I worked for three years designing custom low-latency point-to-point microwave radios for HFT for this very reason. They didn't need very high bandwidths (their long-haul network was less than 200 Mbit, whereas in New York/New Jersey we had about 5 Gbps because the hops were much shorter and they had licenses for more RF bandwidth at a higher frequency).
At those time scales, the difference is so large, it was incredible what they were willing to pay to build these networks!
I somewhat regret not specialising in RF/comms in my EE degree - this side of HFT sounds like a fascinating line of work (Trading at the Speed of Light was a great read).
I doubt there's much here that's cutting edge. Any digital processing that's done in typical radio's to correct for channel impairments is avoided as it just adds latency. Meanwhile LTE is using as many digital techniques as possible to maximize bandwidth (MIMO, HARQ, OFMDA)
Haha, you got us :) - in terms of the digital side yes, kind of. We’d even try to not have any digital in the path if possible on some hops! We did have things like LDPC (and different FEC on control packets) but it was definitely not as complex as LTE or newer cellular or WiFi standards. But what was avoided digitally meant far more work going into the analogue side to improve SNR, dynamic range, NPR etc. through the signal chain.
At those time scales, the difference is so large, it was incredible what they were willing to pay to build these networks!