Sanket Thakur·Jun 22From RLVR to Curriculum RFT and back: Building a Self-Improving GSM8K Pipeline for QwenIn the last post, I implemented Reinforcement Learning with Verifiable Rewards (RLVR) from scratch and trained Qwen-2.5–0.5B on GSM8K using…
InData Science CollectivebyAllohvk·Sep 22, 2025MCMC & the art of Sampling without SamplingStory, Intuition & the gentle Math behind the greatest algorithm of the 20th centuryA response icon7A response icon7
Fabian Owuor·Jan 27, 2025Lattice-Based Signatures and Rejection Sampling: An Introduction to Modern Cryptographic TechniquesThe rapid evolution of quantum computing poses a significant threat to traditional cryptographic systems, such as RSA and elliptic curve…
Garrett Hurst·Jan 25, 2025[Statistics by Example]: Rejection SamplingA step-by-step walk through with math and python code
InTDS ArchivebyOliver S·Jan 10, 2023Introduction to Sampling MethodsImplementing inverse transform sampling, rejection sampling and importance sampling in PythonA response icon3A response icon3
Aras Kayvan·Aug 28, 2022Synthetic data generationA while ago I did some work on the generation of synthetic data from existing real data. This resulted in a small python package that…A response icon1A response icon1
InTDS ArchivebyKapil Sachdeva·Feb 15, 2021What is Rejection Sampling?Rejection sampling is a Monte Carlo algorithm to sample data from a sophisticated (“difficult to sample from”) distribution.A response icon6A response icon6
Papers in 100 Lines of Code·Feb 7, 2021Variational Inference with Normalizing Flows in 100 lines of code — reverse KL divergenceIf you are working in science, chances are that you have encountered a density that you can only evaluate to a constant factor. If you…A response icon1A response icon1
InTDS ArchivebyMengsay Loem·Jul 25, 2020Monte Carlo Integration and Sampling MethodsIntegration Approximation and Random Number GeneratorA response icon3A response icon3