USPS tracking numbers
I noticed the other day that an app on my phone assumed that a long number was a USPS tracking number. I wondered how it decided that and did a little research. I assumed there was some structure to the number, at least a check sum if not more than
Read moreZero-Concentrated Differential Privacy
Differential privacy can be rigid and overly conservative in practice, and so finding ways to relax pure differential privacy while retaining its benefits is an active area of research. Two approaches to doing this are concentrated differential privacy [1] and Rényi differential privacy [3]. Differential privacy quantifies the potential impact
Read moreDifferentially private stochastic gradient descent
Let’s work our way up to differentially private stochastic gradient descent (DP-SGD) a little at a time. We’ll first look at gradient descent, then stochastic gradient descent, then finally differentially private stochastic gradient descent. Gradient descent We’ll start with gradient descent. Suppose you have a function of several variables f(x)
Read moreAn intuitive introduction to text embeddings
Text embeddings are key to LLMs and convert text into vector coordinates.
Read moreUsing dimensional analysis to check probability calculations
Probability density functions are independent of physical units. The normal distribution, for example, works just as well when describing weights or times. But sticking in units anyway is useful. Normal distribution example Suppose you’re trying to remember the probability density function for the normal distribution. Is the correct form or
Read moreRandomized response and local differential privacy
Differential privacy protects user privacy by adding randomness as necessary to the results of queries to a database containing private data. Local differential privacy protects user privacy by adding randomness before the data is inserted to the database. Using the visualization from this post, differential privacy takes the left and
Read more6 Factors That Determine Whether You Will Succeed or Fail
A blueprint to success to guide you in your journey towards your goalsContinue reading on Better Programming »
Read moreLocalisation in Xcode 15
Utilise new String Catalogs to internationalize your Swift appsContinue reading on Better Programming »
Read morePATE framework for differentially private machine learning
Machine learning models can memorize fragments of their training data and return these fragments verbatim. I’ve seen instances, for example, where I believe an LLM returned phrases verbatim from this site. It’s easy to imagine how medical data might leak this way. How might you prevent this? And how might
Read moreCode Migration: Ampere Porting Advisor for x86 to AAarch64
Ampere Porting Advisor offers a streamlined migration process, allowing developers to save time and effort and automate manual steps involved in porting code. Continue reading Code Migration: Ampere Porting Advisor for x86 to AAarch64 on SitePoint.
Read more