 'hardware lottery': Recent advances in modern hardware accelerators and compilers paved the way for large-scale batch gradient optimization. Evolutionary o…

CPUScheduling

Leveraging ASIC AI Chips for Homomorphic Encryption

2025-01-13 · Jianming Tong, Tianhao Huang, Leo de Castro, Anirudh Itagi 외

Cloud-based services are making the outsourcing of sensitive client data increasingly common. Although homomorphic encryption (HE) offers strong privacy guarantee, it requires substantially more resources than computing …

Beyond Application End-Point Results: Quantifying Statistical Robustness of MCMC Accelerators

2020-03-05 · Xiangyu Zhang, Ramin Bashizade, Yicheng Wang, Cheng Lyu 외

Statistical machine learning often uses probabilistic algorithms, such as Markov Chain Monte Carlo (MCMC), to solve a wide range of problems. Probabilistic computations, often considered too slow on conventional processo…

Diagnostic