Dictionary compression isn't really applicable to floating-point data, because it isn't made up of commonly repeated "words" like text is.
Advanced context modeling compression algorithms can work even better than the scheme presented in the article. These are like mini-AIs, and they can recognize patterns more complex than just a string of unchanged bits, and with the appropriate entropy coder, give excellent compression. Or course the processing cost is huge compare to a few bit manipulations, and wouldn't make much sense unless you need extreme compression.