Craft Beer
Starting from malt, hops, and yeast, this guide introduces common terms like ABV and IBU, covers styles such as Lager, Wheat, IPA, Stout, …
blog
Unlocking TikTok Region Switching Without SIM Card Removal
Documenting attempts to use TikTok on iOS without removing the SIM card, including Shadowrocket proxy configuration, downloading and …
The Dirichlet Distribution in Federated Learning: From Probability Vectors to Non-IID Data Partitioning
Introduces the definition, concentration parameters, and statistical properties of the Dirichlet distribution, distinguishes between two …
Efficiency Analysis in Distributed Machine Learning
Analyzing the stochastic runtime of synchronous, asynchronous, and K-worker SGD, and discussing the time to reach target accuracy and …
Convergence Analysis in Federated Learning (Part 5)
Deriving non-convex stationary point bounds and strongly convex error bounds under full participation from FedAvg's local updates, …
Convergence Analysis in Distributed Machine Learning (Part 4)
Deriving strong convexity convergence bounds for synchronous, asynchronous, and K-Async SGD, clarifying assumptions of independent sampling, …
Information Theory in Privacy-Preserving Computation: How to Understand and Measure Information Leakage
Starting from the attacker's observations and auxiliary information, this article introduces entropy, conditional mutual information, the …
Privacy Leakage in Deep Learning: What Models, Predictions, and Gradients Reveal
Reviewing membership inference, attribute inference, model inversion, and training data extraction; deriving the recoverability of …
Convergence Analysis in Deep Learning (Part 3)
Deriving strong convex error bounds and non-convex stationary point bounds for mini-batch SGD under assumptions of conditionally unbiased …
Convergence Analysis in Deep Learning (Part 2)
Derive first-order method convergence bounds under smooth/non-smooth and convex/non-convex conditions, clarifying step sizes, output points, …