Hello! Thanks for the great work. Can you please clarify the intuition behind using the weighted sum of probabilities as the score for the sample ? I can see from the discussion that this might be motivated by ensuring more stable training perhaps, but more details would be very helpful. Thanks!
Hello! Thanks for the great work. Can you please clarify the intuition behind using the weighted sum of probabilities as the score for the sample ? I can see from the discussion that this might be motivated by ensuring more stable training perhaps, but more details would be very helpful. Thanks!