I’m quite excited by this work. Principled justification of various techniques for MELBO, insights into feature multiplicity, a potential generalized procedure for selecting steering coefficients… all in addition to making large progress on the problem of MELBO via e.g. password-locked MATH and vanilla activation-space adversarial attacks.
I’m quite excited by this work. Principled justification of various techniques for MELBO, insights into feature multiplicity, a potential generalized procedure for selecting steering coefficients… all in addition to making large progress on the problem of MELBO via e.g. password-locked MATH and vanilla activation-space adversarial attacks.